ICPR2020 Program Overview is available on the website. Allocation of papers to Sessions can be found at Program/Main Conference/Oral and Poster Sessions.
PAPER# | TITLE | AUTHORS | AFFILIATION | ORAL/POSTER | SESSION | DATE |
1 | Multi-scale Processing of Noisy Images using Edge Preservation Losses | Ofir, Nati; Keller, Joseph | BIU | Poster | PS T1.5 | DAY 2 – January 13, 2021 |
2 | Boundary Guided Image Translation for Pose Estimation from Ultra-Low Resolution Thermal Sensor | Kurihara, Kohei; Wang, Tianren; Zhang, Teng; Lovell, Brian Carrington | Mitsubishi Electric Corporation | Poster | PS T3.8 | DAY 3 – January 14, 2021 |
5 | Progressive Learning Algorithm for Efficient Person Re-Identification | Li, Zhen; Shao, HanYang; Niu, Liang; Xue, Nian | New York University | Poster | PS T5.7 | DAY 4 – January 15, 2021 |
6 | Image Defocus Analysis for Finger Detection on a Virtual Keyboard | Michio, Miwa; Kenji, Honda; Makoto, Sato | Intelectual Propertyh Coorporation Center | Poster | PS T2.2 | DAY 2 – January 13, 2021 |
8 | EM-Net: Deep Learning for Electron Microscopy Image Segmentation | Khadangi, Afshin; Boudier, Thomas; Rajagopal, Vijay | University of Melbourne | Poster | PS T5.3 | DAY 2 – January 13, 2021 |
9 | Incorporating a Graph-Matching Algorithm into a Muscle Mechanics Model | Santacruz Muñoz, Jose Luis; Serratosa, Francesc | Universitat Rovira i Virgili | Poster | PS T1.5 | DAY 2 – January 13, 2021 |
10 | SIMCO: SIMilarity-Based Object COunting | Godi, Marco; Joppi, Christian; Giachetti, Andrea; Cristani, Marco | University of Verona | Poster | PS T1.5 | DAY 2 – January 13, 2021 |
12 | Learning Graph Matching Substitution Weights Based on a Linear Regression | Algabli, Shaima; Serratosa, Francesc | Universitat Rovira i Virgili | Poster | PS T1.5 | DAY 2 – January 13, 2021 |
14 | Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search | Xiangxiang, Chu; Zhang, Bo; Ma, Hailong; Xu, Ruijun; Li, Qingyuan | Xiaomi | Poster | PS T5.3 | DAY 2 – January 13, 2021 |
17 | Crack Detection As a Weakly-Supervised Problem: Towards Achieving Less Annotation-Intensive Crack Detectors | Inoue, Yuki; Nagayoshi, Hiroto | Hitachi Ltd. | Poster | PS T3.8 | DAY 3 – January 14, 2021 |
19 | Probabilistic Latent Factor Model for Collaborative Filtering with Bayesian Inference | Fang, Jiansheng; Zhang, Xiaoqing; Hu, Yan; Xu, Yanwu; Yang, Ming; Liu, Jiang | Southern University of Science and Technology | Oral | OS T1.4 – PS T1.4 | DAY 2 – January 13, 2021 – DAY 2 – January 13, 2021 |
21 | Activity Recognition Using First-Person-View Cameras Based on Sparse Optical Flows | Kao, Peng-Yuan; Lei, Yan-Jing; Chang, Chia-Hao; Chen, Chu-Song; Lee, Ming-Sui; Hung, Yi-Ping | National Taiwan University | Poster | PS T1.5 | DAY 2 – January 13, 2021 |
23 | Learning Embeddings for Image Clustering: An Empirical Study of Triplet Loss Approaches | Ho, Kalun; Keuper, Janis; Pfreundt, Franz-Josef; Keuper, Margret | Fraunhofer ITWM | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
25 | Local Facial Attribute Transfer through Inpainting | Durall, Ricard; Pfreundt, Franz-Josef; Keuper, Janis | Fraunhofer ITWM | Poster | PS T1.5 | DAY 2 – January 13, 2021 |
26 | Calibration and Absolute Pose Estimation of Trinocular Linear Camera Array for Smart City Applications | Ahrnbom, Martin; Nilsson, Mikael; Ardö, Håkan; Åström, Kalle; Yastremska-Kravchenko, Oksana; Laureshyn, Aliaksei | Lund University | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
32 | Adaptive Remote Sensing Image Attribute Learning for Active Object Detection | Xu, Nuo; Huo, Chunlei; Guo, Jiacheng; Liu, Yiwei; Wang, Jian; PAN, Chunhong | Institute of Automation, CAS | Oral | OS T3.6 – PS T3.7 | DAY 4 – January 15, 2021 – DAY 3 – January 14, 2021 |
34 | Efficient Sentence Embedding Via Semantic Subspace Analysis | Wang, Bin; Chen, Fenxiao; Wang, Yun Cheng; Kuo, C.-C. Jay | University of Southern California | Poster | PS T4.1 | DAY 1 – January 12, 2021 |
35 | MD-kNN: An Instance-Based Approach for Multi-Dimensional Classification | Jia, Bin-Bin; Zhang, Min-Ling | Southeast University | Poster | PS T1.5 | DAY 2 – January 13, 2021 |
40 | MANet: Multimodal Attention Network Based Point-View Fusion for 3D Shape Recognition | Zhao, Yaxin; Jiao, Jichao; Li, Ning; Deng, zhongliang | School of Electronic Engineering , Beijing University of Posts and Telecommunications | Poster | PS T3.8 | DAY 3 – January 14, 2021 |
42 | Fully Convolutional Neural Networks for Raw Eye Tracking Data Segmentation, Generation, and Reconstruction | Fuhl, Wolfgang; Rong, Yao; Kasneci, Enkelejda | Eberhard Karls Universität Tübingen | Poster | PS T1.5 | DAY 2 – January 13, 2021 |
43 | Is the Meta-Learning Idea Able to Improve the Generalization of Deep Neural Networks on the Standard Supervised Learning? | Deng, Xiang; Zhang, Zhongfei | State University of New York at Binghamton | Poster | PS T1.5 | DAY 2 – January 13, 2021 |
45 | Deep Reinforcement Learning on a Budget: 3D Control and Reasoning without a Supercomputer | Beeching, Edward; Dibangoye, Jilles Steeve; Simonin, Olivier; Wolf, Christian | INSA, Lyon | Poster | PS T3.6 | DAY 2 – January 13, 2021 |
46 | CT-UNet: An Improved Neural Network Based on U-Net for Building Segmentation in Remote Sensing Images | Ye, Huanran; Liu, Sheng; Jin, Kun; Cheng, Haohao | Zhejiang University of Technology | Poster | PS T5.3 | DAY 2 – January 13, 2021 |
47 | A Joint Super-Resolution and Deformable Registration Network for 3D Brain Images | Lan, Sheng; Guo, Zhenhua | Tsinghua University | Poster | PS T1.5 | DAY 2 – January 13, 2021 |
48 | ResFPN: Residual Skip Connections in Multi-Resolution Feature Pyramid Networks for Accurate Dense Pixel Matching | Rishav, René Schuster; Battrawy, Ramy; Wasenmüler, Oliver; Stricker, Didier | DFKI | Oral | OS T5.1 – PS T5.1 | DAY 1 – January 12, 2021 – DAY 1 – January 12, 2021 |
50 | Visual Oriented Encoder: Integrating Multimodal and Multi-Scale Contexts for Video Captioning | Yang, Bang; Zou, Yuexian | Peking University | Poster | PS T3.8 | DAY 3 – January 14, 2021 |
51 | Toward online handwriting recognition system based on reinforcement learning theory | Ramzi Zouari, Ramzi; Houcine Boubaker, Houcine; Monji Kherallah, Monji | National School of Engineers of SFAX | Poster | cancelled | cancelled |
54 | Few-Shot Learning Based on Metric Learning Using Class Augmentation | Matsumi, Susumu; Yamada, Keiichi | Meijo University | Poster | PS T1.5 | DAY 2 – January 13, 2021 |
57 | 2D License Plate Recognition based on Automatic Perspective Rectification | Xu, Hui; Guo, Zhao-Hong; Wang, Da-Han; Zhou, Xiang-Dong; Shi, Yu | Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences | Poster | PS T4.3 | DAY 3 – January 14, 2021 |
58 | Automatic Classification of Human Granulosa Cells in Assisted Reproductive Technology Using Vibrational Spectroscopy Imaging | Paolanti, Marina; Frontoni, Emanuele; Gioacchini, Giorgia; Elisabetta, Giorgini; Valentina, Notarstefano; Carlotta, Zacà; Oliana, Carnevali; Borini, Andrea; Mameli, Marco | Università Politecnica delle Marche | Poster | PS T1.5 | DAY 2 January 13, 2021 |
59 | Cascade Saliency Attention Network for Object Detection in Remote Sensing Images | Yu, Dayang; Zhang, Rong; Qin, Shan | USTC | Poster | PS T3.8 | DAY 3 – January 14, 2021 |
60 | Softer Pruning, Incremental Regularization | Cai, Linhang; An, Zhulin; Yang, Chuanguang; Xu, Yongjun | Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China | Poster | PS T1.5 | DAY 2 January 13, 2021 |
61 | A CNN-RNN Framework for Image Annotation from Visual Cues and Social Network Metadata | Tesan, Tobia; Coscia, Pasquale; Ballan, Lamberto | University of Padova | Poster | PS T3.6 | DAY 2 – January 13, 2021 |
62 | Fast Approximate Modelling of the Next Combination Result for Stopping the Text Recognition in a Video | Bulatov, Konstantin; Fedotova, Nadezhda; Arlazarov, Vladimir V. | Smart Engines Service LLC, FRC CSC RAS | Poster | PS T4.3 | DAY 3 – January 14, 2021 |
64 | Sparse-Dense Subspace Clustering | Yang, Shuai; Zhu, Wenqi; Zhu, Yuesheng | Peking University | Poster | PS T1.5 | DAY 2 – January 13, 2021 |
70 | HFP: Hardware-Aware Filter Pruning for Deep Convolutional Neural Networks Acceleration | Yu, Fang; Han, Chuanqi; Wang, Pengcheng; Huang, Ruoran; Huang, Xi; Cui, Li | Institute of Computing Technology, Chinese Academy of Sciences | Poster | PS T1.5 | DAY 2 – January 13, 2021 |
73 | Generating Private Data Surrogates for Vision Related Tasks | Webster, Ryan; Rabin, Julien; Simon, Loic; Jurie, Frederic | CNRS GREYC | Poster | PS T1.5 | DAY 2 – January 13, 2021 |
74 | Leveraging a Weakly Adversarial Paradigm for Joint Learning of Disparity and Confidence Estimation | Poggi, Matteo; Tosi, Fabio; Aleotti, Filippo; Mattoccia, Stefano | University of Bologna | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
77 | Cross-Supervised Joint-Event-Extraction with Heterogeneous Information Networks | Wang, Yue; Xu, Zhuo; Wan, Yao; Bai, Lu; Cui, Lixin; Zhao, Qian; Hancock, Edwin; Yu, Philip | Central University of Finance and Economics | Poster | PS T4.2 | DAY 2 – January 13, 2021 |
78 | Weakly Supervised Body Part Segmentation with Pose Based Part Priors | Yang, Zhengyuan; Li, Yuncheng; Yang, Linjie; Zhang, Ning; Luo, Jiebo | University of Rochester | Oral | OS T2.3 – PS T2.5 | DAY 4 – January 15, 2021 – DAY 4 – January 15, 2021 |
79 | Pose-Based Body Language Recognition for Emotion and Psychiatric Symptom Interpretation | Yang, Zhengyuan; Kay, Amanda; Li, Yuncheng; Cross, Wendi; Luo, Jiebo | University of Rochester | Poster | PS T2.1 | DAY 1 – January 12, 2021 |
81 | Flexible and Adaptive Unsupervised Graph Embedding | Qiang, Qianyao; Zhang, Bin; Li, Yu | Xi’an Jiaotong University | Poster | cancelled | cancelled |
82 | Joint Learning Multiple Curvature Descriptor for 3D Palmprint Recognition | Fei, Lunke; Qin, Jianyang; Zhang, Bob; Wen, Jie; Tian, Chunwei; Liu, Peng; Zhao, Shuping | Guangdong University of Technology | Poster | PS T2.2 | DAY 2 – January 13, 2021 |
83 | Spatial-Related and Scale-Aware Network for Crowd Counting | Li, Lei; Dong, Yuan; Bai, Hongliang | Beijing University of Posts and Telecommunications | Poster | PS T1.5 | DAY 2 – January 13, 2021 |
85 | Hierarchical Mixtures of Generators for Adversarial Learning | Ahmetoglu, Alper; Alpaydin, Ethem | Bogazici University | Oral | OS T1.7 – PS T1.13 | DAY 4 – January 15, 2021 – DAY 4 – January 15, 2021 |
86 | A Scalable Deep Neural Network to Detect Low Quality Images without a Reference | Liu, Zongyi | Amazon.com | Poster | PS T5.1 | DAY 1 – January 12, 2021 |
87 | CNN-Based Repetitive Self-Revised Learning for Photos Aesthetics Imbalanced Classification | Ying, Dai | Iwate Prefectural University | Poster | PS T3.8 | DAY 3 – January 14, 2021 |
88 | Extracting Action Hierarchies from Action Labels and their Use in Deep Action Recognition | Bacharidis, Konstantinos; Argyros, Antonis | Univ. of Crete, FORTH | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
90 | The Effect of Multi-Step Methods on Overestimation in Deep Reinforcement Learning | Meng, Lingheng; Gorbet, Rob; Kulić, Dana | University of Waterloo | Poster | PS T1.5 | DAY 2 – January 13, 2021 |
92 | Cost Volume Refinement for Depth Prediction | Cardoso, L. João; Goncalves, Nuno; Wimmer, Michael | TU Wien | Poster | PS T3.3 | DAY 1 – January 12, 2021 |
93 | Augmented Cyclic Consistency Regularization for Unpaired Image-To-Image Translation | Ohkawa, Takehiko; Inoue, Naoto; Kataoka, Hirokatsu; Inoue, Nakamasa | The University of Tokyo | Poster | PS T1.5 | DAY 2 – January 13, 2021 |
95 | Text Recognition in Real Scenarios with a Few Labeled Samples | Lin, Jinghuang; Zhanzhan, Cheng; Bai, Fan; Niu, Yi; Pu, Shiliang; Zhou, Shuigeng | Fudan University | Poster | PS T1.5 | DAY 2 – January 13, 2021 |
101 | A Delayed Elastic-Net Approach for Performing Adversarial Attacks | Cancela, Brais; Bolon-Canedo, Veronica; Alonso-Betanzos, Amparo | Lidia Group, Department of Computer Science, University of A Coruña, Spain | Poster | PS T1.5 | DAY 2 – January 13, 2021 |
103 | Improving Explainability of Integrated Gradients with Guided Non-Linearity | Kwon, Hyuk Jin; Koo, Hyung Il; Cho, Nam Ik | Seoul National University | Poster | PS T1.5 | DAY 2 – January 13, 2021 |
104 | Can Data Placement Be Effective for Neural Networks Classification Tasks? Introducing the Orthogonal Loss | Cancela, Brais; Bolon-Canedo, Veronica; Alonso-Betanzos, Amparo | Lidia Group, Department of Computer Science, University of A Coruña, Spain | Poster | PS T1.5 | DAY 2 – January 13, 2021 |
105 | Finger Vein Recognition and Intra-Subject Similarity Evaluation of Finger Veins Using the CNN Triplet Loss | Wimmer, Georg; Prommegger, Bernhard; Uhl, Andreas | University of Salzburg | Poster | PS T2.3 | DAY 2 – January 13, 2021 |
106 | MetaMix: Improved Meta-Learning with Interpolation-based Consistency Regularization | Chen, Yangbin; MA, YUN; Ko, Tom; WANG, JIANPING; Li, Qing | City University of Hong Kong | Poster | PS T1.5 | DAY 2 January 13, 2021 |
108 | Creating Classifier Ensembles through Meta-Heuristic Algorithms for Aerial Scene Classification | Ferreira Jr., Álvaro Roberto; de Rosa, Gustavo Henrique; Papa, Joao Paulo; Carneiro, Gustavo; Faria, Fabio Augusto | Federal University of São Paulo | Poster | PS T1.5 | DAY 2 January 13, 2021 |
109 | ACRM: Attention Cascade R-CNN with Mix-NMS for Metallic Surface Defect Detection | Fang, Junting; Tan, Xiaoyang; Wang, Yuhui | Nanjing University of Aeronautics and Astronautics | Poster | PS T3.8 | DAY 3 – January 14, 2021 |
110 | Nearest Neighbor Classification Based on Activation Space of Convolutional Neural Network | Ju, Xinbo; Shao, Shuo; Long, Huan; wang, weizhe | Shanghai Jiao Tong University | Poster | PS T1.5 | DAY 2 – January 13, 2021 |
112 | Graph Signal Active Contours | lezoray, Olivier | Université de Caen Normandie | Oral | OS T5.2 – PS T5.2 | DAY 1 – January 12, 2021 – DAY 1 – January 12, 2021 |
113 | Video Summarization with a Dual Attention Capsule Network | Fu, Hao; Wang, Hongxing; Yang, Jianyu | Chongqing University | Poster | PS T3.8 | DAY 3 – January 14, 2021 |
114 | Vertex Feature Encoding and Hierarchical Temporal Modeling in a Spatio-Temporal Graph Convolutional Network for Action Recognition | Papadopoulos, Konstantinos; ghorbel, Enjie; Aouada, Djamila; Ottersten, Bjorn | University of Luxembourg | Poster | PS T2.3 | DAY 2 – January 13, 2021 |
117 | Combined Invariants to Gaussian Blur and Affine Transformation | Kostkova, Jitka; Flusser, Jan; Pedone, Matteo | Czech Academy of Sciences, Institute of Information Theory and Automation | Poster | PS T5.2 | DAY 1 – January 12, 2021 |
118 | PC-Net: A Deep Network for 3D Point Clouds Analysis | Chen, Zhuo; Guan, Tao; Luo, Yawei; Wang, Yuesong; Luo, Keyang; Xu, Luoyuan | Huazhong University of Science & Technology | Poster | PS T1.5 | DAY 2 January 13, 2021 |
119 | Automatically Gather Address Specific Dwelling Images Using Google Street View | Khan, Salman; Salvaggio, Carl | Rochester Institute of Technology | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
120 | PROPEL: Probabilistic Parametric Regression Loss for Convolutional Neural Networks | Asad, Muhammad; Basaru, Rilwan; Al Arif, S M Masudur Rahman; Slabaugh, Greg | Imagination Technologies | Oral | OS T1.1 – PS T1.1 | DAY 1 – January 12, 2021 – DAY 1 – January 12, 2021 |
121 | Video Analytics Gait Trend Measurement for Fall Prevention and Health Monitoring | O’Gorman, Lawrence; Liu, Xinyi; Sarker, Md Imran; Milanova, Mariofanna | Nokia Bell Labs | Poster | PS T2.1 | DAY 1 – January 12, 2021 |
122 | Deep Next-Best-View Planner for Cross-Season Visual Route Classification | Kanya, Kurauchi; Tanaka, Kanji | University of Fukui | Poster | PS T3.8 | DAY 3 – January 14, 2021 |
124 | EdgeNet: Semantic Scene Completion from a Single RGB-D Image | Dourado, Aloisio; de Campos, Teofilo; Kim, Hansung; Hilton, Adrian | University of Brasilia | Poster | PS T3.3 | DAY 1 – January 12, 2021 |
126 | Simple Multi-Resolution Representation Learning for Human Pose Estimation | Tran Quang, Trung; Nguyen, Van Giang; Kim, Daeyoung | Korea Advanced Institute of Science and Technology (KAIST) | Poster | PS T3.8 | DAY 3 – January 14, 2021 |
127 | Multi-Direction Convolution for Semantic Segmentation | Li, Dehui; Cao, Zhiguo; Xian, Ke; Qi, Xinyuan; Zhang, Chao; Lu, Hao | Huazhong University of Science and Technology | Oral | OS T1.8 – PS T1.9 | DAY 4 – January 15, 2021 – DAY 3 January 14, 2021 |
332 | Image Representation Learning by Transformation Regression | Guo, Xifeng; Liu, Jiyuan; Zhou, Sihang; Zhu, En; Dong, Shihao | National University of Defense Technology | Poster | PS T1.5 | DAY 2 – January 13, 2021 |
335 | Temporal Extension Module for Skeleton-Based Action Recognition | Obinata, Yuya; Yamamoto, Takuma | FUJITSU LABORATORIES LTD. | Poster | PS T2.2 | DAY 2 – January 13, 2021 |
336 | F-Mixup: Attack CNNs from Fourier Perspective | Li, Xiu-Chuan; Zhang, Xu-Yao; Yin, Fei; Liu, Cheng-Lin | Institute of Automation, Chinese Academy of Sciences | Poster | PS T1.13 | DAY 4 – January 15, 2021 |
337 | Efficient Correlation Filter Tracking with Adaptive Training Sample Update Scheme | Jiang, Shan; Li, Shuxiao; Zhu, Chengfei; Yan, Nan | Institute of Automation, Chinese Academy of Sciences | Poster | PS T3.8 | DAY 3 – January 14, 2021 |
339 | Enhanced User Interest and Expertise Modeling for Expert Recommendation | He, Tongze; Guo, Caili; Chu, Yunfei | Bejing University of Posts and Telecommunications | Poster | PS T1.13 | DAY 4 – January 15, 2021 |
340 | Translating Adult’s Focus of Attention to Elderly’s | Krishna, Onkar; Irie, Go; Kawanishi, Takahito; Kashino, Kunio; Aizawa, Kiyoharu | NTT Corporation, Japan | Oral | OS T3.6 – PS T3.7 | DAY 4 – January 15, 2021 – DAY 3 – January 14, 2021 |
342 | How to Define a Rejection Class Based on Model Learning? | Laroui, Sarah ; Descombes, Xavier; Vernay, Aurelia; Villiers, Florent; Villalba, Francois; Debreuve, Eric | Universite cote d’Azur | Poster | PS T1.9 | DAY 3 – January 14, 2021 |
345 | Exploiting Distilled Learning for Deep Siamese Tracking | Liu, Chengxin; Cao, Zhiguo; Li, Wei; Xiao, Yang; Du, Shuaiyuan; Zhu, Angfan | Queen Mary University of London | Poster | PS T3.3 | DAY 1 – January 12, 2021 |
346 | Open-World Group Retrieval with Ambiguity Removal: A Benchmark | Mei, Ling; Lai, Jian-huang; Feng, Zhanxiang; Xie, Xiaohua | Sun Yat-sen University | Poster | PS T5.3 | DAY 2 – January 13, 2021 |
347 | RGB-Infrared Person Re-Identification Via Image Modality Conversion | Dai, Huangpeng; Xie, Qing; Ma, Yanchun; Liu, Yongjian; Xiong, ShengWu | Wuhan University of Technology | Poster | PS T1.13 | DAY 4 – January 15, 2021 |
349 | Distortion-Adaptive Grape Bunch Counting for Omnidirectional Images | Akai, Ryota; Utsumi, Yuzuko; Miwa, Yuka; Iwamura, Masakazu; Kise, Koichi | Osaka Prefecture University | Poster | PS T1.13 | DAY 4 – January 15, 2021 |
351 | Video-Based Facial Expression Recognition Using Graph Convolutional Networks | Liu, Daizong; Zhang, Hongting; Zhou, Pan | Huazhong University of Science and Technology | Poster | PS T2.2 | DAY 2 – January 13, 2021 |
353 | Cross-spectrum Face Recognition Using Subspace Projection Hashing | Wang, Hanrui; Dong, Xingbo; Zhe, Jin; Dugelay, Jean-Luc; Tistarelli, Massimo | Monsh Univesity | Poster | PS T2.2 | DAY 2 – January 13, 2021 |
356 | Object Segmentation Tracking from Generic Video Cues | Kardoost, Amirhossein; Müller, Sabine; Weickert, Joachim; Keuper, Margret | University of Mannheim | Poster | PS T5.4 | DAY 2 – January 13, 2021 |
359 | ActionSpotter: Deep Reinforcement Learning Framework for Temporal Action Spotting in Videos | Vaudaux-Ruth, Guillaume; Chan-Hon-Tong, Adrien; Achard, Catherine | ONERA/ Sorbonne University | Poster | PS T3.3 | DAY 1 – January 12, 2021 |
360 | Building Computationally Efficient and Well-Generalizing Person Re-Identification Models with Metric Learning | Sovrasov, Vladislav; Sidnev, Dmitry | Lobachevsky State University of Nizhny Novgorod, Intel IOTG Computer Vision (ICV) | Oral | OS T1.8 – PS T1.15 | DAY 4 – January 15, — DAY 4 – January 15, 2021 |
362 | An Efficient Empirical Solver for Localized Multiple Kernel Learning Via DNNs | Zhang, Ziming | Mitsubishi Electric Research Laboratories (MERL) | Poster | PS T1.13 | DAY 4 – January 15, 2021 |
364 | Total Whitening for Online Signature Verification Based on Deep Representation | Wu, Xiaomeng; Kimura, Akisato; Kashino, Kunio; Uchida, Seiichi | NTT Corporation | Poster | PS T4.2 | DAY 2 – January 13, 2021 |
365 | Reducing False Positives in Object Tracking with Siamese Network | Ogawa, Takuya; Shibata, Takashi; yachida, shoji; Hosoi, Toshinori | NEC | Poster | PS T3.8 | DAY 3 – January 14, 2021 |
366 | TSDM: Tracking by SiamRPN++ with a Depth-Refiner and a Mask-Generator | Zhao, Pengyao; Liu, Quanli; Wang, Wei; Guo, Qiang | Dalian University of Technology | Poster | PS T3.8 | DAY 3 – January 14, 2021 |
368 | Atmospheric Blocking Pattern Recognition in Global Climate Model Simulation Data | Muszynski, Grzegorz; Mr, Prabhat; Balewski, Jan; Kashinath, Karthik; Wehner, Michael; Kurlin, Vitaliy | University of Liverpool | Poster | PS T1.15 | DAY 4 – January 15, 2021 |
369 | MixedFusion: 6D Object Pose Estimation from Decoupled RGB-Depth Features | Feng, Hangtao; Zhang, Lu; Yang, Xu; Liu, Zhiyong | Institute of Automation, Chinese Academy of Sciences | Poster | PS T3.8 | DAY 3 – January 14, 2021 |
370 | An Intransitivity Model for Matchup and Pairwise Comparison | Gu, Yan; Duan, Jiuding; Kashima, Hisashi | Kyoto University | Poster | PS T1.13 | DAY 4 – January 15, 2021 |
374 | Multimodal End-To-End Learning for Autonomous Steering in Adverse Road and Weather Conditions | Maanpää, Jyri Sakari; Taher, Josef; Manninen, Petri; Pakola, Leo; Melekhov, Iaroslav; Hyyppä, Juha | Finnish Geospatial Research Institute FGI, National Land Survey of Finland | Poster | PS T1.9 | DAY 3 – January 14, 2021 |
376 | SiamMT: Real-Time Arbitrary Multi-Object Tracking | Vaquero, Lorenzo; Mucientes, Manuel; Brea, Victor | Universidade de Santiago de Compostela | Poster | PS T3.3 | DAY 1 – January 12, 2021 |
378 | Vehicle Lane Merge Visual Benchmark | Cordes, Kai; Broszio, Hellward | VISCODA GmbH | Poster | PS T1.9 | DAY 3 – January 14, 2021 |
380 | PS^2-Net: A Locally and Globally Aware Network for Point-Based Semantic Segmentation | Zhao, Na; Chua, Tat Seng; Lee, Gim Hee | National University of Singapore | Poster | PS T3.8 | DAY 3 – January 14, 2021 |
384 | Phase Retrieval Using Conditional Generative Adversarial Networks | Uelwer, Tobias; Oberstraß, Alexander; Harmeling, Stefan | Heinrich-Heine-Universität Düsseldorf | Poster | PS T5.4 | DAY 2 – January 13, 2021 |
385 | Learning to Take Directions One Step at a Time | Hu, Qiyang; Wälchli, Adrian; Portenier, Tiziano; Zwicker, Matthias; Favaro, Paolo | University of Bern | Poster | PS T1.16 | DAY 4 – January 15, 2021 |
387 | Deep Universal Blind Image Denoising | Soh, Jae Woong; Cho, Nam Ik | Seoul National University | Oral | OS T5.3 – PS T5.3 | DAY 2 – January 13, 2021 – DAY 2 – January 13, 2021 |
388 | One-Shot Learning for Acoustic Identification of Bird Species in Non-Stationary Environments | Acconcjaioco, Michelangelo; Ntalampiras, Stavros | Università degli studi Milano | Poster | PS T5.4 | DAY 2 – January 13, 2021 |
389 | Adversarial Encoder-Multi-Task-Decoder for Multi-Stage Processes | Mendes, Andre; Togelius, Julian; Dos Santos Coelho, Leandro | New York University | Poster | PS T1.13 | DAY 4 – January 15, 2021 |
390 | What and How? Jointly Forecasting Human Action and Pose | Zhu, Yanjun; Zhang, Yanxia; Liu, Qiong; Girgensohn, Andreas | FX Palo Alto Laboratory | Poster | PS T2.1 | DAY 1 – January 12, 2021 |
391 | Weakly Supervised Attention Rectification for Scene Text Recognition | Gu, Chengyu; Wang, Shilin; Zhu, Yiwei; Huang, Zheng; Chen, Kai | Shanghai Jiao Tong University | Poster | PS T4.3 | DAY 3 – January 14, 2021 |
394 | A Fast and Accurate Object Detector for Handwritten Digit String Recognition | Guo, Jun; Wei, Wenjing; Ma, Yifeng; Peng, Cong | East China Normal University | Poster | PS T4.3 | DAY 3 – January 14, 2021 |
395 | SFPN: Semantic Feature Pyramid Network for Object Detection | Gan, Yi; Xu, Wei; Su, Jianbo | Shanghai Jiao Tong University | Poster | PS T1.13 | DAY 4 – January 15, 2021 |
396 | A General Framework for Small Object Detection Leveraging on Simultaneous Unsupervised Super-resolution | Ji, Hong; Gao, Zhi; Liu, Xiaodong; Mei, Tiancan | wuhan university | Poster | PS T1.13 | DAY 4 – January 15, 2021 |
398 | Class Conditional Alignment for Partial Domain Adaptation | Kheirandishfard, Mohsen; Zohrizadeh, Fariba; Kamangar, Farhad | University of Texas at Arlington | Poster | PS T1.13 | DAY 4 – January 15, 2021 |
401 | AdvHat: Real-World Adversarial Attack on ArcFace Face ID System | Komkov, Stepan; Petiushko, Aleksandr | Lomonosov Moscow State University, Huawei Moscow Research Center | Poster | PS T2.2 | DAY 2 – January 13, 2021 |
403 | PSDNet: A Balanced Architecture of Accuracy and Parameters for Semantic Segmentation | Liu, Yue; Lian, Zhichao | Nanjing University of Science and Technology | Poster | PS T3.8 | DAY 3 – January 14, 2021 |
404 | Bridging the Gap between Natural and Medical Images through Deep Colorization | Morra, Lia; Piano, Luca; Lamberti, Fabrizio; Tommasi, Tatiana | Politecnico di Torino | Poster | PS T5.4 | DAY 2 – January 13, 2021 |
405 | Learning Error-Driven Curriculum for Crowd Counting | Li, Wenxi; Cao, Zhuoqun; Wang, Qian; Chen, Songjian; Feng, Rui | Fudan University | Oral | OS T3.2 – PS T3.7 | DAY 2 – January 13, 2021 – DAY 3 – January 14, 2021 |
407 | Self-Training for Domain Adaptive Scene Text Detection | Chen, Yudi; Wang, Wei; Zhou, Yu; Yang, Fei; Yang, Dongbao; Wang, Weiping | IIE, CAS | Oral | OS T 4.2 – PS T4.2 | DAY 4 – January 15, 2021 – DAY 2 – January 13, 2021 |
408 | Automatical Enhancement and Denoising of Extremely Low-Light Images | Song, Yuda; Zhu, Yunfang; Du, Xin | Zhejiang University | Poster | PS T3.8 | DAY 3 – January 14, 2021 |
409 | FastCompletion: A Cascade Network with Multiscale Group-Fused Inputs for Real-Time Depth Completion | Li, Ang; Yuan, Zejian; Ling, Yonggen; Chi, Wanchao; Zhang, Shenghao; Zhang, Chong | Xi’an Jiaotong University | Poster | PS T3.8 | DAY 3 – January 14, 2021 |
417 | LFIEM: Lightweight Filter-Based Image Enhancement Model | Tatanov, Oktai; Samarin, Aleksei | VK, Saint-Petersburg State University | Poster | PS T5.4 | DAY 2 – January 13, 2021 |
418 | Improving Visual Question Answering Using Active Perception on Static Images | Bozinis, Theodoros; Passalis, Nikolaos; Tefas, Anastasios | Aristotle University of Thessaloniki | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
419 | Leveraging Quadratic Spherical Mutual Information Hashing for Fast Image Retrieval | Passalis, Nikolaos; Tefas, Anastasios | Aristotle University of Thessaloniki | Poster | PS T5.4 | DAY 2 – January 13, 2021 |
420 | DEN: Disentangling and Exchanging Network for Depth Completion | Wu, You-Feng; Tran, Vu-Hoang; Chang, Ting-Wei; Chiu, Wei-Chen; Huang, Ching-Chun | National Chiao Tung University | Oral | OS T1.7 – PS T1.9 | DAY 4 – January 15, 2021 – DAY 3 January 14, 2021 |
422 | Double Manifolds Regularized Non-Negative Matrix Factorization for Data Representation | Guo, Jipeng; Yin, Shuai; Sun, Yanfeng; Hu, Yongli | Beijing University of Technology | Poster | PS T1.13 | DAY 4 – January 15, 2021 |
426 | Low Rank Representation on Product Grassmann Manifolds for Multi-viewSubspace Clustering | Guo, Jipeng; Sun, Yanfeng; Gao, Junbin; Hu, Yongli; Yin, Baocai | Beijing University of Technology | Poster | PS T1.13 | DAY 4 – January 15, 2021 |
428 | Coherence and Identity Learning for Arbitrary-Length Face Video Generation | Ye, Shuquan; Han, Chu; Lin, Jiaying; Han, Guoqiang; He, Shengfeng | South China University of Technology | Poster | PS T1.13 | DAY 4 – January 15, 2021 |
429 | Feature-Aware Unsupervised Learning with Joint Variational Attention and Automatic Clustering | Ru, Wang; Li, Lin; Wang, Peipei; Tao, Xiaohui; Peiyu, Liu | Shandong Normal University | Poster | PS T4.2 | DAY 2 – January 13, 2021 |
430 | Controllable Face Aging | Zeng, Haien; Lai, Hanjiang | Sun Yat-Sen University | Poster | PS T5.3 | DAY 2 – January 13, 2021 |
435 | Learning to Prune in Training via Dynamic Channel Propagation | Shen, Shibo; Li, Rongpeng; Zhao, Zhifeng; Zhang, Honggang; Zhou, Yugeng | Zhejiang University | Oral | OS T1.4 – PS T1.4 | DAY 2 – January 13, 2021 – DAY 2 – January 13, 2021 |
437 | Reinforcement Learning with Dual Attention Guided Graph Convolution for Relation Extraction | Li, Zhixin; Sun, Yaru; Tang, Suqin; Zhang, Canlong; Ma, Huifang | Guangxi Normal University | Poster | PS T1.13 | DAY 4 – January 15, 2021 |
439 | Object Detection Model Based on Scene-Level Region Proposal Self-Attention | Quan, Yu; Li, Zhixin; Zhang, Canlong; Ma, Huifang | Guangxi Normal University | Poster | PS T3.4 | DAY 2 – January 13, 2021 |
440 | RWMF: A Real-World Multimodal Foodlog Database | Zhou, Pengfei; Bai, Cong; Ying, Kaining; Xia, Jie; Huang, Lixin | Zhejiang University of Technology | Poster | PS T4.2 | DAY 2 – January 13, 2021 |
442 | Penalized K-Means Algorithms for Finding the Number of Clusters | Kamgar-Parsi, Behzad; Kamgar-Parsi, Behrooz | Office of Naval Research (ONR) | Poster | PS T1.13 | DAY 4 – January 15, 2021 |
443 | Learning Recurrent High-Order Statistics for Skeleton-Based Hand Gesture Recognition | Nguyen, Xuan Son; Brun, Luc; Lezoray, Olivier; Bougleux, Sébastien | Université de Caen Normandie | Oral | OS T2.1 – PS T2.1 | DAY 1 – January 12, 2021 – DAY 1 – January 12, 2021 |
444 | Unsupervised Domain Adaptation for Object Detection in Cultural Sites | Pasqualino, Giovanni; Furnari, Antonino; Farinella, Giovanni Maria | University of Catania | Oral | OS T3.5 – PS T3.11 | DAY 4 – January 15, 2021 – DAY 4 – January 15, 2021 |
445 | On the Evaluation of Generative Adversarial Networks by Discriminative Models | Torfi, Amirsina; Beyki, Mohammadreza; Fox, Edward Alan | Virginia Polytechnic Institute and State University | Poster | PS T1.13 | DAY 4 – January 15, 2021 |
446 | Scalable Direction-Search-Based Approach to Subspace Clustering | He, Yicong; Atia, George | University of Central Florida | Oral | OS T1.3 – PS T1.7 | DAY 1 – January 12, 2021 – DAY 2 – January 13, 2021 |
448 | Efficient Online Subclass Knowledge Distillation for Image Classification | Tzelepi, Maria; Passalis, Nikolaos; Tefas, Anastasios | Department of Informatics, Aristotle University of Thessaloniki | Poster | PS T1.16 | DAY 4 – January 15, 2021 |
449 | Fourier Domain Pruning of MobileNet-V2 with Application to Video Based Wildfire Detection | Pan, Hongyi; Badawi, Diaa; Cetin, E. | University of Illinois at Chicago | Poster | PS T1.13 | DAY 4 – January 15, 2021 |
450 | Initialization Using Perlin Noise for Training Networks with a Limited Amount of Data | Inoue, Nakamasa; Yamagata, Eisuke; Kataoka, Hirokatsu | Tokyo Institute of Technology | Poster | PS T1.13 | DAY 4 – January 15, 2021 |
453 | MTGAN: Mask and Texture-Driven Generative Adversarial Network for Lung Nodule Segmentation | Chen, Wei; Wang, Qiuli; Wang, Kun; Yang, Dan; Zhang, Xiaohong; Liu, Chen; Li, Yucong | Chongqing University | Poster | PS T5.3 | DAY 2 – January 13, 2021 |
456 | Multiple-Step Sampling for Dense Object Detection and Counting | Deng, Zhaoli; Yang, Chenhui | Xiamen University | Poster | PS T3.4 | DAY 2 – January 13, 2021 |
458 | EasiECG: A Novel Inter-Patient Arrhythmia Classification Method Using ECG Waves | Han, Chuanqi; Huang, Ruoran; Yu, Fang; Huang, Xi; Cui, Li | Institute of Computing Technology Chinese Academy of Sciences | Poster | PS T5.3 | DAY 2 – January 13, 2021 |
459 | Q-SNE: Visualizing Data Using Q-Gaussian Distributed Stochastic Neighbor Embedding | Abe, Motoshi; Miyao, Junichi; Kurita, Takio | Hiroshima University | Poster | PS T1.13 | DAY 4 – January 15, 2021 |
462 | Semi-Supervised Domain Adaptation Via Selective Pseudo Labeling and Progressive Self-Training | Kim, Yoonhyung; Kim, Changick | Korea Advanced Institute of Science and Technology | Poster | PS T1.13 | DAY 4 – January 15, 2021 |
463 | DAPC: Domain Adaptation People Counting Via Style-Level Transfer Learning and Scene-Aware Estimation | Jiang, Na; Wen, Xingsen; Shi, Zhiping | Capital Normal University | Poster | PS T3.4 | DAY 2 – January 13, 2021 |
464 | Lane Detection Based on Object Detection and Image-To-Image Translation | Komori, Hiroyuki; Onoguchi, Kazunori | Hirosaki University | Poster | PS T3.8 | DAY 3 – January 14, 2021 |
465 | TCATD: Text Contour Attention for Scene Text Detection | Hu, ZiLing; Wu, Xingjiao; Yang, Jing | School of Computer Science and Technology,East China Normal University | Poster | PS T4.3 | DAY 3 – January 14, 2021 |
466 | Filter Pruning Using Hierarchical Group Sparse Regularization for Deep Convolutional Neural Networks | Mitsuno, Kakeru; Kurita, Takio | Hiroshima University | Poster | PS T1.13 | DAY 4 – January 15, 2021 |
468 | JUMPS: Joints Upsampling Method for Pose Sequences | Mourot, Lucas; Le Clerc, Francois; Thébault, Cédric; Hellier, Pierre | InterDidital | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
469 | Fast Multi-Level Foreground Estimation | Germer, Thomas; Uelwer, Tobias; Conrad, Stefan; Harmeling, Stefan | Heinrich-Heine-Universität Düsseldorf | Poster | PS T5.4 | DAY 2 – January 13, 2021 |
475 | Local Gradient Difference Based Mass Features for Classification of 2D-3D Natural Scene Text Images | Nandanwar, Lokesh; Palaiahnakote, Shivakumara; Ramachandra, Raghavendra; Lu, Tong; Pal, Umapada; Lopresti, Daniel; Anuar, Nor Badrul | National University of Singapore | Poster | PS T4.3 | DAY 3 – January 14, 2021 |
476 | FOANet: A Focus of Attention Network with Application to Myocardium Segmentation | Zhao, Zhou; Puybareau, Elodie; Boutry, Nicolas; Geraud, Thierry | EPITA Research and Development Laboratory (LRDE) | Poster | PS T5.4 | DAY 2 – January 13, 2021 |
479 | Stabilized Calculation of Gaussian Smoothing and Its Differentials Using Attenuated Sliding Fourier Transform | Yamashita, Yukihiko; Wakahara, Toru | Tokyo Institute of Technology | Poster | PS T5.3 | DAY 2 – January 13, 2021 |
481 | Minimal Solvers for Indoor UAV Positioning | Örnhag, Marcus Valtonen; Persson, Patrik; Wadenbäck, Mårten; Åström, Kalle; Heyden, Anders | Lund University | Poster | PS T3.6 | DAY 2 – January 13, 2021 |
482 | Polynomial Universal Adversarial Perturbations for Person Re-Identification | Ding, Wenjie; WEI, Xing; Ji, Rongrong; Hong, Xiaopeng; Gong, Yihong | Xi’an Jiaotong University | Poster | PS T1.13 | DAY 4 – January 15, 2021 |
483 | Explore and Explain: Self-Supervised Navigation and Recounting | Bigazzi, Roberto; Landi, Federico; Cornia, Marcella; Cascianelli, Silvia; Baraldi, Lorenzo; Cucchiara, Rita | University of Modena and Reggio Emilia | Oral | OS T3.2 – PS T3.5 | DAY 2 – January 13, 2021 – DAY 2 – January 13, 2021 |
484 | RobusterNet: Improving Copy-Move Forgery Detection with Volterra-Based Convolutions | Kafali, Efthimia; Vretos, Nicholas; Semertzidis, Theodoros; Daras, Petros | CERTH | Oral | OS T1.6 – PS T1.13 | DAY 3 – January 14, 2021 – DAY 4 – January 15, 2021 |
485 | Human Segmentation with Dynamic LiDAR Data | Zhong, Tao; Kim, Wonjik; Tanaka, Masayuki; Okutomi, Masatoshi | 东京工业大学 | Oral | OS T1.8 – PS T1.9 | DAY 4 – January 15, 2021 – DAY 3 January 14, 2021 |
486 | Answer-Checking in Context: A Multi-Modal Fully Attention Network for Visual Question Answering | Huang, Hantao; HAN, TAO; Han, Wei; Deep Yap, Deep Yap; Chiang, Cheng-Ming | Mediatek Singapore | Poster | PS T3.4 | DAY 2 – January 13, 2021 |
487 | Exploring the Ability of CNNs to Generalise to Previously Unseen Scales Over Wide Scale Ranges | Jansson, Ylva; Lindeberg, Tony | KTH Royal Institute of Technology | Oral | OS T1.7 – PS T1.14 | DAY 4 – January 15, 2021 – DAY 4 – January 15, 2021 |
488 | SCA Net: Sparse Channel Attention Module for Action Recognition | Song, Hang; Song, Yonghong; Zhang, Yuanlin | Xi’an Jiaotong University | Poster | PS T3.4 | DAY 2 – January 13, 2021 |
489 | HMFlow: Hybrid Matching Optical Flow Network for Small and Fast-Moving Objects | Yu, Suihanjin; Zhang, Youmin; Wang, Chen; Bai, Xiao; Zhang, Liang; Hancock, Edwin | Beihang University | Poster | PS T1.13 | DAY 4 – January 15, 2021 |
490 | PowerHC: Non Linear Normalization of Distances for Advanced Nearest Neighbor Classification | Bicego, Manuele; Orozco-Alzate, Mauricio | University of Verona | Poster | PS T1.13 | DAY 4 – January 15, 2021 |
492 | A Novel Attention-Based Aggregation Function to Combine Vision and Language | Stefanini, Matteo; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita | University of Modena and Reggio Emilia | Poster | PS T3.6 | DAY 2 – January 13, 2021 |
497 | Rethinking Deep Active Learning: Using Unlabeled Data at Model Training | Siméoni, Oriane; Budnik, Mateusz; Avrithis, Yannis; Gravier, Guillaume | INRIA | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
500 | Pose-Aware Multi-Feature Fusion Network for Driver Distraction Recognition | Wu, Mingyan; Zhang, Xi; Shen, Linlin; Yu, Hang | Shenzhen University | Poster | PS T3.4 | DAY 2 – January 13, 2021 |
501 | SA-UNet: Spatial Attention U-Net for Retinal Vessel Segmentation | Guo, Changlu; Szemenyei, Marton; Yi, Yugen; Wang, Wenle; Chen, Buer; Fan, Changqi | Budapest University of Technology and Economics | Poster | PS T5.4 | DAY 2 – January 13, 2021 |
502 | Delving in the Loss Landscape to Embed Robust Watermarks into Neural Networks | Tartaglione, Enzo; Grangetto, Marco; Cavagnino, Davide; Botta, Marco | Università degli Studi di Torino | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
503 | PEAN: 3D Hand Pose Estimation Adversarial Network | Sun, Linhui; Zhang, Yifan; Cheng, Jian; Lu, Hanqing | Institute of Automation,Chinese Academy of Sciences | Poster | PS T2.2 | DAY 2 – January 13, 2021 |
504 | ILS-SUMM: Iterated Local Search for Unsupervised Video Summarization | Shemer, Yair; Rotman, Daniel; Shimkin, Nahum | Technion | Oral | OS T3.4 – PS T3.9 | DAY 3 – January 14, 2021 – DAY 3 – January 14, 2021 |
505 | Snapshot Hyperspectral Imaging Based on Weighted High-Order Singular Value Regularization | Niankai, Cheng; Huang, Hua; Zhang, Lei; Wang, Lizhi | Beijing Normal University | Poster | PS T5.3 | DAY 2 – January 13, 2021 |
506 | Multi-Task Learning Based Traditional Mongolian Words Recognition | Wei, Hongxi; Zhang, Hui; Zhang, Jing; Liu, KeXin | Inner Mongolia University | Poster | PS T4.3 | DAY 3 – January 14, 2021 |
509 | Seasonal Inhomogeneous Nonconsecutive Arrival Process Search and Evaluation | Holmgren, Kimberly; Gibby, Paul; Zipkin, Joseph | MIT Lincoln Laboratory | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
510 | Cross-Media Hash Retrieval Using Multi-head Attention Network | Li, Zhixin; Ling, Feng; Xu, Chuansheng; Zhang, Canlong; Ma, Huifang | Guangxi Normal University | Poster | PS T5.3 | DAY 2 – January 13, 2021 |
512 | Confidence Calibration for Deep Renal Biopsy Immunofluorescence Images Classification | Pollastri, Federico; Maroñas, Juan; Bolelli, Federico; Ligabue, Giulia; Paredes, Roberto; Magistroni, Riccardo; Grana, Costantino | Università degli Studi di Modena e Reggio Emilia | Poster | PS T3.5 | DAY 2 – January 13, 2021 |
513 | Color Texture Description Based on Holistic and Hierarchical Order-Encoding Patterns | Song, Tiecheng; Feng, Jie; Wang, Yuanlin; Gao, Chenqiang | Chongqing University of Posts and Telecommunications | Poster | PS T5.3 | DAY 2 – January 13, 2021 |
516 | Porting a Convolutional Neural Network for Stereo Matching in Hardware | Sotiropoulos, Dionisis – Odysseas; Economou, George – Peter | University of Patras | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
517 | Learning with Multiplicative Perturbations | Yang, Xiulong; Ji, Shihao | Georgia State University | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
519 | GCNs-Based Context-Aware Short Text Similarity Model | Sun, Xiaoqi; Wu, Shaochun; Liu, Yue | Shanghai University | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
521 | Cascade Attention Guided Residue Learning GAN for Cross-Modal Translation | Duan, Bin; Wang, Wei; Tang, Hao; Latapie, Hugo; Yan, Yan | Illinois Institute of Technology | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
523 | A Novel Random Forest Dissimilarity Measure for Multi-View Learning | Cao, Hongliu; Bernard, Simon; Sabourin, Robert; Heutte, Laurent | Université de Rouen Normandie | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
524 | Recurrent Graph Convolutional Networks for Skeleton-Based Action Recognition | Zhu, Guangming; Yang, Lu; Zhang, Liang; Shen, Peiyi; Song, Juan | Xidian University | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
525 | Watermelon: A Novel Feature Selection Method Based on Bayes Error Rate Estimation and a New Interpretation of Feature Relevance and Redundancy | Xie, Xiang; Stork, Wilhelm | Karlsruhe Institute of Technology | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
526 | SATGAN: Augmenting Age Biased Dataset for Cross-Age Face Recognition | Liu, Wenshuang; Chen, Wenting; Zhu, Yuanlue; Shen, Linlin | Shenzhen University | Poster | PS T2.2 | DAY 2 – January 13, 2021 |
528 | MFPP: Morphological Fragmental Perturbation Pyramid for Black-Box Model Explanations | Yang, Qing; Zhu, Xia; Fwu, Jong-Kae; Ye, Yun; You, Ganmei; Zhu, Yuan | Intel | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
536 | Semantics to Space(S2S): Embedding semantics into spatial space for zero-shot verb-object query inferencing | Eum, Sungmin; Kwon, Heesung | Booz Allen Hamilton/US Army Research Lab | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
537 | Quantifying Model Uncertainty in Inverse Problems Via Bayesian Deep Gradient Descent | barbano, riccardo; Zhang, Chen; Arridge, Simon; Jin, Bangti | University College London (UCL) | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
541 | Meta Generalized Network for Few-Shot Classification | Wu, Wei; Pang, Shanmin; Tian, Zhiqiang; Li, Yaochen | Xi’an Jiaotong University | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
544 | Arbitrary Style Transfer with Parallel Self-Attention | Zhang, Tiange; Gao, Ying; Gao, Feng; Qi, Lin; Dong, Junyu | Ocean University of China | Poster | PS T5.3 | DAY 2 – January 13, 2021 |
546 | An Adaptive Fusion Model Based on Kalman Filtering and LSTM for Fast Tracking of Road Signs | Wang, Chengliang; Xie, Xin; Liao, Chao | Chongqing University | Poster | PS T3.4 | DAY 2 – January 13, 2021 |
547 | Exploring and Exploiting the Hierarchical Structure of a Scene for Scene Graph Generation | Kurosawa, Ikuto; Kobayashi, Tetsunori; Hayashi, Yoshihiko | Waseda university | Poster | PS T3.4 | DAY 2 – January 13, 2021 |
548 | Self-Paced Bottom-Up Clustering Network with Side Information for Person Re-Identification | Li, Mingkun; Li, Chun-Guang; Guo, Ruo-Pei; Guo, Jun | Beijing University of Posts and Telecommunications | Poster | PS T2.2 | DAY 2 – January 13, 2021 |
549 | The Aleatoric Uncertainty Estimation Using a Separate Formulation with Virtual Residuals | Kawashima, Takumi; Yu, Qing; Asai, Akari; Ikami, Daiki; Aizawa, Kiyoharu | The University of Tokyo | Oral | OS T1.5 – PS T1.10 | DAY 3 – January 14, 2021 – DAY 3 – January 14, 2021 |
551 | NAS-EOD: An End-To-End Neural Architecture Search Method for Efficient Object Detection | Zhang, Huigang; Wang, Liuan; sun, jun; Sun, Li; Kobashi, Hiromichi; Imamura, Nobutaka | FUJITSU R&D CENTER CO.,LTD. | Oral | OS T3.5 – PS T3.7 | DAY 4 – January 15, 2021 – DAY 3 – January 14, 2021 |
553 | Triplet-Path Dilated Network for Detection and Segmentation of General Pathological Images | Luo, Jiaqi; zhao, zhicheng; Su, Fei; Guo, Limei | Beijing University of Posts and Telecommunications | Oral | OS T5.5 – PS T5.3 | DAY 4 – January 15, 2021 – DAY 2 – January 13, 2021 |
555 | UHRSNet: A Semantic Segmentation Network Specifically for Ultra-High-Resolution Images | Shan, Lianlei; Wang, Weiqiang; Li, Minglong | University of Chinese Academy of Sciences | Poster | PS T3.4 | DAY 2 – January 13, 2021 |
558 | Revisiting ImprovedGAN with Metric Learning for Semi-Supervised Learning | Park, Jaewoo; Jung, Yoon Gyo; Teoh, Andrew | Yonsei University | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
561 | VGG-Embedded Adaptive Layer-Normalized Crowd Counting Net with Scale-Shuffling Modules | Guo, Dewen; Feng, Jie; Zhou, Bingfeng | Peking University | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
563 | MagnifierNet: Learning Efficient Small-Scale Pedestrian Detector towards Multiple Dense Regions | Cheng, Qi; Chen, Mingqin; Wu, Yingjie; Chen, Fei; Lin, Shiping | Fuzhou University | Poster | PS T3.4 | DAY 2 – January 13, 2021 |
564 | Coarse to Fine: Progressive and Multi-Task Learning for Salient Object Detection | Kang, Dong-Goo; park, sangwoo; Paik, Joonki | Chung-Ang University | Poster | PS T5.3 | DAY 2 – January 13, 2021 |
565 | Residual Learning of Video Frame Interpolation Using Convolutional LSTM | Suzuki, Keito; ikehara, masaaki | Keio Univ. | Poster | PS T5.3 | DAY 2 – January 13, 2021 |
566 | Camera Calibration Using Parallel Line Segments | Nakano, Gaku | NEC Corporation | Poster | PS T3.4 | DAY 2 – January 13, 2021 |
568 | The Role of Cycle Consistency for Generating Better Human Action Videos from a Single Frame | Li, Runze; Bhanu, Bir | University of California Riverside | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
569 | RLST: A Reinforcement Learning Approach to Scene Text Detection Refinement | Peng, Xuan; Huang, Zheng; Chen, Kai; Guo, Jie; Qiu, Weidong | Shanghai Jiao Tong University | Poster | PS T4.3 | DAY 3 – January 14, 2021 |
571 | Multi-Scale and Attention Based ResNet for Heartbeat Classification | Zhang, Haojie; Yang, Gongping; Huang, Yuwen; Yuan, Feng; Yin, Yilong | Shandong University | Poster | PS T5.3 | DAY 2 – January 13, 2021 |
572 | Improving reliability of attention branch network by introducing uncertainty | Tsukahara, Takuya; Hirakawa, Tsubasa; Yamashita, Takayoshi; Fujiyoshi, Hironobu | Chubu University | Poster | PS T3.8 | DAY 3 – January 14, 2021 |
574 | Motion Complementary Network for Efficient Action Recognition | Cheng, Ke; Zhang, Yifan; Li, Chenghua; Cheng, Jian; Lu, Hanqing | Institute of Automation, Chinese Academy of Sciences | Poster | PS T2.2 | DAY 2 – January 13, 2021 |
575 | Discrete Semantic Matrix Factorization Hashing for Cross-Modal Retrieval | Qin, Jianyang; Fei, Lunke; Teng, Shaohua; Zhang, Wei; Dongning, Liu; Zhao, Genping; Yuan, Haoliang | Guangdong University of Technology | Poster | PS T5.3 | DAY 2 – January 13, 2021 |
576 | Fast Subspace Clustering Based on the Kronecker Product | Zhou, Lei; Bai, Xiao; Zhang, Liang; Zhou, Jun; Hancock, Edwin | Beihang University | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
577 | Learning Sparse Deep Neural Networks Using Efficient Structured Projections on Convex Constraints for Green AI | Barlaud, Michel; Guyard, Frederic | CNRS/University of Nice-Sophia Antipolis | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
578 | You Ought to Look Around: Precise, Large Span Action Detection | Pan, Ge; Han, Zhang; yu, fan; Song, Yonghong; Zhang, Yuanlin; Yuan, Han | Xi’an Jiaotong University | Oral | OS T3.4 – PS T3.4 | DAY 3 – January 14, 2021 – DAY 2 – January 13, 2021 |
580 | UCCTGAN: Unsupervised Clothing Color Transformation Generative Adversarial Network | Sun, Shuming; Li, Xiaoqiang; Li, Jide | Shanghai University | Poster | PS T5.3 | DAY 2 – January 13, 2021 |
584 | Accurate Cell Segmentation in Digital Pathology Images Via Attention Enforced Networks | Yao, Zeyi; Li, Kaiqi; Zhang, Guanhong; Luo, Yiwen; Zhou, Xiaoguang; Sun, Muyi | Beijing University of Posts and Telecommunications, School of Automation | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
585 | Residual Fractal Network for Single Image Super Resolution by Widening and Deepening | Gu, Jiahang; Qu, Zhaowei; Wang, Xiaoru; Dan, Jiawang; Sun, Junwei | Beijing University of Posts and Telecommunications | Poster | PS T5.3 | DAY 2 – January 13, 2021 |
587 | Video Object Detection Using Object’s Motion Context and Spatio-Temporal Feature Aggregation | Kim, Jaekyum; Koh, Junho; Choi, Jun Won | Hanyang University | Poster | PS T3.4 | DAY 2 – January 13, 2021 |
588 | Learning Stereo Matchability in Disparity Regression Networks | Zhang, Jingyang; Yao, Yao; Luo, Zixin; Li, Shiwei; Shen, Tianwei; Fang, Tian; Quan, Long | The Hong Kong University of Science and Technology | Oral | OS T3.3 – PS T3.4 | DAY 3 – January 14, 2021 – DAY 2 – January 13, 2021 |
589 | Self-Supervised Learning of Dynamic Representations for Static Images | Song, Siyang; Sanchez, Enrique; Shen, Linlin; Valstar, Michel | University of Nottingham | Poster | PS T2.3 | DAY 2 – January 13, 2021 |
592 | Wasserstein k-Means with Sparse Simplex Projection | Fukunaga, Takumi; Kasai, Hiroyuki | Waseda University | PS T1.1 | DAY 1 – January 12, 2021 | |
593 | Pretraining Image Encoders without Reconstruction Via Feature Prediction Loss | Grund Pihlgren, Gustav; Sandin, Fredrik; Liwicki, Marcus | Luleå University of Technology | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
595 | Cross-Layer Information Refining Network for Single Image Super-Resolution | Zhang, Hongyi; Lu, Wen; Sun, Xiaopeng | xidian university | Poster | PS T5.5 | DAY 3 – January 14, 2021 |
598 | Thermal Characterisation of Unweighted and Weighted Networks | Wang, Jianjia; Wu, Hui; Hancock, Edwin | Shanghai University | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
599 | ReADS: A Rectified Attentional Double Supervised Network for Scene Text Recognition | Song, Qi; Jiang, Qianyi; Li, Nan; Zhang, Rui; Wei, Xiaolin | Meituan | Poster | PS T4.3 | DAY 3 – January 14, 2021 |
600 | Attributes Aware Face Generation with Generative Adversarial Networks | Yuan, Zheng; Zhang, Jie; Shan, Shiguang; Chen, xilin | ICT, CAS | Poster | PS T3.4 | DAY 2 – January 13, 2021 |
601 | Saliency Prediction on Omnidirectional Images with Brain-Like Shallow Neural Network | Dandan, Zhu; Yongqing, Chen; Xiongkuo, Min; Defang, Zhao; Yucheng, Zhu; Qiangqiang, Zhou; Xiaokang, Yang; Han, Tian | Shanghai jiaotong university | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
602 | G-FAN: Graph-Based Feature Aggregation Network for Video Face Recognition | Zhao, He; Shi, Yongjie; Tong, Xin; Wen, Jingsi; Ying, Xianghua; Zha, Hongbin | Peking University | Poster | PS T2.2 | DAY 2 – January 13, 2021 |
604 | Unsupervised Multi-Task Domain Adaptation | Yang, Shih-Min; Yeh, Mei-Chen | National Taiwan Normal University | Poster | PS T3.4 | DAY 2 – January 13, 2021 |
605 | Embedding Shared Low-Rank and Feature Correlation for Multi-View Data Analysis | Wang, Zhan; Wang, Lizhi; Zhang, Lei; Huang, Hua | Beijing Institute of Technology | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
606 | FMRI Brain Networks As Statistical Mechanical Ensembles | Wang, Jianjia; Wu, Hui; Hancock, Edwin | Shanghai University | Poster | PS T5.5 | DAY 3 – January 14, 2021 |
607 | Position-Aware and Symmetry Enhanced GAN for Radial Distortion Correction | Shi, Yongjie; Tong, Xin; Wen, Jingsi; Zhao, He; Ying, Xianghua; Zha, Hongbin | Peking University | Poster | PS T3.4 | DAY 2 – January 13, 2021 |
609 | Feature Embedding Based Text Instance Grouping for Largely Spaced and Occluded Text Detection | Gao, Pan; Wan, Qi; Gao, Renwu; Shen, Linlin | Shenzhen University | Poster | PS T4.3 | DAY 3 – January 14, 2021 |
611 | Deeply-Fused Attentive Network for Stereo Matching | Yang, Zuliu; Ai, Xindong; Yang, Weida; Zhao, Yong; Dai, Qifei; Li, Fuchi | Shenzhen Graduate School of Peking University | Poster | PS T3.4 | DAY 2 – January 13, 2021 |
612 | HP2IFS: Head Pose Estimation Exploiting Partitioned Iterated Function Systems | Bisogni, Carmen; Nappi, Michele; Pero, Chiara; Ricciardi, Stefano | University of Salerno, Department of Computer Science, Fisciano (SA) | Poster | PS T2.3 | DAY 2 – January 13, 2021 |
614 | Detail Fusion GAN: High-Quality Translation for Unpaired Images with GAN-Based Data Augmentation | Li, Ling; Li, Yaochen; Wu, Chuan; Dong, Hang; Jiang, Peilin; Wang, Fei | Xi’an Jiaotong University | Poster | PS T5.5 | DAY 3 – January 14, 2021 |
615 | Content-Sensitive Superpixels Based on Adaptive Regrowth | Li, Xiaopeng; Xiong, Junlin | University of Science and Technology of China | Poster | PS T5.5 | DAY 3 – January 14, 2021 |
617 | CAggNet: Crossing Aggregation Network for Medical Image Segmentation | Cao, Xu; Lin, Yanghao | Fudan University | Poster | PS T3.4 | DAY 2 – January 13, 2021 |
619 | MixTConv: Mixed Temporal Convolutional Kernels for Efficient Action Recognition | Shan, Kaiyu; Wang, Yongtao; Tang, Zhi; Chen, Ying; Li, Yangyan | Peking University | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
623 | 3D Facial Matching by Spiral Convolutional Metric Learning and a Biometric Fusion-Net of Demographic Properties | Mahdi, Soha Sadat; Nauwelaers, Nele; Joris, Philip; Bouritsas, Giorgos; Gong, Shunwang; Bokhnyak, Sergiy; Walsh, Susan; Shriver, Mark; Bronstein, Michael; Claes, Peter | KU Leuven | Oral | OS T2.2 – PS T2.4 | DAY 3 – January 14, 2021 – DAY 3 – January 14, 2021 |
625 | Reducing-Over-Time Tree for Event-Based Data | Harrigan, Shane; Coleman, Sonya; Kerr, Dermot; Yogarajah, Pratheepan; Fang, Zheng; Wu, Chengdong | Ulster University | Poster | PS T5.2 | DAY 1 – January 12, 2021 |
626 | 3CS Algorithm for Efficient Gaussian Process Model Retrieval | Berns, Fabian; Schmidt, Kjeld; Bracht, Ingolf; Beecks, Christian | University of Muenster | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
628 | ClusterFace: Joint Clustering and Classification for Set-Based Face Recognition | Wickrama Arachchilage, Samadhi Poornima Kumarasinghe; Izquierdo, Ebroul | Queen Mary University of London | Poster | PS T2.3 | DAY 2 – January 13, 2021 |
631 | Sensor-Independent Pedestrian Detection for Personal Mobility Vehicles in Walking Space Using Dataset Generated by Simulation | Shimizu, Takahiro; Koide, Kenji; Oishi, Shuji; Yokozuka, Masashi; Banno, Atsuhiko; Shino, Motoki | The University of Tokyo | Poster | PS T3.4 | DAY 2 – January 13, 2021 |
632 | A Unified Framework for Distance-Aware Domain Adaptation | Wang, Fei; Ding, Youdong; Liang, Huan; Gao, Yuzhen; Che, Wenqi | Shanghai University | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
633 | DCT/IDCT Filter Design for Ultrasound Image Filtering | Honarvar Shakibaei Asli, Barmak; Flusser, Jan; Zhao, Yifan; Ahmet Erkoyuncu, John; Roy, Rajkumar | The School of Aerospace, Transport and Manufacturing, Cranfield University | Poster | PS T5.2 | DAY 1 – January 12, 2021 |
635 | Enlarging Discriminative Power by Adding an Extra Class in Unsupervised Domain Adaptation | Tran, Hai H.; Ahn, Sumyeong; Lee, Taeyoung; Yi, Yung | Korea Advanced Institute of Science and Technology | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
636 | Road Network Metric Learning for Estimated Time of Arrival | Sun, Yiwen; Fu, Kun; Wang, Zheng; Zhang, Changshui; Ye, Jieping | Tsinghua University | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
638 | Boundary-Aware Graph Convolution for Semantic Segmentation | Hu, Hanzhe; Cui, Jinshi, Jinshi; Zha, Hongbin | Peking University | Poster | PS T5.5 | DAY 3 – January 14, 2021 |
643 | VSB^2-Net: Visual-Semantic Bi-Branch Network for Zero-Shot Hashing | li, xin; Wang, Xiangfeng; Jin, Bo; Zhang, Wenjie; Wang, Jun; Zha, Hongyuan | East China Normal University | Poster | PS T4.2 | DAY 2 – January 13, 2021 |
644 | MRP-Net: A Light Multiple Region Perception Neural Network for Multi-Label AU Detection | Tang, Yang; Chen, Shuang; Zhang, Honggang; Wang, Gang; Yang, Rui | Beijing University of Posts and Telecommunications | Poster | PS T2.2 | DAY 2 – January 13, 2021 |
645 | Deep Iterative Residual Convolutional Network for Single Image Super-Resolution | Umer, Rao Muhammad; Foresti, Gian Luca; Micheloni, Christian | University of Udine | Oral | OS T5.1 – PS T5.1 | DAY 1 – January 12, 2021 – DAY 1 – January 12, 2021 |
647 | Heterogeneous Graph-Based Knowledge Transfer for Generalized Zero-Shot Learning | Wang, Junjie; Wang, Xiangfeng; Jin, Bo; Yan, Junchi; Zhang, Wenjie; Zha, Hongyuan | East China Normal University | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
648 | Visual Saliency Oriented Vehicle Scale Estimation | Ding, Jiali; Liu, Tie; Chen, Qixin; Yuan, Zejian; Shang, Yuanyuan | Capital Normal University | Poster | PS T3.4 | DAY 2 – January 13, 2021 |
649 | Hierarchical Classification with Confidence Using Generalized Logits | Davis, James W.; Liang, Tong; Enouen, James; Ilin, Roman | Ohio State University | Poster | PS T1.1 | DAY 1 – January 12, 2021 |
651 | P-DIFF: Learning Classifier with Noisy Labels Based on Probability Difference Distributions | Hu, Wei; Zhao, Qihao; Huang, Yangyu; Zhang, Fan | Microsoft Research Asia | Poster | PS T3.4 | DAY 2 – January 13, 2021 |
652 | RSAN: Residual Subtraction and Attention Network for Single Image Super-Resolution | Wei, Shuo; Sun, Xin; Zhao, Haoran; Dong, Junyu | Ocean University of China | Oral | OS T5.1 – PS T5.5 | DAY 1 – January 12, 2021 – DAY 3 – January 14, 2021 |
653 | Audio-Visual Speech Recognition Using a Two-Step Feature Fusion Strategy | Liu, Hong; Xu, Wanlu; Yang, Bing | Peking University | Poster | PS T1.10 | DAY 3 – January 14, 2021 |
654 | Rethinking ReID:Multi-Feature Fusion Person Re-Identification Based on Orientation Constraints | Ai, Mingjing; Shan, Guozhi; Liu, Bo; Liu, Tianyang | Beihang University | Poster | PS T2.2 | DAY 2 – January 13, 2021 |
655 | Cross-Domain Semantic Segmentation of Urban Scenes Via Multi-Level Feature Alignment | Zhang, Bin; Zhao, Shengjie; Zhang, Rongqing | Tongji University | Poster | PS T1.10 | DAY 3 – January 14, 2021 |
656 | DA-RefineNet: Dual-Inputs Attention RefineNet for Whole Slide Image Segmentation | li, ziqiang; Tao, Rentuo; Wu, qianrun; Li, Bin | University of Science and Technology of China, Hefei, China | Poster | PS T5.5 | DAY 3 – January 14, 2021 |
657 | Small Object Detection by Generative and Discriminative Learning | Gu, Yi; Li, Jie; Wu, Chentao; Jia, Weijia; Chen, Jianping | Shanghai Jiaotong University | Poster | PS T3.4 | DAY 2 – January 13, 2021 |
658 | Fused 3-Stage Image Segmentation for Pleural Effusion Cell Clusters | Ma, Sike; Zhao, Meng; Wang, Hao; Shi, Fan; Sun, Xuguo; Chen, Shengyong; Dai, Hong-Ning | Tianjin University of Technology | Poster | PS T5.5 | DAY 3 – January 14, 2021 |
659 | Interpreting the Latent Space of GANs Via Correlation Analysis for Controllable Concept Manipulation | li, ziqiang; Tao, Rentuo; Niu, Hongjing; Mingdao, Yue; Li, Bin | University of Science and Technology of China, Hefei, China | Poster | PS T1.10 | DAY 3 – January 14, 2021 |
660 | One-Stage Multi-Task Detector for 3D Cardiac MR Imaging | Lu, Weizeng; Jia, Xi; Chen, Wei; Savioli, Nicolò; de Marvao, Antonio; Shen, Linlin; O’Regan, Declan; Duan, Jinming | Shenzhen University | Poster | PS T5.5 | DAY 3 – January 14, 2021 |
663 | PHNet: Parasite-Host Network for Video Crowd Counting | Meng, Shiqiao; Li, Jiajie; Guo, Weiwei; Jiang, JinFeng; Ye, Lai | Tongji University | Poster | PS T1.10 | DAY 3 – January 14, 2021 |
664 | Semantic Object Segmentation in Cultural Sites Using Real and Synthetic Data | Ragusa, Francesco; Di Mauro, Daniele; Palermo, Alfio; Furnari, Antonino; Farinella, Giovanni Maria | University of Catania | Poster | PS T1.8 | DAY 2 – January 13, 2021 |
666 | Improving Low-Resolution Image Classification by Super-Resolution with Enhancing High-Frequency Content | Zhou, Liguo; Chen, Guang; Feng, Mingyue; Knoll, Alois | Technical University of Munich | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
668 | Correlation-Based ConvNet for Small Object Detection in Videos | Bosquet, Brais; Mucientes, Manuel; Brea, Victor | University of Santiago de Compostela | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
672 | Stage-Wise Neural Architecture Search | Jordão, Artur; Yamada, Fernando Akio; Lie, Maiko; Schwartz, William | Federal University of Minas Gerais | Poster | PS T1.8 | DAY 2 – January 13, 2021 |
674 | User-Independent Gaze Estimation by Extracting Pupil Parameter and Its Mapping to the Gaze Angle | Han, Sang Yoon; Cho, Nam Ik | Seoul National University | Poster | PS T2.2 | DAY 2 – January 13, 2021 |
675 | Regularized Flexible Activation Function Combinations for Deep Neural Networks | Jie, Renlong; Gao, Junbin; Vasnev, Andrey; Tran, Minh-Ngoc | The University of Sydney | Poster | PS T1.10 | DAY 3 – January 14, 2021 |
677 | Vacant Parking Space Detection Based on Task Consistency and Reinforcement Learning | Nguyen, Manh Hung; Chao, Tzu-Yin; Huang, Ching-Chun | National Chiao Tung University | Poster | PS T1.10 | DAY 3 – January 14, 2021 |
678 | Disentangled Representation Based Face Anti-Spoofing | Liu, Zhao; Feng, Zunlei; Zou, Zeyu; Zhang, Rong; Song, Mingli; Shen, Jianping | Ping An Life Insurance Of China, Ltd. | Poster | PS T2.2 | DAY 2 – January 13, 2021 |
679 | Online Object Recognition Using CNN-Based Algorithm on High-Speed Camera Imaging | Namiki, Shigeaki; Yokoyama, Keiko; yachida, shoji; Shibata, Takashi; Miyano, Hiroyoshi; Ishikawa, Masatoshi | NEC Corporation | Poster | PS T3.4 | DAY 2 – January 13, 2021 |
681 | Stylized-Colorization for Line Arts | Fang, Tzu-Ting; Vo, Minh Duc; Sugimoto, Akihiro; Lai, Shang-Hong | The Graduate University for Advanced Studies | Poster | PS T3.4 | DAY 2 – January 13, 2021 |
683 | Integrating Historical States and Co-Attention Mechanism for Visual Dialog | Jiang, Tianling; Ji, Yi; Liu, Chunping | Soochow University | Poster | PS T3.8 | DAY 3 – January 14, 2021 |
684 | Video Episode Boundary Detection with Joint Episode-Topic Model | Wang, Shunyao; Tian, Ye; Wang, Ruidong; Du, Yang; Yan, Han; Yang, Ruilin; Ma, Jian | Beijing University of Posts and Telecommunications | Poster | PS T4.3 | DAY 3 – January 14, 2021 |
687 | Part-Based Collaborative Spatio-Temporal Feature Learning for Cloth-Changing Gait Recognition | Yao, Lingxiang; Kusakunniran, Worapan; Wu, Qiang; Zhang, Jian; XU, Jingsong | Mahidol University | Poster | PS T2.2 | DAY 2 – January 13, 2021 |
692 | Disentangle, Assemble, and Synthesize: Unsupervised Learning to Disentangle Appearance and Location | Aizawa, Hiroaki; Kataoka, Hirokatsu; Satoh, Yutaka; Kato, Kunihito | Gifu University | Poster | PS T1.10 | DAY 3 – January 14, 2021 |
693 | PCANet: Pyramid Context-Aware Network for Retinal Vessel Segmentation | Zhang, Yi; Chen, Yixuan; Zhang, Kai | Tsinghua University | Poster | PS T5.5 | DAY 3 – January 14, 2021 |
694 | Removing Raindrops from a Single Image Using Synthetic Data | Kokubo, Yoshihito; Asada, Shusaku; Maruyama, Hirotaka; Koide, Masaru; Yamamoto, Kohei; Suetsugu, Yoshihisa | Aisin Seiki Co., Ltd. | Poster | PS T5.5 | DAY 3 – January 14, 2021 |
695 | ACCLVOS: Atrous Convolution with Spatial-Temporal ConvLSTM for Video Object Segmentation | Xu, Muzhou; Zong, Shan; Liu, Chunping; Gong, Shengrong; Wang, Zhaohui; Xia, Yu | Changshu Institute of Technology | Poster | PS T1.10 | DAY 3 – January 14, 2021 |
698 | DualBox: Generating BBox Pair with Strong Correspondence Via Occlusion Pattern Clustering and Proposal Refinement | Ge, Zheng; Hu, Chuyu; Xin, Huang; Qiu BaiQiao; Yoshie, Osamu | Waseda University | Poster | PS T3.4 | DAY 2 – January 13, 2021 |
702 | Adaptive Word Embedding Module for Semantic Reasoning in Large-Scale Detection | Zhang, Yu; wu, xiaoyu; Zhu, Ruolin | Institute of Automation, Chinese Academy of Sciences | Poster | PS T3.8 | DAY 3 – January 14, 2021 |
703 | A Comparison of Neural Network Approaches for Melanoma Classification | Frasca, Maria; Nappi, Michele; Risi, Michele; Tortora, Genoveffa; Auriemma Citarella, Alessia | University of Salerno | Poster | PS T5.2 | DAY 1 – January 12, 2021 |
704 | AdaFilter: Adaptive Filter Design with Local Image Basis Decomposition for Optimizing Image Recognition Preprocessing | Suzuki, Aiga; Ito, Keiichi; Ibe, Takahide; Otsu, Nobuyuki | Adacotech Incorporated | Poster | PS T5.5 | DAY 3 – January 14, 2021 |
705 | Face Anti-Spoofing Using Spatial Pyramid Pooling | Shi, Lei; Zhou, Zhuo; GUO, Zhenhua | Tsinghua University | Poster | PS T2.2 | DAY 2 – January 13, 2021 |
706 | Multiple Document Datasets Pre-Training Improves Text Line Detection with Deep Neural Networks | Boillet, Mélodie; Kermorvant, Christopher; paquet, thierry | University of Rouen-Normandy; Teklia | Oral | OS T4.1 – PS T4.1 | DAY 1 – January 12, 2021 – DAY 1 – January 12, 2021 |
707 | Ballroom Dance Recognition from Audio Recordings | Pavlin, Tomas; Cech, Jan; Matas, Jiri | Czech Technical University in Prague | Poster | PS T5.1 | DAY 1 – January 12, 2021 |
710 | Low-Cost Lipschitz-Independent Adaptive Importance Sampling of Stochastic Gradients | Liu, Huikang; Wang, Xiaolu; Li, Jiajin; So, Man-Cho Anthony | The Chinese University of Hong Kong | Oral | OS T1.2 – PS T1.5 | DAY 1 – January 12, 2021 – DAY 2 January 13, 2021 |
711 | Feature Pyramid Hierarchies for Multi-Scale Temporal Action Detection | He, Jiayu; Li, Guohui; Lei, Jun | National University of Defense Technology | Poster | PS T1.10 | DAY 3 – January 14, 2021 |
719 | Dual Loss for Manga Character Recognition with Imbalanced Training Data | Li, Yonggang; Zhou, Yafeng; Wang, Yongtao; Qin, Xiaoran; Tang, Zhi | Peking University | Poster | PS T4.2 | DAY 2 – January 13, 2021 |
720 | Parallel Network to Learn Novelty from the Known | Du, Shuaiyuan; Hong, Chaoyi; Pan, Zhiyu; Feng, Chen; Cao, Zhiguo | School of Artificial Intelligence and Automation | Poster | PS T3.8 | DAY 3 – January 14, 2021 |
721 | Rethinking Experience Replay: A Bag of Tricks for Continual Learning | Buzzega, Pietro; Boschini, Matteo; Porrello, Angelo; Calderara, Simone | University of Modena and Reggio Emilia | Poster | PS T1.8 | DAY 2 – January 13, 2021 |
723 | Person Recognition with HGR Maximal Correlation on Multimodal Data | Liang, Yihua; Ma, Fei; Li, Yang; Huang, Shao-Lun | Tsinghua University | Poster | PS T5.5 | DAY 3 – January 14, 2021 |
724 | Variational Deep Embedding Clustering by Augmented Mutual Information Maximization | Ji, Qiang; Sun, Yanfeng; Hu, Yongli; Yin, Baocai | Beijing University of Technology | Poster | PS T1.10 | DAY 3 – January 14, 2021 |
725 | A Novel Region of Interest Extraction Layer for Instance Segmentation | Rossi, Leonardo; Karimi, Akbar; Prati, Andrea | University of Parma | Poster | PS T1.8 | DAY 2 – January 13, 2021 |
726 | Detection and Correspondence Matching of Corneal Reflections for Eye Tracking Using Deep Learning | Chugh, Soumil; Brousseau, Braiden; Rose, Jonathan; Eizenman, Moshe | University of Toronto | Poster | PS T1.8 | DAY 2 – January 13, 2021 |
727 | Siamese Fully Convolutional Tracker with Motion Correction | Francis, Mathew; Guha, Prithwijit | Indian Institute of Technology Guwahati | Poster | PS T3.6 | DAY 2 – January 13, 2021 |
730 | S2I-Bird: Sound-To-Image Generation of Bird Species Using Generative Adversarial Networks | Shim, Joo Yong; Kim, Joongheon; Kim, Jong-Kook | Korea University | Poster | PS T3.8 | DAY 3 – January 14, 2021 |
731 | Modulation Pattern Detection Using Complex Convolutions in Deep Learning | Krzyston, Jakob; Bhattacharjea, Rajib; Stark, Andrew | Georgia Institute of Technology | Poster | PS T1.8 | DAY 2 – January 13, 2021 |
734 | Responsive Social Smile: A Machine-Learning Based Multimodal Behavior Assessment Framework towards Early Stage Autism Screening | Pan, Yueran; Cai, Kunjing; Cheng, Ming; Zou, Xiaobing; Li, Ming | Duke Kunshan University | Poster | PS T2.2 | DAY 2 – January 13, 2021 |
735 | Hierarchically Aggregated Residual Transformation for Single Image Super Resolution | Hou, Zejiang; Kung, SY | Princeton University | Poster | PS T5.7 | DAY 4 – January 15, 2021 |
736 | Label Self-Adaption Hashing for Image Retrieval | Lu, Jianglin; Lai, Zhihui; Lin, Jingxu; Lin, Qinghong; Zhou, Jie | Nanjing University of Science and Technology | Poster | PS T5.5 | DAY 3 – January 14, 2021 |
738 | Fast and Accurate Real-Time Semantic Segmentation with Dilated Asymmetric Convolutions | Rosas-Arias, Leonel; Benitez-Garcia, Gibran; Portillo-Portillo, Jose; Sanchez-Perez, Gabriel; Yanai, Keiji | The University of Electro-Communications | Poster | PS T5.3 | DAY 2 – January 13, 2021 |
740 | Neural Compression and Filtering for Edge-assisted Real-time Object Detection in Challenged Networks | Matsubara, Yoshitomo; Levorato, Marco | University of California, Irvine | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
741 | Self-Selective Context for Interaction Recognition | Kilickaya, Kilickaya; Hussein, Noureldien; Gavves, Efstratios; Smeulders, Arnold | University of Amsterdam | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
743 | Teacher-Student Training and Triplet Loss for Facial Expression Recognition under Occlusion | Georgescu, Mariana-Iuliana; Ionescu, Radu | University of Bucharest | Oral | OS T2.2 – PS T2.4 | DAY 3 – January 14, 2021 – DAY 3 – January 14, 2021 |
744 | Temporally Consistent Geo-Localization through Map Learning | Zha, Bing; Yilmaz, Alper | Student | Poster | PS T1.8 | DAY 2 – January 13, 2021 |
746 | Unsupervised deep learning for text line segmentation | Kurar Barakat, Berat; Droby, Ahmad; Alaasam, Reem; Madi, Borak; Rabaev, Irina; Shammes, Raed; El-Sana, Jihad | Ben-Gurion University | Poster | PS T4.3 | DAY 3 – January 14, 2021 |
748 | The eXPose Approach to Crosslier Detection | Barata, Antonio; Takes, Frank; van den Herik, Hendrik; Veenman, Cor | Leiden University | Poster | PS T1.8 | DAY 2 – January 13, 2021 |
749 | RefiNet: 3D Human Pose Refinement with Depth Maps | D’Eusanio, Andrea; Pini, Stefano; Borghi, Guido; Vezzani, Roberto; Cucchiara, Rita | University of Modena and Reggio Emilia | Oral | OS T2.3 – PS T2.2 | DAY 4 – January 15, 2021 – DAY 2 – January 13, 2021 |
750 | Fall Detection by Human Pose Estimation and Kinematic Theory | Dentamaro, Vincenzo; Impedovo, Donato; PIRLO, Giuseppe | Università degli studi di Bari | Poster | PS T2.3 | DAY 2 – January 13, 2021 |
751 | Aerial Road Segmentation in the Presence of Topological Label Noise | Henry, Corentin; Fraundorfer, Friedrich; Vig, Eleonora | German Aerospace Center (DLR) | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
752 | Generic Document Image Dewarping by Probabilistic Discretization of Vanishing Points | Simon, Gilles; Tabbone, Salvatore | Nancy-Université | Poster | PS T4.3 | DAY 3 – January 14, 2021 |
755 | Hybrid Network for End-To-End Text-Independent Speaker Identification | Ghezaiel, Wajdi; Brun, Luc; lezoray, olivier | NormaSTIC CNRS | Poster | PS T2.3 | DAY 2 – January 13, 2021 |
758 | Cycle-Consistent Adversarial Networks and Fast Adaptive Bi-Dimensional Empirical Mode Decomposition for Style Transfer | Batziou, Elissavet; Alvanitopoulos, Petros; Ioannidis, Konstantinos; Patras, Ioannis; Vrochidis, Stefanos; Kompatsiaris, Ioannis | CERTH, QMUL | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
761 | Cost-Effective Adversarial Attacks against Scene Text Recognition | Yang, Mingkun; Zheng, Haitian; Bai, Xiang; Luo, Jiebo | Huazhong University of Science and Technology | Poster | PS T4.3 | DAY 3 – January 14, 2021 |
762 | Adversarially Constrained Interpolation for Unsupervised Domain Adaptation | Azzam, Mohamed; Tohokantche Gnanha, Aurele; Wong, Hau-San; Wu, Si | City University of Hong Kong | Poster | PS T1.10 | DAY 3 – January 14, 2021 |
763 | Encoder-Decoder Based Convolutional Neural Networks with Multi-Scale-Aware Modules for Crowd Counting | Thanasutives, Pongpisit; Fukui, Ken-ichi; Numao, Masayuki; Kijsirikul, Boonserm | Osaka University | Poster | PS T2.2 | DAY 2 – January 13, 2021 |
765 | Boosting High-Level Vision with Joint Compression Artifacts Reduction and Super-Resolution | Xiang, Xiaoyu; Lin, Qian; Allebach, Jan | Purdue University | Poster | PS T5.7 | DAY 4 – January 15, 2021 |
766 | 3D Pots Configuration System by Optimizing Over Geometric Constraints | Kim, Jae Eun; Arshad, Muhammad Zeeshan; Yoo, Seong Jong; Hong, Je Hyeong; Kim, Jinwook; Kim, Young Min | Seoul National University | Poster | PS T5.5 | DAY 3 – January 14, 2021 |
768 | Unsupervised Face Manipulation via Hallucination | Kusumam, Keerthy; Sanchez, Enrique; Tzimiropoulos, Georgios | University of Nottingham | Poster | PS T5.1 | DAY 1 – January 12, 2021 |
771 | Classifier Pool Generation based on a Two-level Diversity Approach | Monteiro, Marcos; Britto, Alceu; Barddal, Jean Paul; Oliveira, Luiz; Sabourin, Robert | Pontificia Universidade Católica do Paraná | Poster | PS T1.8 | DAY 2 – January 13, 2021 |
775 | A Novel Deep-Learning Pipeline for Light Field Image Based Material Recognition | Wang, Yunlong; Zhang, Kunbo; Sun, Zhenan | Institute of Automation, Chinese Academy of Sciences (CASIA) | Oral | OS T3.6 – PS T3.4 | DAY 4 – January 15, 2021 – DAY 2 – January 13, 2021 |
778 | Complex-Object Visual Inspection: Empirical Studies on a Multiple Lighting Solution | Aghaei, Maya; Bustreo, Matteo; Morerio, Pietro; Carissimi, Nicolò; Del Bue, Alessio; Murino, Vittorio | Istituto Italiano di Tecnologia (IIT) | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
779 | ISP4ML: The Role of Image Signal Processing in Efficient Deep Learning Vision Systems | Hansen, Patrick; Vilkin, Alexey; Khrustalev, Yury; Imber, James Stuart; Talagala, Dumidu Sanjaya; Hanwell, David; Mattina, Matthew; Whatmough, Paul | Arm | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
784 | Automatic Student Network Search for Knowledge Distillation | Zhang, Zhexi; Zhu, Wei; Yan, Junchi; GAO, PENG; Xie, Guotong | Ping An Technology | Poster | PS T1.10 | DAY 3 – January 14, 2021 |
785 | AerialMPTNet: Multi-Pedestrian Tracking in Aerial Imagery Using Temporal and Graphical Features | Kraus, Maximilian; Azimi, Seyed Majid; Ercelik, Emec; Bahmanyar, Reza; Reinartz, Peter; Knoll, Alois | Technical University of Munich | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
786 | STaRFlow: A SpatioTemporal Recurrent Cell for Lightweight Multi-Frame Optical Flow Estimation | Godet, Pierre; Boulch, Alexandre; Plyer, Aurélien; Le Besnerais, Guy | ONERA | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
787 | Deep Topic Modeling by Multilayer Bootstrap Network and Lasso | Wang, Jian-Yu; Zhang, Xiao-Lei | Northwestern Polytechnical University | Poster | PS T1.10 | DAY 3 – January 14, 2021 |
788 | Deep transformation models: Tackling complex regression problems with neural network based transformation models | Sick, Beate; Hothorn, Torsten; Dürr, Oliver | ZHAW and University of Zurich | Poster | PS T1.8 | DAY 2 – January 13, 2021 |
790 | FC-DCNN: A Densely Connected Neural Network for Stereo Estimation | Hirner, Dominik; Fraundorfer, Friedrich | University of Technology | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
792 | A Close Look at Deep Learning with Small Data | Brigato, Lorenzo; Iocchi, Luca | Sapienza University of Rome | Poster | PS T1.8 | DAY 2 – January 13, 2021 |
795 | Adaptive Matching of Kernel Means | Cheng, Miao; You, Xinge | Guangxi Normal University | Poster | PS T1.10 | DAY 3 – January 14, 2021 |
796 | From Certain to Uncertain: Toward Optimal Solution for Offline Multiple Object Tracking | Zhao, Kaikai; Imaseki, Takashi; Mouri, Hiroshi; Suzuki, Einoshin; Matsukawa, Tetsu | Tokyo University of Agriculture and Technology | Poster | PS T3.8 | DAY 3 – January 14, 2021 |
797 | Adaptive Context-Aware Discriminative Correlation Filters for Robust Visual Object Tracking | Xu, Tianyang; Feng, Zhen-Hua; Wu, Xiaojun; Kittler, Josef | University of Surrey | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
798 | Accurate Background Subtraction Using Dynamic Object Presence Probability in Sports Scenes | Watanabe, Ryosuke; Chen, Jun; Konno, Tomoaki; Naito, Sei | KDDI Research, Inc. | Poster | PS T5.5 | DAY 3 – January 14, 2021 |
800 | Variational Information Bottleneck Model for Accurate Indoor Position Recognition | Qian, Weizhu; Gechter, Franck | University of Burgundy – Franche-Comté | Poster | PS T1.8 | DAY 2 – January 13, 2021 |
801 | Audio-Video Detection of the Active Speaker in Meetings | Madrigal, Francisco; Lerasle, Frederic; Pibre, Lionel; Ferrané, Isabelle | LAAS-CNRS | Poster | PS T2.3 | DAY 2 – January 13, 2021 |
804 | Automatic Estimation of Self-Reported Pain by Interpretable Representations of Motion Dynamics | Szczapa, Benjamin; Daoudi, Mohammed; Berretti, Stefano; Pala, Pietro; Del Bimbo, Alberto; Hammal, Zakia | Université de Lille/CRIStAL (UMR 9189) | Poster | PS T1.9 | DAY 3 – January 14, 2021 |
805 | DAG-Net: Double Attentive Graph Neural Network for Trajectory Forecasting | Monti, Alessio; Bertugli, Alessia; Calderara, Simone; Cucchiara, Rita | University of Modena and Reggio Emilia | Poster | PS T1.9 | DAY 3 – January 14, 2021 |
807 | Active Sampling for Pairwise Comparisons via Approximate Message Passing and Information Gain Maximization | Mikhailiuk, Aliaksei; Wilmot, Clifford; Perez-Ortiz, Maria; Yue, Dingcheng; Mantiuk, Rafal | University of Cambridge | Oral | OS T1.2 – PS T1.2 | DAY 1 – January 12, 2021 – DAY 1 – January 12, 2021 |
808 | Recursive Convolutional Neural Networks for Epigenomics | Symeonidi, Aikaterini; Nicolaou, Anguelos; Johannes, Frank; Christlein, Vincent | Population Epigenetics & Epigenomics | Poster | PS T5.1 | DAY 1 – January 12, 2021 |
810 | DE-Net: Dilated Encoder Network for Automated Tongue Segmentation | Tang, Hui; Wang, Bin; Zhou, Jun; Gao, Yongsheng | Griffith University | Poster | PS T5.3 | DAY 2 – January 13, 2021 |
811 | DID: A Nested Dense in Dense Structure with Variable Local Dense Blocks for Super-Resolution Image Reconstruction | Li, Longxi; Feng, Hesen; Zheng, Bing; Ma, Lihong; Tian, Jing | South China University of Technology | Poster | PS T5.5 | DAY 3 – January 14, 2021 |
813 | An Adaptive Video-To-Video Face Identification System Based on Self-Training | Lopez-Lopez, Eric; Regueiro, Carlos V.; Pardo, Xosé M. | Universidade da Coruña, CITIC, Computer Architecture Group | Poster | PS T2.3 | DAY 2 – January 13, 2021 |
816 | LFIR2Pose: Pose Estimation from an Extremely Low-Resolution FIR Image Sequence | Iwata, Saki; Kawanishi, Yasutomo; Deguchi, Daisuke; Ide, Ichiro; Murase, Hiroshi; Aizawa, Tomoyoshi | Nagoya university | Poster | PS T2.2 | DAY 2 – January 13, 2021 |
818 | Using Meta Labels for the Training of Weighting Models in a Sample-Specific Late Fusion Classification Architecture | Bellmann, Peter; Thiam, Patrick; Schwenker, Friedhelm | Ulm University | Poster | PS T1.9 | DAY 3 – January 14, 2021 |
819 | Human or Machine? It Is Not What You Write, but How You Write It | Leiva, Luis; Diaz, Moises; Ferrer, M.A.; Plamondon, Réjean | Aalto University | Poster | PS T2.3 | DAY 2 – January 13, 2021 |
820 | Image Sequence Based Cyclist Action Recognition Using Multi-Stream 3D Convolution | Zernetsch, Stefan; Schreck, Steven; Kress, Viktor; Doll, Konrad; Sick, Bernhard | University of Applied Sciences Aschaffenburg | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
822 | Object Detection in the DCT Domain: Is Luminance the Solution? | Deguerre, Benjamin; Chatelain, Clement; Gasso, Gilles | LITIS | Poster | PS T1.9 | DAY 3 – January 14, 2021 |
823 | Estimation of Abundance and Distribution of SaltMarsh Plants from Images Using Deep Learning | Parashar, Jayant; Bhandarkar, Suchendra; Simon, Jacob; Hopkinson, Brian; Pennings, Steven | University of Georgia | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
824 | Fusion of Global-Local Features for Image Quality Inspection of Shipping Label | Suh, Sungho; Lukowicz, Paul; Lee, Yong Oh | KIST Europe | Poster | PS T4.3 | DAY 3 – January 14, 2021 |
831 | Generalized Shortest Path-Based Superpixels for Accurate Segmentation of Spherical Images | Giraud, Rémi; Borba Pinheiro, Rodrigo; Berthoumieu, Yannick | Bordeaux INP | Poster | PS T5.1 | DAY 1 – January 12, 2021 |
833 | OmniFlowNet: A Perspective Neural Network Adaptation for Optical Flow Estimation in Omnidirectional Images | Artizzu, Charles-Olivier; Zhang, Haozhou; Allibert, Guillaume; Demonceaux, Cédric | Universite Cote d’Azur, CNRS, I3S | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
834 | Emerging Relation Network and Task Embedding for Multi-Task Regression Problems.pdf | Jens, Schreiber; Sick, Bernhard | University of Kassel | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
835 | MaxDropout: Deep Neural Network Regularization Based on Maximum Output Values | Santos, Claudio Filipi Gonçalves; Colombo, Danilo; Roder, Mateus; Papa, Joao Paulo | Federal University of São Carlos | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
838 | Complementing Representation Deficiency in Few-Shot Image Classification: A Meta-Learning Approach | Zhong, Xian; Gu, Cheng; Huang, Wenxin; Li, Lin; Chen, Shuqin; Lin, Chia-Wen | Wuhan University | Poster | PS T3.8 | DAY 3 – January 14, 2021 |
839 | Model Decay in Long-Term Tracking | Gavves, Efstratios; Tao, Ran; Gupta, Deepak; Smeulders, Arnold | University of Amsterdam | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
841 | Few-Shot Few-Shot Learning and the Role of Spatial Attention | Lifchitz, Yann; Avrithis, Yannis; Picard, Sylvaine | Inria | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
844 | Countering Anti-Forensics of SIFT-Based Copy-Move Detection | Salman, Muhammad; Uhl, Andreas | University of Salzburg | Poster | PS T5.1 | DAY 1 – January 12, 2021 |
845 | Deep Convolutional Embedding for Digitized Painting Clustering | Castellano, Giovanna; Vessio, Gennaro | University of Bari | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
846 | Learning from Learners: Adapting Reinforcement Learning Agents to be Competitive in a Card Game. | Alves de Barros, Pablo Vinicius; Tanevska, Ana; Sciutti, Alessandra | Italian Institute of Technology | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
847 | Revisiting the Training of Very Deep Neural Networks without Skip Connections | Oyedotun, Oyebade Kayode; Shabayek, Abd El Rahman; Aouada, Djamila; Ottersten, Bjorn | University of Luxembourg | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
848 | Deep Top-Rank Counter Metric for Person Re-Identification | Chen, Chen; Dou, Hao; Hu, Xiyuan; Peng, Silong | Chinese Academy of Sciences | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
850 | Deep Ordinal Regression with Label Diversity | Berg, Axel; Oskarsson, Magnus; OConnor, Mark | Arm Research, Lund University | Oral | OS T1.7 – PS T1.14 | DAY 4 – January 15, 2021 – DAY 4 – January 15, 2021 |
852 | P ≈ NP, at Least in Visual Question Answering | Jolly, Shailza; Palacio, Sebastian; Folz, Joachim; Raue, Federico; Hees, Jörn; Dengel, Andreas | University of Kaiserslautern, DFKI | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
853 | Light3DPose: Real-Time Multi-Person 3D Pose Estimation from Multiple Views | Elmi, Alessio; Mazzini, Davide; Tortella, Pietro | Checkout Technologies | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
856 | Ground-truthing Large Human Behavior Monitoring Datasets | Qasim, Tehreem; Fisher, Robert; Bhatti, Naeem | Quaid i Azam University | Poster | PS T2.3 | DAY 2 – January 13, 2021 |
858 | A Two-Stream Recurrent Network for Skeleton-Based Human Interaction Recognition | Men, Qianhui; Ho, Edmond S. L.; Shum, Hubert P. H.; Leung, Howard | City University of Hong Kong | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
859 | Learning to Find Good Correspondences of Multiple Objects | Xie, Youye; Tang, Yingheng; Tang, Gongguo; Hoff, William | Colorado School of Mines | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
861 | A Cheaper Rectified-Nearest-Feature-Line-Segment Classifier Based on Safe Points | Orozco-Alzate, Mauricio; Bicego, Manuele | University of Verona | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
864 | Progressive Gradient Pruning for Classification, Detection and Domain Adaptation | Nguyen.Meidine, Le Thanh; Granger, Eric; Pedersoli, Marco; Kiran, Madhu; Blais-Morin, Louis-Antoine | Ecole de Technologie Superieure, Universite de Quebec | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
868 | An Empirical Bayes Approach to Topic Modeling | Gangopadhyay, Anirban | Columbia University | Oral | OS T1.2 – PS T1.1 | DAY 1 – January 12, 2021 – DAY 1 – January 12, 2021 |
870 | Global Feature Aggregation for Accident Anticipation | Fatima, Mishal; Karim Khan, Umar; Min Kyung, Chong | Korea Advanced Institute of Science and Technology | Oral | OS T3.1 – PS T3.7 | DAY 1 – January 12, 2021 – DAY 3 – January 14, 2021 |
872 | Detecting Manipulated Facial Videos: A Time Series Solution | Zhewei, Zhang; Can, Ma; Meilin, Gao; Bowen, Ding | The Third Research Laboratory, Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China | Poster | PS T2.2 | DAY 2 – January 13, 2021 |
874 | Task-based Focal Loss for Adversarially Robust Meta-Learning | Hou, Yufan; Zou, Lixin; Liu, Weidong | Tsinghua University | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
876 | On the Impact of Lossy Image and Video Compression on the Performance of Deep Convolutional Neural Network Architectures | Poyser, Matt; Breckon, Toby; Atapour Abarghouei, Amir | University of Durham | Oral | OS T5.4 – PS T5.4 | DAY 3 – January 14, 2021 – DAY 2 – January 13, 2021 |
877 | Aggregating Object Features Based on Attention Weights for Fine-Grained Image Retrieval | Lin, Hongli; Song, Yongqi; Wang, Weisheng; Zeng, Zixuan; wang, jiayi | Hunan University | Poster | PS T5.5 | DAY 3 – January 14, 2021 |
879 | Unsupervised Domain Adaptation with Multiple Domain Discriminators and Adaptive Self-Training | Spadotto, Teo; Toldo, Marco; Michieli, Umberto; Zanuttigh, Pietro | University of Padova | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
880 | Electroencephalography Signal Processing Based on Textural Features for Monitoring the Drivers State by a Brain-Computer Interface | Orrù, Giulia; Micheletto, Marco; Terranova, Fabio; Marcialis, Gian Luca | Università degli studi di Cagliari | Poster | PS T2.3 | DAY 2 – January 13, 2021 |
883 | Constrained Spectral Clustering Network with Self-Training | Liu, Xinyue; Yang, Shichong; Zong, Linlin | Dalian University of Technology | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
886 | A General Model for Learning Node and Graph Representations Jointly | Chen, Chaofan | University of Science and Technology of China | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
889 | MedZip: 3D Medical Images Lossless Compressor Using Recurrent Neural Network (LSTM) | Nagoor, Omniah; Whittle, Joss; Deng, Jingjing; Mora, Benjamin; Jones, Mark W. | Swansea University | Poster | PS T5.4 | DAY 2 – January 13, 2021 |
891 | Moto: Enhancing Embedding with Multiple Joint Factors for Chinese Text Classification | Tang, Xunzhu; Zhu, Rujie; Sun, Tiezhu; Wang, Shi | Huazhong University of Science and Technology | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
892 | CKG: Dynamic Representation Based on Context and Knowledge Graph | Tang, Xunzhu; Sun, Tiezhu; Zhu, Rujie; Wang, Shi | Huazhong University of Science and Technology | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
893 | Motion Segmentation with Pairwise Matches and Unknown Number of Motions | Arrigoni, Federica; Magri, Luca; Pajdla, Tomas | University of Trento | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
894 | Breast Anatomy Enriched Tumor Saliency Estimation | Xu, Fei; zhang, yingtao; Cheng, Heng-Da; Ding, Jianrui; Zhang, Boyu; Ning, Chunping; wang, ying | Utah State University | Poster | PS T5.1 | DAY 1 – January 12, 2021 |
895 | Automatic Detection of Stationary Waves in the Venus Atmosphere Using Deep Generative Models | Narita, Minori; Kimura, Daiki; Imamura, Takeshi | University of Massachusetts, Amherst | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
896 | Fast and Efficient Neural Network for Light Field Disparity Estimation | Ma, Dizhi; Lumsdaine, Andrew | University of Washington | Poster | PS T5.1 | DAY 1 – January 12, 2021 |
899 | PoseCVAE: Anomalous Human Activity Detection | Jain, Yashswi; Sharma, Ashvini Kumar; Velmurugan, Rajbabu; Banerjee, Biplab | Indian Institute of Technology Bombay | Poster | PS T2.3 | DAY 2 – January 13, 2021 |
903 | Edge-Aware Monocular Dense Depth Estimation with Morphology | Li, Zhi; Zhu, Xiaoyang; Yu, Haitao; Zhang, Qi; Jiang, Yongshi | Institute of Automation, Chinese Academy of Sciences | Poster | PS T3.7 | DAY 3 – January 14, 2021 |
905 | Stroke Based Posterior Attention for Online Handwritten Mathematical Expression Recognition | Wu, Changjie; Wang, Qing; Zhang, Jianshu; Du, Jun; Wang, Jiaming; wu, jiajia; Hu, Jin-Shui | University of Science and Technology of China | Poster | PS T4.2 | DAY 2 – January 13, 2021 |
906 | PIN: A Novel Parallel Interactive Network for Spoken Language Understanding | Zhou, Peilin; Huang, Zhiqi; Liu, Fenglin; Zou, Yuexian | Peking University | Poster | PS T2.2 | DAY 2 – January 13, 2021 |
909 | SIDGAN: Single Image Dehazing without Paired Supervision | Wei, Pan; Wang, Xin; Wang, Lei; Xiang, Ji | Institute of Information Engineering, Chinese Academy of Sciences | Poster | PS T3.7 | DAY 3 – January 14, 2021 |
911 | An Adaptive Model for Face Distortion Correction | Nguyen, Duong H.; Bui, Tien D. | Concordia University | Poster | PS T5.7 | DAY 4 – January 15, 2021 |
912 | Linear Embedding by Joint Robust Discriminant Analysis and Inter-class Sparsity | Dornaika, Fadi; Khoder Ahmad | University of the Basque Country | Oral | OS T1.3 – PS T1.6 | DAY 1 – January 12, 2021 – DAY 2 – January 13, 2021 |
914 | Top-DB-Net: Top DropBlock for Activation Enhancement in Person Re-Identification | Quispe, Rodolfo; Pedrini, Helio | University of Campinas | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
917 | 6D Pose Estimation with Correlation Fusion | Cheng, Yi; Zhu, Hongyuan; Sun, Ying; Acar, Cihan; Jing, Wei; Wu, Yan; Li, Liyuan; Tan, Cheston; Lim, Joo-Hwee | A*STAR | Poster | PS T3.7 | DAY 3 – January 14, 2021 |
918 | Predicting Online Video Advertising Effects With Multimodal Deep Learning | Ikeda, Jun; Seshime, Hiroyuki; Wang, Xueting; Yamasaki, Toshihiko | The University of Tokyo | Poster | PS T5.7 | DAY 4 – January 15, 2021 |
920 | Face Image Quality Assessment for Model and Human Perception | chen, ken; Wu, Yichao; Li, Zhenmao; wu, yudong; liang, ding | Sensetime Group Limited | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
924 | An Accurate Threshold Insensitive Kernel Detector for Arbitrary Shaped Text | Qian, Xijun; Liu, Yifan; Yang Yu-Bin | Nanjing University | Oral | OS T 4.2 – PS T4.2 | DAY 4 – January 15, 2021 – DAY 2 – January 13, 2021 |
925 | Smart Inference for Multidigit Convolutional Neural Network Based Barcode Decoding | Do, Duy-Thao; Yalew, Tolcha; Jun, Tae Joon; Kim, Daeyoung | KAIST | Poster | PS T3.7 | DAY 3 – January 14, 2021 |
926 | Cross-People Mobile-Phone Based Airwriting Character Recognition | Li, Yunzhe; Zheng, Hui; Zhu, He; Ai, Haojun; Dong, Xiaowei | Wuhan University | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
932 | The Color Out of Space: Learning Self-Supervised Representations for Earth Observation Imagery | vincenzi, stefano; Porrello, Angelo; Buzzega, Pietro; Cipriano, Marco; Fronte, Pietro; Cuccu, Roberto; Ippoliti, Carla; Conte, Annamaria; Calderara, Simone | University of Modena and Reggio Emilia | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
934 | Fixed Simplex Coordinates for Angular Margin Loss in CapsNet | Pucci, Rita; Micheloni, Christian; Foresti, Gian Luca; Martinel, Niki | University of Udine | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
936 | Digit Recognition Applied to Reconstructed Audio Signals Using Deep Learning | Toufa, Anastasia-Sotiria; Kotropoulos, Constantine | Aristotle University of Thessaloniki | Poster | PS T5.1 | DAY 1 – January 12, 2021 |
939 | A Globally Optimal Method for the PnP Problem with MRP Rotation Parameterization | Lourakis, Manolis; Terzakis, George | Foundation for Research and Technology – Hellas | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
940 | Hybrid Decomposition Convolution Neural Network and Vocabulary Forest for Image Retrieval | Youcef, Djenouri; Hjelmervik, Jon | SINTEF | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
941 | Second-Order Attention Guided Convolutional Activations for Visual Recognition | Chen, Shannan; Wang, Qian; Sun, Qiule; Liu, Bin; Zhang, Jianxin; Zhang, Qiang | Dalian Minzu University | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
942 | Attentional Wavelet Network for Traditional Chinese Painting Transfer | wang, rui; Huang, Huaibo; Zheng, Aihua; He, Ran | Chinese Academy of Sciences | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
943 | The Effect of Image Enhancement Algorithmson Convolutional Neural Networks | Rodríguez-Rodríguez, José A.; Molina-Cabello, Miguel A.; Benítez-Rochel, Rafaela; López-Rubio, Ezequiel | University of Málaga | Poster | PS T5.4 | DAY 2 – January 13, 2021 |
944 | Neuron-Based Network Pruning Based on Majority Voting | Alqahtani, Ali; Xie, Xianghua; Essa, Ehab; Jones, Mark W. | Swansea University | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
945 | Machine-Learned Regularization and Polygonization of Building Segmentation Masks | Zorzi, Stefano; Bittner, Ksenia; Fraundorfer, Friedrich | Graz University of Technology | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
947 | Adaptive Estimation of Optimal Color Transformations for Deep Convolutional Network Based Homography Estimation | Molina-Cabello, Miguel A.; García-González, Jorge; Luque-Baena, Rafael Marcos; Thurnhofer-Hemsi, Karl; López-Rubio, Ezequiel | University of Málaga | Poster | PS T5.4 | DAY 2 – January 13, 2021 |
951 | On Identification and Retrieval of Near-Duplicate Biological Images: A New Dataset and Protocol | Koker, Thomas E.; Chintapalli, Sai Spandana; Wang, San; Talbot, Blake A.; Wainstock, Daniel; Cicconet, Marcelo; Walsh, Mary C. | Harvard Medical School | Poster | PS T4.1 | DAY 1 – January 12, 2021 |
953 | Cross-Lingual Text Image Recognition Via Multi-Task Sequence to Sequence Learning | Chen, Zhuo; Yin, Fei; Zhang, Xu-Yao; Yang, Qing; Liu, Cheng-Lin | Institute of Automation of Chinese Academy of Sciences | Poster | PS T4.2 | DAY 2 – January 13, 2021 |
955 | Stratified Multi-Task Learning for Robust Spotting of Scene Texts | Dasgupta, Kinjal; Das, Sudip; Bhattacharya, Ujjwal | Indian Statistical Institute, Kolkata | Oral | OS T 4.2 – PS T4.2 | DAY 4 – January 15, 2021 – DAY 2 – January 13, 2021 |
956 | Recursive Recognition of Offline Handwritten Mathematical Expressions | Cotogni, Marco; Cusano, Claudio; Nocera, Antonino | University of Pavia | Poster | PS T4.3 | DAY 3 – January 14, 2021 |
957 | Predicting Chemical Properties Using Self-Attention Multi-Task Learning Based on SMILES Representation | Lim, Sangrak; Lee, Yong Oh | KIST Europe | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
959 | Anime Sketch Colorization by Component-Based Matching Using Deep Appearance Features and Graph Representation | Do, Thien; Van, Pham; Nguyen, Anh; Dang, Trung; Nguyen, Quoc; Hoang, Bach; Nguyen, Giao | Cinnamon AI Labs | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
960 | Textual-Content Based Classification of Bundles of Untranscribed of Manuscript Images | Prieto Fontcuberta, José Ramón; Vidal, Enrique; Bosch, Vicente; Alonso, Carlos; Orcero, Carmen; Márquez, Lourdes | Universitat Politècnica de València | Poster | PS T4.1 | DAY 1 – January 12, 2021 |
962 | Visual Localization for Autonomous Driving: Mapping the Accurate Location in the City Maze | Liu, Dongfang; Cui, Yiming; Guo, Xiaolei; Ding, Wei; Yang, Baijian; Chen, Yingjie | Purdue University | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
963 | A GAN-Based Blind Inpainting Method for Masonry Wall Images | Ibrahim, Yahya; Nagy, Balázs; Benedek, Csaba | Péter Pázmany Catholic University | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
964 | Do We Really Need Scene-Specific Pose Encoders? | Shavit, Yoli; Ferens, Ron | Toga Networks a Huawei Company | Oral | OS T3.4 – PS T3.9 | DAY 3 – January 14, 2021 – DAY 3 – January 14, 2021 |
965 | CardioGAN: An Attention-Based Generative Adversarial Network for Generation of Electrocardiograms | Dasgupta, Subhrajyoti; Das, Sudip; Bhattacharya, Ujjwal | Amity University, Kolkata | Poster | PS T5.7 | DAY 4 – January 15, 2021 |
967 | Unsupervised Moving Object Detection through Background Models for PTZ Camera | Yun, Kimin; Kim, Hyung-Il; Bae, Kangmin; Park, Jongyoul | ETRI | Poster | PS T3.7 | DAY 3 – January 14, 2021 |
968 | Enhanced Feature Pyramid Network for Semantic Segmentation | Beihang | Poster | PS T1.14 | DAY 4 – January 15, 2021 | |
969 | Extracting and Interpreting Unknown Factors with Classifier for Foot Strike Types in Running | Seo, Chanjin; Sabanai, Masato; Goto, Yuta; Tagami, Koji; Ogata, Hiroyuki; Kanosue, Kazuyuki; Ohya, Jun | Waseda University | Poster | PS T5.7 | DAY 4 – January 15, 2021 |
970 | A Self-Supervised GAN for Unsupervised Few-Shot Object Recognition | Nguyen, Khoi; Todorovic, Sinisa | Oregon State University | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
971 | Robust Lexicon-Free Confidence Prediction for Text Recognition | Song, Qi; Jiang, Qianyi; Zhang, Rui; Wei, Xiaolin | Meituan | Poster | PS T4.3 | DAY 3 – January 14, 2021 |
972 | Single Image Super-Resolution with Dynamic Residual Connection | Park, Karam; Soh, Jae Woong; Cho, Nam Ik | Seoul National University, Institute of New Media and Communications | Poster | PS T5.7 | DAY 4 – January 15, 2021 |
974 | Efficient-Receptive Field Block with Group Spatial Attention Mechanism for Object Detection | Zhang, Jiacheng; zhao, zhicheng; Su, Fei | Beijing University of Posts and Telecommunications | Poster | PS T3.7 | DAY 3 – January 14, 2021 |
976 | A Deep Learning-Based Method for Predicting Volumes of Nasopharyngeal Carcinoma for Adaptive Radiation Therapy Treatment | Daoud, Bilel; Morooka, Ken’ichi; Miyauchi, Shoko; Kurazume, Ryo; Mnejja, Wafa; Farhat, Leila; Daoud, Jamel | Kyushu university | Poster | PS T1.14 | DAY 4 – January 15, 2021 |
977 | Learning Sign-Constrained Support Vector Machines | Tajima, Kenya; Tsuchida, Kouhei; Zara, Esmeraldo Ronnie Rey; Ohta, Naoya; Kato, Tsuyoshi | Gunma University | Poster | PS T1.3 | DAY 2 – January 13, 2021 |
979 | Manual-Label Free 3D Detection Via an Open-Source Simulator | Yang, Zhen; Zhang, Chi; Guo, Huiming; Zhang, Zhaoxiang | Institute of Automation, Chinese Academy of Sciences | Poster | PS T1.3 | DAY 2 – January 13, 2021 |
980 | Object Detection Using Dual Graph Network | Chen, Shengjia; Li, Zhixin; Huang, Feicheng; Zhang, Canlong; Ma, Huifang | Guangxi Normal University | Oral | OS T3.5 – PS T3.4 | DAY 4 – January 15, 2021 – DAY 2 – January 13, 2021 |
981 | Factor Screening Using Bayesian Active Learning and Gaussian Process Meta-Modelling | Li, Cheng; Rana, Santu; Gill, Andrew William; Nguyen, Dang; Gupta, Sunil Kumar; Venkatesh, Svetha | National University of Singapore | Poster | PS T1.3 | DAY 2 – January 13, 2021 |
984 | Late Fusion of Bayesian and Convolutional Models for Action Recognition | Maurice, Camille; Madrigal, Francisco; Lerasle, Frederic | LAAS-CNRS | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
985 | Explainable Online Validation of Machine Learning Models for Practical Applications | Fuhl, Wolfgang; Rong, Yao; Motz, Thomas; Scheidt, Michael; Hartel, Andreas Markus; Koch, Andreas; Kasneci, Enkelejda | Eberhard Karls Universität Tübingen | Poster | PS T1.2 | DAY 1 – January 12, 2021 |
986 | Knowledge Distillation for Action Anticipation Via Label Smoothing | Camporese, Guglielmo; Coscia, Pasquale; Furnari, Antonino; Farinella, Giovanni Maria; Ballan, Lamberto | University of Padova | Poster | PS T3.1 | DAY 1 – January 12, 2021 |
987 | Conditional Multi-Task Learning for Plant Disease Identification | Lee, Sue Han; Goëau, Herve; Bonnet, Pierre; Joly, Alexis | Swinburne University of Technology Sarawak Campus | Poster | PS T1.3 | DAY 2 – January 13, 2021 |
991 | Gaussian Constrained Attention Network for Scene Text Recognition | Qiao, Zhi; Qin, Xugong; Zhou, Yu; Yang, Fei; Wang, Weiping | IIE, CAS | Poster | PS T4.3 | DAY 3 – January 14, 2021 |
992 | Unconstrained Facial Expression Recogniton Based on Cascade Decision and Gabor Filters | Wu, Yanhong; Zhang, Lijie; Chen, Guannan; Navarrete Michelini, Pablo | BOE Technology Group Co., Ltd. | Oral | OS T2.2 – PS T2.3 | DAY 3 – January 14, 2021 – DAY 2 – January 13, 2021 |
995 | How Does DCNN Make Decisions? | Lin, Yi; Wang, Namin; Ma, Xiaoqing; Li, Ziwei; Bai, Gang | College of Computer and Control Engineering, Nankai University | Poster | PS T1.3 | DAY 2 – January 13, 2021 |
996 | Augmentation of Small Training Data Using GANs for Enhancing the Performance of Image Classification | Hung, Shih-Kai; Gan, John Q. | University of Essex | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
997 | Semantic Segmentation of Breast Ultrasound Image with Pyramid Fuzzy Uncertainty Reduction and Direction Connectedness Feature | Huang, Kuan; zhang, yingtao; Cheng, Heng-Da; Xing, Ping; Zhang, Boyu | Utah State University | Poster | PS T5.1 | DAY 1 – January 12, 2021 |
998 | Sample-Dependent Distance for 1 : N Identification Via Discriminative Feature Selection | Kawamura, Naoki; Kubota, Susumu | Toshiba Corporation | Poster | PS T1.3 | DAY 2 – January 13, 2021 |
999 | Evaluating Initialization of Nelder-Mead Method for Hyperparameter Optimization in Deep Learning | Takenaga, Shintaro; Watanabe, Shuhei; Nomura, Masahiro; Ozaki, Yoshihiko; Onishi, Masaki; Habe, Hitoshi | Kindai University | Poster | PS T1.3 | DAY 2 – January 13, 2021 |
1000 | Three-Dimensional Lip Motion Network for Text-Independent Speaker Recognition | Wang, Jianrong; Wu, Tong; Wang, Shanyu; Yu, Mei; Fang, Qiang; Zhang, Ju; Liu, Li | Shenzhen Research Institute of Big Data | Poster | PS T2.2 | DAY 2 – January 13, 2021 |
1001 | Context-Aware Residual Module for Image Classification | Bai, Jing; Chen, Ran | North Minzu University | Poster | PS T5.7 | DAY 4 – January 15, 2021 |
1002 | Comparison of Deep Learning and Hand Crafted Features for Mining Simulation Data | Georgiou, Theodoros; Schmitt, Sebastian; Baeck, Thomas; Pu, Nan; Chen, Wei; Lew, Michael | Leiden University | Poster | PS T1.7 | DAY 2 – January 13, 2021 |
1005 | Adaptive Sampling of Pareto Frontiers with Binary Constraints Using Regression and Classification | Heese, Raoul; Bortz, Michael | Fraunhofer-Institut fuer Techno- und Wirtschaftsmathematik | Poster | PS T1.15 | DAY 4 – January 15, 2021 |
1006 | Are Spoofs from Latent Fingerprints a Real Threat for the Best State-Of-Art Liveness Detectors? | Casula, Roberto; Orrù, Giulia; Angioni, Daniele; Feng, Xiaoyi; Marcialis, Gian Luca; Roli, Fabio | Università degli studi di Cagliari | Oral | OS T2.3 – PS T2.2 | DAY 4 – January 15, 2021 – DAY 2 – January 13, 2021 |
1010 | Anomaly Detection, Localization and Classification for Railway Inspection | Gasparini, Riccardo; D’Eusanio, Andrea; Borghi, Guido; Pini, Stefano; Scaglione, Giuseppe; Calderara, Simone; Fedeli, Eugenio; Cucchiara, Rita | University of Modena and Reggio Emilia | Oral | OS T3.1 – PS T3.1 | DAY 1 – January 12, 2021 — DAY 1 – January 12, 2021 |
1013 | Understanding When Spatial Transformer Networks Do Not Support Invariance, and What to Do about It | Finnveden, Lukas; Jansson, Ylva; Lindeberg, Tony | KTH Royal Institute of Technology | Poster | PS T1.2 | DAY 1 – January 12, 2021 |
1014 | A Prototype-Based Generalized Zero-Shot Learning Framework for Hand Gesture Recognition | Wu, Jinting; Zhang, Yujia; Zhao, Xiao-Guang | Institute of Automation, Chinese Academy of Sciences | Poster | PS T2.2 | DAY 2 – January 13, 2021 |
1016 | Detection of Makeup Presentation Attacks Based on Deep Face Representations | Rathgeb, Christian; Drozdowski, Pawel; Busch, Christoph | Hochschule Darmstadt | Poster | PS T2.1 | DAY 1 – January 12, 2021 |
1018 | On Learning Random Forests for Random Forest Clustering | Bicego, Manuele; Escolano, Francisco | University of Verona | Poster | PS T1.2 | DAY 1 – January 12, 2021 |
1019 | Expectation-Maximization for Scheduling Problems in Satellite Communication | Bailer, Werner; Winter, Martin; Ebert, Johannes; Flavio, Joel; Plimon, Karin | JOANNEUM RESEARCH | Poster | PS T1.2 | DAY 1 – January 12, 2021 |
1022 | GAN-Based Gaussian Mixture Model Responsibility Learning | Huang, Wanming; Xu, Yi Da; Jiang, Shuai; Liang, Xuan; Oppermann, Ian | University of Technology, Sydney (UTS) | Poster | PS T1.3 | DAY 2 – January 13, 2021 |
1023 | DSPNet: Deep Learning-Enabled Blind Reduction of Speckle Noise | Lu, Yuxu; Yang, Meifang; Wen, Liu | Wuhan University of Technology | Poster | PS T5.7 | DAY 4 – January 15, 2021 |
1024 | Constructing Geographic and Long-term Temporal Graph for Traffic Forecasting | Sun, Yiwen; Wang, Yulu; Fu, Kun; Wang, Zheng; Zhang, Changshui; Ye, Jieping | Tsinghua University | Poster | PS T1.3 | DAY 2 – January 13, 2021 |
1025 | Multi-Modal Contextual Graph Neural Network for Text Visual Question Answering | Liang, Yaoyuan; Wang, Xin; Duan, Xuguang; Zhu, Wenwu | Beijing University of Posts and Telecommunications | Poster | PS T4.3 | DAY 3 – January 14, 2021 |
1026 | Defense Mechanism against Adversarial Attacks Using Density-Based Representation of Images | Huang, Yen-Ting; Liao, Wen-Hung; Huang, Chen-Wei | National Chengchi University | Poster | PS T1.3 | DAY 2 – January 13, 2021 |
1027 | Multi-Laplacian GAN with Edge Enhancement for Face Super Resolution | Ko, Shanlei; Dai, Bi-Ru | National Taiwan University of Science and Technology | Poster | PS T5.7 | DAY 4 – January 15, 2021 |
1028 | 2D Deep Video Capsule Networkwith Temporal Shift for Action Recognition | Voillemin, Théo; Wannous, Hazem; Vandeborre, Jean-Philippe | University of Lille | Oral | OS T2.1 – PS T2.1 | DAY 1 – January 12, 2021 – DAY 1 – January 12, 2021 |
1030 | Interactive Style Space of Deep Features and Style Innovation | Guo, Bingqing; Hao, Pengwei | Queen Mary University of London | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
1031 | Vesselness Filters: A Survey with Benchmarks Applied to Liver Imaging | Lamy, Jonas; Merveille, Odyssée; Kerautret, Bertrand; Passat, Nicolas; Vacavant, Antoine | Université de Reims Champagne-Ardenne | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
1032 | Attention Based Multi-Instance Thyroid Cytopathological Diagnosis with Multi-Scale Feature Fusion | Qiu, Shuhao; Guo, Yao; Zhu, Chuang; ZHOU, WENLI; Chen, Huang | Beijing University of Posts and Telecommunications | Poster | PS T5.7 | DAY 4 – January 15, 2021 |
1033 | Question-Agnostic Attention for Visual Question Answering | Farazi, Moshiur R; Khan, Salman Hameed; Barnes, Nick | Australian National University (ANU) | Poster | PS T3.4 | DAY 2 – January 13, 2021 |
1036 | 3D Semantic Labeling of Photogrammetry Meshes Based on Active Learning | Rong, Mengqi; Shen, Shuhan; Hu, Zhanyi | Institute of Automation, Chinese Academy of Sciences | Poster | PS T3.7 | DAY 3 – January 14, 2021 |
1037 | Time Series Data Augmentation for Neural Networks by Time Warping with a Discriminative Teacher | Iwana, Brian Kenji; Uchida, Seiichi | Kyushu University | Poster | PS T1.3 | DAY 2 – January 13, 2021 |
1038 | Learning Emotional Blinded Face Representations | Peña Almansa, Alejandro; Fierrez, Julian; Lapedriza, Agata; Morales, Aythami | Universidad Autonoma de Madrid | Poster | PS T2.1 | DAY 1 – January 12, 2021 |
1039 | Let’s Play Music: Audio-Driven Performance Video Generation | Zhu, Hao; Li, Yi; Zhu, Feixia; ZHENG, AIHUA; He, Ran | Anhui University | Poster | PS T2.2 | DAY 2 – January 13, 2021 |
1040 | Incorporating Depth Information into Few-Shot Semantic Segmentation | Zhang, Yifei; SIDIBE, DESIRE; Morel, Olivier; Meriaudeau, Fabrice | Universite Bourgogne Franche Comte | Poster | PS T1.2 | DAY 1 – January 12, 2021 |
1041 | Cut and Compare: End-To-End Offline Signature Verification Network | Lu, Xi; Huang, Lin-Lin; Yin, Fei | Beijing Jiaotong University | Poster | PS T4.2 | DAY 2 – January 13, 2021 |
1043 | Improving Visual Relation Detection Using Depth Maps | Sharifzadeh, Sahand; Moayed Baharlou, Sina; Berrendorf, Max; Koner, Rajat; Tresp, Volker | LMU | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
1045 | MA-LSTM: A Multi-Attention Based LSTM for Complex Pattern Extraction | Guo, Jingjie; Tian, Kelang; Ye, Kejiang; Xu, Cheng-Zhong | Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences | Poster | PS T1.3 | DAY 2 – January 13, 2021 |
1048 | Inception Based Deep Learning Architecture for Tuberculosis Screening of Chest X-Rays | Das, Dipayan; Santosh, K.C.; Pal, Umapada | National Institute of Technology Durgapur, India | Poster | PS T5.7 | DAY 4 – January 15, 2021 |
1049 | Ordinal Depth Classification Using Region-based Self-attention | Phan, Vu Minh; Phung, Son Lam; Bouzerdoum, Abdesselam | University of Wollongong | Poster | PS T3.4 | DAY 2 – January 13, 2021 |
1051 | Movement-Induced Priors for Deep Stereo | Hou, Yuxin; Janjua, Muhammad Kamran; Kannala, Juho; Solin, Arno | Aalto University | Poster | PS T3.3 | DAY 1 – January 12, 2021 |
1053 | Classification of Intestinal Gland Cell-Graphs Using Graph Neural Networks | Studer, Linda; Wallau, Jannis; Dawson, Heather; Zlobec, Inti; Fischer, Andreas | University of Fribourg | Poster | PS T5.4 | DAY 2 – January 13, 2021 |
1054 | ID Documents Matching and Localization with Multi-Hypothesis Constraints | Chiron, Guillaume; Ghanmi, Nabil; Awal, Ahmad Montaser | AriadNext | Poster | PS T4.1 | DAY 1 – January 12, 2021 |
1055 | Attentive Part-Aware Networks for Partial Person Re-Identification | Huo, Lijuan; Song, Chunfeng; liu, zhengyi; Zhang, Zhaoxiang | Institute of Automation, Chinese Academy of Sciences (CASIA) | Poster | PS T2.2 | DAY 2 – January 13, 2021 |
1056 | Semantic Bilinear Pooling for Fine-Grained Recognition | Li, Xinjie; Yang, Chun; Chen, Song-Lu; Zhu, Chao; Yin, Xu-Cheng | University of Science and Technology Beijing | Poster | PS T3.7 | DAY 3 – January 14, 2021 |
1058 | Domain Siamese CNNs for Sparse Multispectral Disparity Estimation | Beaupre, David-Alexandre; Bilodeau, Guillaume-Alexandre | Polytechnique Montreal | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
1059 | GAN-Based Image Deblurring Using DCT Discriminator | Tomosada, Hiroki; Kudo, Takahiro; Fujisawa, Takanori; ikehara, masaaki | Keio University | Poster | PS T5.7 | DAY 4 – January 15, 2021 |
1060 | Talking Face Generation Via Learning Semantic and Temporal Synchronous Landmarks | ZHENG, AIHUA; Zhu, Feixia; Zhu, Hao; Luo, Mandi; He, Ran | Anhui University | Poster | PS T2.2 | DAY 2 – January 13, 2021 |
1061 | Single View Learning in Action Recognition | Goyal, Gaurvi; Noceti, Nicoletta; Odone, Francesca | University of genova | Poster | PS T1.2 | DAY 1 – January 12, 2021 |
1062 | Local Binary Quaternion Rotation Pattern for Colour Texture Retrieval | Jebali, Hela; Richard, Noel; Naouai, Mohamed | Faculty of Science of Tunis University campus el Manar, Tunisia | Poster | PS T3.3 | DAY 1 – January 12, 2021 |
1063 | First and Second-Order Sorted Local Binary Pattern Features for Grayscale-Inversion and Rotation Invariant Texture Classification | Song, Tiecheng; Han, Yuanjing; Feng, Jie; Wang, Yuanlin; Gao, Chenqiang | Chongqing University of Posts and Telecommunications | Poster | PS T5.7 | DAY 4 – January 15, 2021 |
1064 | A Transformer-Based Radical Analysis Network for Chinese Character Recognition | Yang, Chen; Wang, Qing; Du, Jun; Zhang, Jianshu; Wu, Changjie; Wang, Jiaming | University of Science and Technology of China | Poster | PS T4.2 | DAY 2 – January 13, 2021 |
1065 | InsideBias: Measuring Bias in Deep Networks and Application to Face Gender Biometrics | Serna, Ignacio; Peña Almansa, Alejandro; Morales, Aythami; Fierrez, Julian | Universidad Autonoma de Madrid | Poster | PS T2.1 | DAY 1 – January 12, 2021 |
1066 | VSR++: Improving Visual Semantic Reasoning for Fine-Grained Image-Text Matching | Yuan, Hui; Huang, Yan; ZHANG, DONGBO; Chen, Zerui; Cheng, Wenlong; Wang, Liang | Xiangtan University | Poster | PS T3.7 | DAY 3 – January 14, 2021 |
1067 | Low Dimensional State Representation Learning with Reward-Shaped Priors | Botteghi, Nicolò; Obbink, Ruben; Geijs, Daan; Poel, Mannes; Sirmacek, Beril; Brune, Christoph; Mersha, Abeje; Stramigioli, Stefano | University of Twente | Poster | PS T1.2 | DAY 1 – January 12, 2021 |
1069 | Towards Practical Compressed Video Action Recognition: A Temporal Enhanced Multi-Stream Network | Li, Bing; Kong, Longteng; Zhang, Dongming; Bao, Xiuguo; Huang, Di; Wang, Yunhong | Beihang University | Poster | PS T3.7 | DAY 3 – January 14, 2021 |
1072 | Feature-Supervised Action Modality Transfer | Thoker, Fida Mohammad; Snoek, Cees | University of Amsterdam | Poster | PS T3.3 | DAY 1 – January 12, 2021 |
1073 | Feature Point Matching in Cross-Spectral Images with Cycle Consistency Learning | Furuta, Ryosuke; Noguchi, Naoaki; Wang, Xueting; Yamasaki, Toshihiko | The University of Tokyo | Poster | PS T3.7 | DAY 3 – January 14, 2021 |
1075 | Group-Wise Feature Orthogonalization and Suppression for GAN Based Facial Attribute Translation | Wen, Zhiwei; Wu, Haoqian; Xie, Weicheng; Shen, Linlin | Shenzhen University | Poster | PS T1.3 | DAY 2 – January 13, 2021 |
1077 | A Weak Coupling of Semi-Supervised Learning with Generative Adversarial Networks for Malware Classification | Wang, ShuWei; Wang, Qiuyun; Jiang, Zhengwei; Wang, Xuren; Jing, RongQi | Institute of information engineering, Chinese academy of sciences | Poster | PS T5.7 | DAY 4 – January 15, 2021 |
1078 | Graph-Based Image Decoding for Multiplexed in Situ RNA Detection | Partel, Gabriele; Wahlby, Carolina | Uppsala University | Poster | PS T5.8 | DAY 4 – January 15, 2021 |
1079 | Tiny Object Detection in Aerial Images | Wang, Jinwang; Yang, Wen; Guo, Haowen; Zhang, Ruixiang; Xia, Gui-Song | Wuhan University | Oral | OS T3.5 – PS T3.4 | DAY 4 – January 15, 2021 – DAY 2 – January 13, 2021 |
1082 | Channel-Wise Dense Connection Graph Convolutional Network for Skeleton-Based Action Recognition | Lao BanTeng, Michael; Wu, Zhiyong | Tsinghua University | Poster | PS T2.2 | DAY 2 – January 13, 2021 |
1085 | Coarse-To-Fine Foreground Segmentation Based on Co-Occurrence Pixel-Block and Spatio-Temporal Attention Model | Liang, Dong; Liu, Xinyu | Nanjing University of Aeronautics and Astronautics | Poster | PS T3.7 | DAY 3 – January 14, 2021 |
1086 | Uncertainty-Sensitive Activity Recognition: A Reliability Benchmark and the CARING Models | Roitberg, Alina; Haurilet, Monica; Martinez, Manuel; Stiefelhagen, Rainer | Karlsruhe Institute of Technology (KIT) | Oral | OS T3.4 – PS T3.9 | DAY 3 – January 14, 2021 – DAY 3 – January 14, 2021 |
1087 | A New Geodesic-Based Feature for Characterization of 3D Shapes: Application to Soft Tissue Organ Temporal Deformations | Makki, Karim; Bohi, Amine; Ogier, Augustin C.; Bellemare, Marc-Emmanuel | Aix Marseille Univ | Poster | PS T5.8 | DAY 4 – January 15, 2021 |
1088 | Online Domain Adaptation for Person Re-Identification with a Human in the Loop | Delussu, Rita; Putzu, Lorenzo; Fumera, Giorgio; Roli, Fabio | University of Cagliari | Poster | PS T2.3 | DAY 2 – January 13, 2021 |
1089 | Hierarchical Deep Hashing for Fast Large Scale Image Retrieval | Zhang, Yongfei; Peng, Cheng; Jingtao, Zhang; Liu, Xianglong; Pu, Shiliang; Chen, Changhuai | Beihang University | Poster | PS T5.7 | DAY 4 – January 15, 2021 |
1090 | Learning to Segment Clustered Amoeboid Cells from Brightfield Microscopy Via Multi-Task Learning with Adaptive Weight Selection | Sarkar, Rituparna; Mukherjee, Suvadip; Labruyere, Elisabeth; Olivo-Marin, Jean-Christophe | Institut Pasteur | Poster | PS T5.8 | DAY 4 – January 15, 2021 |
1091 | Learning Metric Features for Writer-Independent Signature Verification Using Dual Triplet Loss | Wan, Qian; Zou, Qin | Wuhan University | Poster | PS T4.2 | DAY 2 – January 13, 2021 |
1092 | Recovery of 2D and 3D Layout Information through an Advanced Image Stitching Algorithm Using Scanning Electron Microscope Images | Singla, Aayush; Lippmann, Bernhard; Graeb, Helmut | Technical University of Munich | Poster | PS T5.8 | DAY 4 – January 15, 2021 |
1093 | Speeding-Up Pruning for Artificial Neural Networks: Introducing Accelerated Iterative Magnitude Pruning | Zullich, Marco; Medvet, Eric; Pellegrino, Felice Andrea; Ansuini, Alessio | University of Trieste | Poster | PS T1.2 | DAY 1 – January 12, 2021 |
1094 | Two-Stage Adaptive Object Scene Flow Using Hybrid CNN-CRF Model | Li, Congcong; Ma, Haoyu; Liao, Qingmin | Tsinghua University | Poster | PS T3.7 | DAY 3 – January 14, 2021 |
1101 | Localization and Transformation Reconstruction of Image Regions: An Extended Congruent Triangles Approach | Ahmad Alyosef, Afra’a; Elias, Christian; Nürnberger, Andreas | Otto-von-Guericke-University Magdeburg | Poster | PS T5.8 | DAY 4 – January 15, 2021 |
1104 | Subspace Clustering Via Joint Unsupervised Feature Selection | Dong, Wenhua; Wu, Xiaojun; Li, Hui; Feng, Zhen-Hua; Kittler, Josef | Jiangnan University | Poster | PS T1.3 | DAY 2 – January 13, 2021 |
1105 | A Multi-Task Neural Network for Action Recognition with 3D Key-Points | Tang, Rongxiao; Wang, Luyang; GUO, Zhenhua | Tsinghua University | Poster | PS T1.3 | DAY 2 – January 13, 2021 |
1107 | Signal Generation Using 1d Deep Convolutional Generative Adversarial Networks for Fault Diagnosis of Electrical Machines | Sabir, Russell; Rosato, Daniele; Hartmann, Sven; Gühmann, Clemens | SEG Automotive Germany GmbH and Chair of Electronic Measurement and Diagnostic Technology & Technische Universität Berlin | Poster | PS T1.2 | DAY 1 – January 12, 2021 |
1109 | Documents Counterfeit Detection through a Deep Learning Approach | Saire Pilco, Darwin Danilo; Tabbone, Salvatore | University of Campinas | Poster | PS T4.1 | DAY 1 – January 12, 2021 |
1110 | GarmentGAN: Photo-Realistic Adversarial Fashion Transfer | Raffiee, Amir Hossein; Sollami, Michael | Salesforce | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
1112 | Semantic Segmentation Refinement Using Entropy and Boundary-guided Monte Carlo Sampling and Directed Regional Search | Sun, Zitang; Kamata, Sei-ichiro; Wang, Ruojing; Chen, Weili | Waseda University,Graduate School of Information, Production and System | Poster | PS T5.7 | DAY 4 – January 15, 2021 |
1115 | Combining GANs and AutoEncoders for efficient anomaly detection | Carrara, Fabio; Amato, Giuseppe; Brombin, Luca; Falchi, Fabrizio; Gennaro, Claudio | ISTI CNR | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1116 | A Bayesian Approach to Reinforcement Learning of Vision-Based Vehicular Control | Gharaee, Zahra; Holmquist, Karl; He, Linbo; Felsberg, Michael | Linköping University | Poster | PS T1.16 | DAY 4 – January 15, 2021 |
1117 | Quantified Facial Temporal-Expressiveness Dynamics for Affect Analysis | Uddin, Md Taufeeq; Canavan, Shaun | University of South Florida | Poster | PS T2.1 | DAY 1 – January 12, 2021 |
1118 | A Simple Domain Shifting Network for Generating Low Quality Images | Hegde, Guruprasad; Ramesh, Avinash Nittur; Gandikota, Kanchana Vaishnavi; Möller, Michael; Obermaisser, Roman | University of Siegen | Poster | PS T3.3 | DAY 1 – January 12, 2021 |
1119 | A Multi-Head Self-Relation Network for Scene Text Recognition | Zhou, Junwei; Gao, Hongchao; Dai, Jiao; Liu, Dongqin; Han, Jizhong | Institute of information engineering, Chinese Academy of Sciences | Poster | PS T4.3 | DAY 3 – January 14, 2021 |
1121 | A Modified Single-Shot Multibox Detector for Beyond Real-Time Object Detection | Orfanidis, Georgios; Ioannidis, Konstantinos; Vrochidis, Stefanos; Tefas, Anastasios; Kompatsiaris, Ioannis | Information Technologies Institute (ITI) / Centre of Research and Technology Hellas (CERTH) | Poster | PS T3.3 | DAY 1 – January 12, 2021 |
1124 | Progressive Scene Segmentation Based on Self-Attention Mechanism | Pan, Yunyi; Gan, Yuan; Liu, Kun; Zhang, Yan | Nanjing University | Poster | PS T3.10 | DAY 4 – January 15, 2021 |
1125 | Walk the Lines: Object Contour Tracing CNN for Contour Completion of Ships | Kelm, André Peter; Zölzer, Udo | Helmut Schmidt University | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
1126 | Multi-Task Learning for Calorie Prediction on a Novel Large-Scale Recipe Dataset Enriched with Nutritional Information | Ruede, Robin; Heusser, Verena; Frank, Lukas; Roitberg, Alina; Haurilet, Monica; Stiefelhagen, Rainer | Karlsruhe Institute of Technology | Poster | PS T3.6 | DAY 2 – January 13, 2021 |
1127 | A Versatile Crack Inspection Portable System based on Classifier Ensemble and Controlled Illumination | Padalkar, Milind Gajanan; Beltran-Gonzalez, Carlos; Bustreo, Matteo; Del Bue, Alessio; Murino, Vittorio | Insituto Italiano di Tecnologia | Poster | PS T3.6 | DAY 2 – January 13, 2021 |
1129 | Uncertainty-Aware Data Augmentation for Food Recognition | Aguilar, Eduardo; Nagarajan, Bhalaji; Khatun, Rupali; Bolaños, Marc; Radeva, Petia | Universidad Católica del Norte | Poster | PS T3.5 | DAY 2 – January 13, 2021 |
1131 | Self and Channel Attention Network for Person Re-Identification | Munir, Asad; Martinel, Niki; Micheloni, Christian | University of Udine | Poster | PS T3.6 | DAY 2 – January 13, 2021 |
1132 | Feature-Dependent Cross-Connections in Multi-Path Neural Networks | Tissera, Dumindu; Vithanage, Hewa Walimunige Mihira Kasun; Wijesinghe, Rukshan; Kahatapitiya, Kumara; Fernando, Subha; Rodrigo, Ranga | University of Moratuwa | Poster | PS T3.5 | DAY 2 – January 13, 2021 |
1134 | Iterative Bounding Box Annotation for Object Detection | Adhikari, Bishwo; Huttunen, Heikki Juhani | Tampere University | Poster | PS T3.6 | DAY 2 – January 13, 2021 |
1136 | Investigating and Exploiting Image Resolution for Transfer Learning-Based Skin Lesion Classification | Mahbod, Amirreza; Schaefer, Gerald; Wang, Chunliang; Ecker, Rupert; Dorffner, Georg; Ellinger, Isabella | Medical University of Vienna | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1137 | Attention Based Pruning for Shift Networks | Hacene, Ghouthi; Lassance, Carlos; Gripon, Vincent; Courbariaux, Matthieu; Bengio, Yoshua | MILA | Poster | PS T3.5 | DAY 2 – January 13, 2021 |
1140 | An Integrated Approach of Deep Learning and Symbolic Analysis for Digital PDF Table Extraction | Zhang, Mengshi; Perelman, Daniel; Le, Vu; Gulwani, Sumit | Microsoft | Poster | PS T4.1 | DAY 1 – January 12, 2021 |
1143 | Relatable Clothing: Detecting Visual Relationships between People and Clothing | Truong, Thomas; Yanushkevich, Svetlana | University of Calgary | Poster | PS T2.1 | DAY 1 – January 12, 2021 |
1144 | Unsupervised Learning of Landmarks Based on Inter-Intra Subject Consistencies | Li, Weijian; Liao, Haofu; Miao, Shun; Lu, Le; Luo, Jiebo | University of Rochester | Oral | OS T2.2 – PS T2.5 | DAY 3 – January 14, 2021 – DAY 4 – January 15, 2021 |
1148 | Sparse Network Inversion for Key Instance Detection in Multiple Instance Learning | Shin, Beomjo; Cho, Junsu; Yu, Hwanjo; Choi, Seungjin | Pohang University of Science and Technology | Poster | PS T1.3 | DAY 2 – January 13, 2021 |
1149 | Inferring Functional Properties from Fluid Dynamics Features | Schillaci, Andrea; Quadrio, Maurizio; Pipolo, Carlotta; Restelli, Marcello; Boracchi, Giacomo | Politecnico di Milano | Poster | PS T1.2 | DAY 1 – January 12, 2021 |
1150 | A Generalizable Saliency Map-Based Interpretation of Model Outcome | Thakur, Shailja; Fischmeister, Sebastian | University of Waterloo | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1152 | EEG-Based Cognitive State Assessment Using Deep Ensemble Model and Filter Bank Common Spatial Pattern | Das Chakladar, Debashis; Dey, Shubhashis; Roy, Partha Pratim; Iwamura, Masakazu | Indian Institute of Technology Roorkee | Poster | PS T2.3 | DAY 2 – January 13, 2021 |
1153 | Dynamically Mitigating Data Discrepancy with Balanced Focal Loss for Replay Attack Detection | Dou, Yongqiang; Yang, Haocheng; Yang, Maolin; Xu, Yanyan; Ke, Dengfeng | Chinese Academy of Sciences | Poster | PS T2.4 | DAY 3 – January 14, 2021 |
1155 | Robust Visual Object Tracking with Two-Stream Residual Convolutional Networks | Zhang, Ning; Liu, Jingen; Wang, Ke; Zeng, Dan; Mei, Tao | JD AI Research | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
1156 | Feature Representation Learning for Calving Detection of Cows Using Video Frames | Hyodo, Ryosuke; Nakano, Teppei; Ogawa, Tetsuji | Waseda University | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1160 | Dynamic Multi-Path Neural Network | Su, Yingcheng; Wu, Yichao; Chen, Ken; Liang, Ding; Hu, Xiaolin | Sensetime Group Limited | Oral | OS T1.5 – PS T1.10 | DAY 3 – January 14, 2021 – DAY 3 – January 14, 2021 |
1161 | Learning Neural Textual Representations for Citation Recommendation | Kieu, Thanh Binh; Jauregi Unanue, Inigo; Pham, Son Bao; Phan, Xuan-Hieu; Piccardi, M. | University of Technology Sydney | Poster | PS T4.2 | DAY 2 – January 13, 2021 |
1162 | RSINet: Rotation-Scale Invariant Network for Online Visual Tracking | Fang, Yang; Jo, Geun-Sik; Lee, Chang-Hee | Inha University | Poster | PS T3.10 | DAY 4 – January 15, 2021 |
1163 | Meta Learning Via Learned Loss | Bechtle, Sarah; Molchanov, Artem; Chebotar, Yevgen; Grefenstette, Edward Thomas; Righetti, Ludovic; Sukhatme, Gaurav; Meier, Franziska | Max-Planck-Institute for Intelligent Systems Tuebingen | Oral | OS T1.1 – PS T1.1 | DAY 1 – January 12, 2021 – DAY 1 – January 12, 2021 |
1165 | Angus Cattle Recognition Using Deep Learning | Chen, Shunnan; Wang, Sen; Zuo, Xinxin; Yang, Ruigang | University of Kentucky | Poster | PS T2.1 | DAY 1 – January 12, 2021 |
1167 | Self-Supervised Learning for Astronomical Image Classification | Martinazzo, Ana; Espadoto, Mateus; Hirata, Nina S. T. | University of São Paulo | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1171 | RWF-2000: An Open Large Scale Video Database for Violence Detection | Cheng, Ming; Cai, Kunjing; Li, Ming | Duke Kunshan University | Poster | PS T2.4 | DAY 3 – January 14, 2021 |
1173 | Radical Counter Network for Robust Chinese Character Recognition | Li, Yunqing; Zhu, Yixing; Du, Jun; Wu, Changjie; Zhang, Jianshu | University of Science and Technology of China | Poster | PS T4.2 | DAY 2 – January 13, 2021 |
1176 | Graph Convolutional Neural Networks for Power Line Outage Identification | He, Jia; Cheng, Maggie | Illinois Institute of Technology | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1177 | Exemplar Guided Cross-Spectral Face Hallucination Via Mutual Information Disentanglement | Wu, Haoxue; Huang, Huaibo; Yu, Aijing; Cao, Jie; Lei, Zhen; He, Ran | Institute of Automation, Chinese Academy of Sciences | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1179 | Efficient Game-Theoretic Hypergraph Matching | Hou, Jian; Qi, Nai-Ming | Dongguan University of Technology | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1180 | Face Anti-spoofing Based on Dynamic Color Texture Analysis Using Local Directional Number Pattern | Zhou, Junwei; Shu, Ke; Liu, Peng; Xiang, Jianwen; Xiong, ShengWu | School of Computer Science and Technology, Wuhan University of Technology | Poster | PS T2.4 | DAY 3 – January 14, 2021 |
1183 | Dual-Attention Guided Dropblock Module for Weakly Supervised Object Localization | Yin, Junhui; Zhang, Siqing; Chang, Dongliang; Ma, Zhanyu; Guo, Jun | Beijing University of Posts and Telecommunications | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1185 | Gabriella: An Online System for Real-Time Activity Detection in Untrimmed Security Videos | Rizve, Mamshad Nayeem; Demir, Ugur; Tirupattur, Praveen; Rana, Aayush Jung; Duarte, Kevin; Dave, Ishan Rajendrakumar; Rawat, Yogesh; Shah, Mubarak | University of Central Florida | Oral | OS T3.1 – PS T3.6 | DAY 1 – January 12, 2021 – DAY 2 – January 13, 2021 |
1187 | Privacy Attributes-Aware Message Passing Neural Network for Visual Privacy Attributes Classification | Hong, Hanbin; Bao, Wentao; Hong, Yuan; Kong, Yu | Rochester Institute of Technology | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1188 | Text Synopsis Generation for Egocentric Videos | Sharghi, Aidean; Da Vitoria Lobo, Niels; Shah, Mubarak | University of Central Florida | Oral | OS T3.1 – PS T3.6 | DAY 1 – January 12, 2021 – DAY 2 – January 13, 2021 |
1190 | Decision Snippet Features | Welke, Pascal; Alkhoury, Fouad; Bauckhage, Christian; Wrobel, Stefan | University of Bonn | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1191 | Semi-Supervised Outdoor Image Generation Conditioned on Weather Signals | Kawakami, Sota; Okada, Kei; Nitta, Naoko; Nakamura, Kazuaki; Babaguchi, Noboru | Osaka University | Poster | PS T5.7 | DAY 4 – January 15, 2021 |
1199 | Recurrent Deep Attention Network for Person Re-Identification | Wang, Changhao; Zhou, Jun; Duan, Xianfei; Zhang, Guanwen; Zhou, Wei | Northwestern Polytechnical University | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1201 | Continuous Learning of Face Attribute Synthesis | Xin, Ning; Xu, Shaohui; Nan, fangzhe; Dong, Xiaoli; Li, Weijun; Yao, Yuanzhou | Cognitive Computing Technology Joint Laboratory, Wave Group | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
1202 | Exploring Graph-based Feature for Scientific Document Summarization using Evolutionary Framework | Saini, Naveen; Kumar, Sushil; Saha, Sriparna; Bhattacharyya, Pushpak | Indian Institute of Technology Patna | Poster | PS T4.2 | DAY 2 – January 13, 2021 |
1204 | Applying (3+2+1)D Residual Neural Network with Frame Selection for Hong Kong Sign Language Recognition | Zhou, Zhenxing; Lui, King-Shan; Tam, Vincent W.L.; Lam, Edmund Y. | The University of Hong Kong | Poster | PS T2.4 | DAY 3 – January 14, 2021 |
1205 | Flow-guided Spatial Attention Tracking for Egocentric Activity Recognition | Liu, Tianshan; Lam, Kin-Man | The Hong Kong Polytechnic University | Poster | PS T2.4 | DAY 3 – January 14, 2021 |
1207 | A Cross Domain Multi-Modal Dataset for Robust Face Anti-Spoofing | Ji, Qiaobin; Xu, Shugong; Chen, Xudong; Cao, Shan; Zhang, Shunqing | Shanghai Institute for Advanced Communication and Data Science, Shanghai University | Poster | PS T2.4 | DAY 3 – January 14, 2021 |
1209 | Multi-focus Image Fusion for Confocal Microscopy Using U-Net Regression Map | Shuvo, Md Maruf Hossain; Kassim, Yasmin M.; Bunyak, Filiz; Glinskii, Olga V.; Xie, Leike; Glinsky, Vladislav V; Huxley, Virginia H.; Thakkar, Mahesh M.; Palaniappan, Kannappan | University of Missouri-Columbia | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
1210 | Dual Path Multi-Modal High-Order Features for Textual Content Based Visual Question Answering | Li, Yanan; Lin, Yuetan; Zhao, Hongrui; Wang, Donghui | Zhejiang Lab | Oral | OS T3.6 – PS T3.8 | DAY 4 – January 15, 2021 – DAY 3 – January 14, 2021 |
1211 | Neural Machine Registration for Motion Correction in Breast DCE-MRI | Aprea, Federica; Marrone, Stefano; Sansone, Carlo | University of Naples Federico II | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
1213 | IPN Hand: A Video Dataset and Benchmark for Real-Time Continuous Hand Gesture Recognition | Benitez-Garcia, Gibran; Olivares-Mercado, Jesus; Sanchez-Perez, Gabriel; Yanai, Keiji | The University of Electro-Communications | Poster | PS T2.4 | DAY 3 – January 14, 2021 |
1216 | Nonlinear Ranking Loss on Riemannian Potato Embedding | Kim, Byung Hyung; Suh, Yoon-Je; Lee, Honggu; Jo, Sungho | KAIST | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1217 | Crowdsourced Verification for Operating Calving Surveillance Systems at an Early Stage | Okimoto, Yusuke; Kawata, Soshi; Saito, Susumu; Nakano, Teppei; Ogawa, Tetsuji | Waseda University | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1219 | PICK: Processing Key Information Extraction from Documents Using Improved Graph Learning-Convolutional Networks | Yu, Wenwen; Lu, Ning; Qi, Xianbiao; Gong, Ping; Xiao, Rong | Xuzhou Medical University | Poster | PS T4.2 | DAY 2 – January 13, 2021 |
1220 | TSMSAN: A Three-Stream Multi-Scale Attentive Network for Video Saliency Detection | Yang, Jingwen; Zhang, Guanwen; Yan, Jiaming; Zhou, Wei | Northwestern Polytechnical University | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1222 | Towards Low-Bit Quantization of Deep Neural Networks with Limited Data | Yuan, Yong; Chen, Chen; Hu, Xiyuan; Peng, Silong | Chinese Academy of Sciences | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1226 | Generic Merging of Structure from Motion Maps with a Low Memory Footprint | Flood, Gabrielle; Gillsjö, David; Persson, Patrik; Heyden, Anders; Åström, Kalle | Lund University | Poster | PS T3.6 | DAY 2 – January 13, 2021 |
1227 | Investigation of DNN Model Robustness Using Heterogeneous Datasets | Liao, Wen-Hung; Huang, Yen-Ting | National Chengchi University | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1228 | Extended Depth of Field Preserving Color Fidelity for Automated Digital Cytology | Bouyssoux, Alexandre; Fezzani, Riadh; Olivo-Marin, Jean-Christophe | BioImage Analysis Lab, CNRS UMR 3691, Institut Pasteur, France | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
1230 | RescueNet: Joint Building Segmentation and Damage Assessment from Satellite Imagery | Gupta, Rohit; Shah, Mubarak | University of Central Florida | Poster | PS T3.5 | DAY 2 – January 13, 2021 |
1231 | Deep Multi-Task Learning for Facial Expression Recognition and Synthesis Based on Selective Feature Sharing | Zhao, Rui; Liu, Tianshan; Xiao, Jun; Lun, P. K. Daniel; Lam, Kin-Man | The Hong Kong Polytechnic University | Poster | PS T2.4 | DAY 3 – January 14, 2021 |
1233 | Image Inpainting with Contrastive Relation Network | Zhou, Xiaoqiang; LI, Junjie; Wang, Zilei; He, Ran; Tan, Tieniu | University of Science and Technoloy of China | Oral | OS T5.1 – PS T5.5 | DAY 1 – January 12, 2021 – DAY 3 – January 14, 2021 |
1235 | CANU-ReID: A Conditional Adversarial Network for Unsupervised Person Re-IDentification | Delorme, Guillaume; Xu, Yihong; Lathuiliere, Stéphane; Horaud, Radu; Alameda-Pineda, Xavier | Inria | Oral | OS T2.1 – PS T2.1 | DAY 1 – January 12, 2021 — DAY 1 – January 12, 2021 |
1238 | Deep Reinforcement Learning for Autonomous Driving by Transferring Visual Features | Zhou, Hongli; Chen, Xiaolei; Zhang, Guanwen; Zhou, Wei | Northwestern Polytechnical University | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1239 | Prediction of Obstructive Coronary Artery Disease from Myocardial Perfusion Scintigraphy using Deep Neural Networks | Arvidsson, Ida; Overgaard, Niels Christian; Ochoa Figueroa, Miguel; Rose, Jeronimo; Davidsson, Anette; Åström, Kalle; Heyden, Anders | Lund University | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1240 | Exploring Seismocardiogram Biometrics with Wavelet Transform | Hsu, Po-Ya; Hsu, Po-Han; Liu, Hsin-Li | UC San Diego | Poster | PS T2.1 | DAY 1 – January 12, 2021 |
1241 | Toward Building a Data-Driven System ForDetecting Mounting Actions of Black Beef Cattle | Kawano, Yuriko; Saito, Susumu; Nakano, Teppei; Kondo, Ikumi; Yamazaki, Ryota; Kusaka, Hiromi; Sakaguchi, Minoru; Ogawa, Tetsuji | Waseda University | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1244 | Biomimetic Active Vision in a Simulated Human | Nakada, Masaki; Chen, Honglin; Lakshmipathy, Arjun; Terzopoulos, Demetri | University of California, Los Angeles | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
1245 | Median-Shape Representation Learning for Category-Level Object Pose Estimation in Cluttered Environments | Tatemichi, Hiroki; Kawanishi, Yasutomo; Deguchi, Daisuke; Ide, Ichiro; Murase, Hiroshi; Amma, Ayako | Nagoya University | Poster | PS T3.10 | DAY 4 – January 15, 2021 |
1246 | Temporal Pattern Detection in Time-Varying Graphical Models | Tomasi, Federico; Tozzo, Veronica; Barla, Annalisa | Spotify | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1247 | Text Recognition – Real World Data and Where to Find Them | Janouková, Klára; Gomez, Lluis; Karatzas, Dimosthenis; Matas, Jiri | Centre for Machine Perception, Department of Cybernetics, Czech Technical University in Prague | Poster | PS T4.3 | DAY 3 – January 14, 2021 |
1248 | Multi-Camera Sports Players 3D Localization with Identification Reasoning | Yang, Yukun; Zhang, Ruiheng; Wu, Wanneng; Peng, Yu; Xu, Min | University of Technology, Sydney | Poster | PS T3.4 | DAY 2 – January 13, 2021 |
1250 | ScarfNet: Multi-Scale Features with Deeply Fused and Redistributed Semantics for Enhanced Object Detection | Yoo, Jin Hyeok; Kum, Dongsuk; Choi, Jun Won | Hanyang University | Poster | PS T3.10 | DAY 4 – January 15, 2021 |
1251 | Facial Expression Recognition Using Residual Masking Network | Pham, Luan; huynh, vu; Tran, TuanAnh | Ho Chi Minh University of Technology, HoChiMinh National University | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
1252 | Unsupervised Contrastive Photo-To-Caricature Translation Based on Auto-Distortion | Ding, Yuhe; Ma, Xin; Luo, Mandi; Zheng Aihua; He, Ran | Anhui University | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
1253 | Sequential Non-Rigid Factorisation for Head Pose Estimation | Cristina, Stefania; Camilleri, Kenneth Patrick | University of Malta | Poster | PS T3.6 | DAY 2 – January 13, 2021 |
1254 | Distilling Spikes: Knowledge Distillation in Spiking Neural Networks | Kushawaha, Ravi Kumar; Kumar, Saurabh; Banerjee, Biplab; Velmurugan, Rajbabu | Indian Institute of Technology Bombay | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1255 | A Deep Learning Approach for the Segmentation of Myocardial Diseases | Brahim, Khawla; Qayyum, Abdul; Lalande, Alain; Boucher, Arnaud; Sakly, Anis; Meriaudeau, Fabrice | *Universite de Sousse, Ecole Nationale d’’Ingénieurs de Sousse ; **Universite Bourgogne Franche Comte ; ***Universite de Monastir, Ecole Nationale d’’Ingénieurs de Monastir, LASEE-Laboratory | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
1256 | Future Urban Scenes Generation through Vehicles Synthesis | Simoni, Alessandro; Bergamini, Luca; Palazzi, Andrea; Calderara, Simone; Cucchiara, Rita | University of Modena and Reggio Emilia | Poster | PS T3.11 | DAY 4 – January 15, 2021 |
1259 | Explainable Feature Embedding Using Convolutional Neural Networks for Pathological Image Analysis | Uehara, Kazuki; Murakawa, Masahiro; Nosato, Hirokazu; Sakanashi, Hidenori | National Institute of Advanced Industrial Science and Technology | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1263 | ConvMath : A Convolutional Sequence Network for Mathematical Expression Recognition | Yan, Zuoyu; Zhang, Xiaode; Gao, Liangcai; yuan, ke; Tang, Zhi | Peking University | Poster | PS T4.2 | DAY 2 – January 13, 2021 |
1264 | SL-DML: Signal Level Deep Metric Learning for Multimodal One-Shot Action Recognition | Memmesheimer, Raphael; Theisen, Nick; Paulus, Dietrich | University of Koblenz-Landau | Oral | OS T3.4 – PS T3.10 | DAY 3 – January 14, 2021 – DAY 4 – January 15, 2021 |
1267 | Few Shot Learning Framework to Reduce Inter-Observer Variability in Medical Images | Roychowdhury, Sohini | Volvo cars US Tech Office | Poster | PS T5.1 | DAY 1 – January 12, 2021 |
1268 | Trajectory-User Link with Attention Recurrent Networks | Sun, Tao; Xu, Yongjun; Wang, Fei; Wu, Lin; Qian, Tangwen; Shao, Zezhi | Institute of Computing Technology Chinese Academy of Science; University of Chinese Academy of Sciences | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1274 | VOWEL: A Local Online Learning Rule for Recurrent Networks of Probabilistic Spiking Winner-Take-All Circuits | Jang, Hyeryung; Skatchkovsky, Nicolas; Simeone, Osvaldo | King’s College London | Oral | OS T1.1 – PS T1.1 | DAY 1 – January 12, 2021 – DAY 1 – January 12, 2021 |
1275 | Siamese-Structure Deep Neural Network Recognizing Changes in Facial Expression According to the Degree of Smiling | Kondo, Kazuaki; Nakamura, Taichi; Nakamura, Yuichi; Satoh, Shin’ichi | Kyoto Univ. | Poster | PS T2.4 | DAY 3 – January 14, 2021 |
1276 | Robust Localization of Retinal Lesions Via Weakly-Supervised Learning | Zhao, Ruohan; Li, Qin; You, Jane | Shenzhen Institute of Information Technology | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1277 | Feature Fusion for Online Mutual Knowledge Distillation | Kim, Jangho; Hyun, Minsung; Chung, Inseop; Kwak, Nojun | Seoul National University | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1279 | Open Set Domain Recognition Via Attention-Based GCN and Semantic Matching Optimization | He, Xinxing; Yuan, Yuan; Jiang, Zhiyu | Northwestern Polytechnical University | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1280 | Enhancing Deep Semantic Segmentation of RGB-D data with Entangled Forest | Terreran, Matteo; Bonetto, Elia; Ghidoni, Stefano | University of Padova | Poster | PS T3.3 | DAY 1 – January 12, 2021 |
1281 | Detecting Anomalies from Video-Sequences: A Novel Descriptor | Orrù, Giulia; Ghiani, Davide; Pintor, Maura; Marcialis, Gian Luca; Roli, Fabio | Università degli studi di Cagliari | Poster | PS T2.4 | DAY 3 – January 14, 2021 |
1285 | Global Context-Based Network with Transformer for Image2latex | Pang, Nuo; Yang, Chun; Zhu, Xiaobin; Li, Jixuan; Yin, Xu-Cheng | University of Science and Technology Beijing | Poster | PS T4.2 | DAY 2 – January 13, 2021 |
1286 | Yolo+FPN: 2D and 3D Fused Object Detection with an RGB-D Camera | Wang, Ya; Zell, Andreas | University of Tuebingen | Poster | PS T3.3 | DAY 1 – January 12, 2021 |
1287 | Signature Features with the Visibility Transformation | Wu, Yue; Ni, Hao; Lyons, Terry; Hudson, Robin | University of Oxford | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1288 | Text Baseline Recognition Using a Recurrent Convolutional Neural Network | Wödlinger, Matthias; Sablatnig, Robert | Technical University of Vienna | Poster | PS T4.1 | DAY 1 – January 12, 2021 |
1290 | Anticipating Activity from Multimodal Signals | Rotondo, Tiziana; Farinella, Giovanni Maria; Giacalone, Davide; Strano, Sebastiano Mauro; Tomaselli, Valeria; Battiato, Sebastiano | University of Catania | Poster | PS T3.3 | DAY 1 – January 12, 2021 |
1292 | Space-Time Domain Tensor Neural Networks: An Application on Human Pose Classification | Makantasis, Konstantinos; Voulodimos, Athanasios; Doulamis, Anastasios; Doulamis, Nikolaos; Bakalos, Nikolaos | Technical University of Crete | Poster | PS T2.4 | DAY 3 – January 14, 2021 |
1293 | Killing Four Birds with One Gaussian Process: The Relation between Different Test-Time Attacks | Grosse, Kathrin; Smith, Michael Thomas; Backes, Michael | Cispa-Helmholtz Center, Saarland Informatics Campus | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1294 | E-DNAS: Differentiable Neural Architecture Search for Embedded Systems | García López, Javier; Agudo, Antonio; Moreno-Noguer, Francesc | Universitat Politècnica de Catalunya | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1295 | Derivation of Geometrically and Semantically Annotated UAV Datasets at Large Scales from 3D City Models | Wu, Sidi; Liebel, Lukas; Körner, Marco | Chair of Remote Sensing Technology,Technical University of Munich | Poster | PS T3.3 | DAY 1 – January 12, 2021 |
1296 | A Multi-Task Multi-View Based Multi-Objective Clustering Algorithm | mitra, Sayantan; Saha, Sriparna | Indian Institute of Technology Patna | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1298 | Multi-Modal Deep Clustering: Unsupervised Partitioning of Images | Shiran, Guy; Weinshall, Daphna | Hebrew University of Jerusalem | Poster | PS T1.6 | DAY 2 – January 13, 2021 |
1300 | Temporal Collaborative Filtering with Graph Convolutional Neural Networks | Rodrigo-Bonet, Esther; Nguyen, Minh Duc; Deligiannis, Nikos | Vrije Universiteit Brussel (VUB) | Poster | PS T1.7 | DAY 2 – January 13, 2021 |
1301 | Multi-Scanning Based Recurrent Neural Network for Hyperspectral Image Classification | Zhou, Weilian; Kamata, Sei-ichiro | Waseda University | Poster | PS T1.4 | DAY 2 – January 13, 2021 |
1302 | Prior Knowledge about Attributes: Learning a More Effective Potential Space for Zero-Shot Recognition | Chai, Chunlai; Lou, Yukuan; Zhang, Shijin; Hua, Ming | Zhejiang Gongshang University | Poster | PS T1.4 | DAY 2 – January 13, 2021 |
1304 | Better Prior Knowledge Improves Human-Pose-Based Extrinsic Camera Calibration | Moliner, Olivier; Huang, Sangxia; Åström, Kalle | Lund University | Poster | PS T3.5 | DAY 2 – January 13, 2021 |
1305 | Modeling Extent-Of-Texture Information for Ground Terrain Recognition | Ghose, Shuvozit; Chowdhury, Pinaki Nath; Roy, Partha Pratim; Pal, Umapada | IIT | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
1306 | Merged 1D-2D Deep Convolutional Neural Networks for Nerve Detection in Ultrasound Images | Alkhatib, Mohammad; Hafiane, Adel; Vieyres, Pierre | Université d’Orléans | Poster | PS T3.5 | DAY 2 – January 13, 2021 |
1307 | Precise Temporal Action Localization with Quantified Temporal Structure of Actions | Lu, Chongkai; Li, Ruimin; Fu, Hong; Fu, Bin; Wang, Yihao; Lo, Wai Lun; Chi, Zheru | The Education University of Hong Kong | Poster | PS T3.10 | DAY 4 – January 15, 2021 |
1310 | Fine-Tuning DARTS for Image Classification | Tanveer, Muhammad Suhaib; Karim Khan, Umar; Min Kyung, Chong | KAIST | Poster | PS T1.4 | DAY 2 – January 13, 2021 |
1314 | Pseudo Rehearsal Using Non Photo-Realistic Images | Suri, Bhasker Sri Harsha; Yeturu, Kalidas | Indian Institute of Technology Tirupati | Poster | PS T1.4 | DAY 2 – January 13, 2021 |
1317 | Hyperspectral Imaging for Analysis and Classification of Plastic Waste | Krasniewski Jakub, Dabala Lukasz, Lewandowski Marcin | AVICON and Warsaw University of Technology | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
1319 | LODENet: A Holistic Approach to Offline Handwritten Chinese and Japanese Text Line Recognition | Hoang, Huu Tin; Peng, Chun-Jen; Tran, Hung; Le, Hung; Nguyen, Huy Hoang | Cinnamon AI | Poster | PS T4.1 | DAY 1 – January 12, 2021 |
1321 | Semi-Supervised Generative Adversarial Networks with a Pair of Complementary Generators for Retinopathy Screening | Xie, Yingpeng; Wan, Qiwei; Xie, Hai; Tan, En-Leng; Xu, Yanwu; Lei, Baiying | Shenzhen University | Poster | PS T1.4 | DAY 2 – January 13, 2021 |
1325 | Neural Architecture Search for Image Super-Resolution Using Densely Connected Search Space: DeCoNAS | Ahn, Joon Young; Cho, Nam Ik | seoul national university | Poster | PS T5.7 | DAY 4 – January 15, 2021 |
1327 | ResMax: Detecting Voice Spoofing Attacks with Residual Network and Max Feature Map | Kwak, Il-Youp; Kwag, Sungsu; Lee, Junhee; Huh, Jun Ho; Lee, Choong-Hoon; Jeon, Youngbae; Hwang, Jeonghwan; Yoon, Ji Won | Chung-Ang University | Poster | PS T2.4 | DAY 3 – January 14, 2021 |
1328 | Fast Discrete Cross-Modal Hashing Based on Label Relaxation and Matrix Factorization | Zhang, Donglin; Wu, Xiaojun; Liu, Zhen; Yu, Jun; Kittler, Josef | Jiangnan University | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
1331 | Learning Visual Voice Activity Detection with an Automatically Annotated Dataset | Guy, Sylvain; lathuiliere, Stéphane; Mesejo, Pablo; Horaud, Radu | Télécom Paris | Oral | OS T2.1 – PS T2.1 | DAY 1 – January 12, 2021 – DAY 1 – January 12, 2021 |
1334 | Benchmarking Cameras for OpenVSLAM Indoors | Chappellet, Kevin; Caron, Guillaume; Kanehiro, Fumio; Sakurada, Ken; Kheddar, Abderrahmane | CNRS-AIST JRL | Poster | PS T3.10 | DAY 4 – January 15, 2021 |
1337 | Can Reinforcement Learning Lead to Healthy Life?: Simulation Study Based on User Activity Logs | Takahashi, Masami; Kohjima, Masahiro; Kurashima, Takeshi; Toda, Hiroyuki | NTT Corporation | Poster | PS T1.4 | DAY 2 – January 13, 2021 |
1342 | A Local Descriptor with Physiological Characteristic for Finger Vein Recognition | Zhang, Liping; Li, weijun; Xin, Ning; Sun, Linjun; Dong, Xiaoli | Institute of Semiconductors, CAS, | Poster | PS T1.4 | DAY 2 – January 13, 2021 |
1343 | Sequential Domain Adaptation through Elastic Weight Consolidation for Sentiment Analysis | Madasu, Avinash; Rao, Anvesh | Samsung R&D Institute India, Bangalore | Poster | PS T1.4 | DAY 2 – January 13, 2021 |
1348 | Kernel-based Graph Convolutional Networks | Sahbi, Hichem | UPMC Sorbonne University | Poster | PS T1.7 | DAY 2 – January 13, 2021 |
1351 | Learning with Delayed Feedback | Theivendiram, Pranavan; Sim, Terence | National University of Singapore | Poster | PS T3.10 | DAY 4 – January 15, 2021 |
1353 | Detecting Rare Cell Populations in Flow Cytometry Data using UMAP | Weijler, Lisa; Diem, Markus; Reiter, Michael | TU Wien | Poster | PS T1.7 | DAY 2 – January 13, 2021 |
1354 | Progressive Adversarial Semantic Segmentation | Imran, Abdullah-Al-Zubaer; Terzopoulos, Demetri | University of California, Los Angeles | Poster | PS T5.1 | DAY 1 – January 12, 2021 |
1358 | A Novel Actor Dual-Critic Model for Remote Sensing Image Captioning | Chavhan, Ruchika; Banerjee, Biplab; Zhu, Xiao Xiang; Chaudhuri, Subhasis | Indian Institute of Technology, Bombay | Poster | PS T3.5 | DAY 2 – January 13, 2021 |
1359 | Exploiting Local Indexing and Deep Feature Confidence Scores for Fast Image-To-Video Search | Ozkan, Savas; Akar, Gözde Bozda; | Middle East Technical University | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
1361 | ESResNet: Environmental Sound Classification Based on Visual Domain Models | Guzhov, Andrey; Raue, Federico; Hees, Jörn; Dengel, Andreas | DFKI | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
1362 | SAGE: Sequential Attribute Generator for Analyzing Glioblastomas using Limited Dataset | Jonnalagedda, Padmaja; Weinberg, Brent; Allen, Jason; Min, Taejin; Bhanu, Shiv; Bhanu, Bir | University of California Riverside | Poster | PS T1.12 | DAY 3 – January 14, 2021 |
1363 | Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution | Goh, Gary Shing Wee; Lapuschkin, Sebastian; Weber, Leander; Samek, Wojciech; Binder, Alexander | Singapore University of Technology and Design | Oral | OS T1.1 – PS T1.3 | DAY 1 – January 12, 2021 – DAY 2 – January 13, ,2021 |
1365 | Unsupervised Domain Adaptation for Person Re-Identification through Source-guided Pseudo-labeling | Dubourvieux, Fabian; Audigier, Romaric; Loesch, Angélique; Samia, Ainouz-Zemouche; Canu, Stéphane | CEA, LIST, Laboratoire Vision et Apprentissage pour lAnalyse de Scene, Gif-sur-Yvette, France | Poster | PS T2.4 | DAY 3 – January 14, 2021 |
1369 | Superpixel-based Refinement for Object Proposal Generation | Wilms, Christian; Frintrop, Simone | University of Hamburg | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
1371 | Attention Stereo Matching Network | Zhang, Doudou; Cai, Jing; xue, yanbing; Gao, Zan; Zhang, Hua | TJUT | Poster | PS T1.4 | DAY 2 – January 13, 2021 |
1372 | Hierarchical Head Design for Object Detectors | Agarwal, Shivang; Jurie, Frederic | CNRS | Poster | PS T3.5 | DAY 2 – January 13, 2021 |
1373 | Exploiting Knowledge Embedded Soft Labels For Image Recognition | Yuan, Lixian; Chen, Riquan; Wu, Hefeng; Chen, Tianshui; Wang, Wentao; Chen, Pei | Sun Yat-sen University | Poster | PS T1.4 | DAY 2 – January 13, 2021 |
1376 | Which Airline is This? Airline Logo Detection in Real-World Weather Conditions | Wilms, Christian; Heid, Rafael; Sadeghi, Mohammad Araf; Ribbrock, Andreas; Frintrop, Simone | University of Hamburg | Poster | PS T3.5 | DAY 2 – January 13, 2021 |
1384 | Can You Trust Your Pose? Confidence Estimation in Visual Localization | Ferranti, Luca; Li, Xiaotian; Boutellier, Jani; Kannala, Juho | University of Vaasa | Poster | PS T3.11 | DAY 4 – January 15, 2021 |
1385 | Video Face Manipulation Detection through Ensemble of CNNs | Bonettini, Nicolo; Cannas, Edoardo Daniele; Mandelli, Sara; Bondi, Luca; Bestagini, Paolo; Tubaro, Stefano | Politecnico di Milano | Oral | OS T5.1 – PS T5.1 | DAY 1 – January 12, 2021 – DAY 1 – January 12, 2021 |
1388 | Overcoming Noisy and Irrelevant Data in Federated Learning | Tuor, Tiffany; Wang, Shiqiang; Ko, Bong Jun; Liu, Changchang; Leung, Kin K | IBM Research | Poster | PS T1.7 | DAY 2 – January 13, 2021 |
1391 | Novel View Synthesis from a 6-DoF Pose by Two-Stage Networks | Guo, Xiang; Li, Bo; Dai, Yuchao; Zhang, Tongxin; Deng, Hui | Northwestern Polytechnical University | Poster | PS T3.10 | DAY 4 – January 15, 2021 |
1392 | SAT-Net: Self-Attention and Temporal Fusion for Facial Action Unit Detection | Li, Zhihua; Zhang, Zheng; Yin, Lijun | Binghamton University | Poster | PS T2.1 | DAY 1 – January 12, 2021 |
1393 | Optimal Transport As a Defense against Adversarial Attacks | Bouniot, Quentin; Audigier, Romaric; Loesch, Angélique | CEA LIST | Poster | PS T1.7 | DAY 2 – January 13, 2021 |
1394 | Tensor Factorization of Brain Structural Graph for Unsupervised Classification in Multiple Sclerosis | Barile, Berardino; Marzullo, Aldo; Stamile, Claudio; Durand-Dubief, Françoise; Sappey-Marinier, Dominique | CREATIS; CNRS UMR5220; INSERM U1206; Université de Lyon, Université Lyon 1, INSA-Lyon, Villeurbanne, France | Poster | PS T3.11 | DAY 4 – January 15, 2021 |
1397 | Towards Artifacts-Free Image Defogging | Graffieti, Gabriele; Maltoni, Davide | University of Bologna | Oral | OS T5.3 – PS T5.4 | DAY 2 – January 13, 2021 – DAY 2 – January 13, 2021 |
1398 | CARRADA Dataset: Camera and Automotive Radar with Range-Angle-Doppler Annotations | Ouaknine, Arthur; Newson, Alasdair; Rebut, Julien; Tupin, Florence; Pérez, Patrick | Telecom Paris | Poster | PS T3.11 | DAY 4 – January 15, 2021 |
1400 | Exact and Convergent Iterative Methods to Compute the Orthogonal Point-To-Ellipse Distance | Guo, Siyu; Hu, Pingping; Ling, zhigang; Wen, He; Liu, Min; Tang, Lu | Hunan University | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
1401 | Data Augmentation Via Mixed Class Interpolation Using Cycle-Consistent Generative Adversarial Networks Applied to Cross-Domain Imagery | Sasaki, Hiroshi; Willcocks, Chris G.; Breckon, Toby | Durham University | Poster | PS T1.7 | DAY 2 – January 13, 2021 |
1402 | Transferable Model for Shape Optimization subject to Physical Constraints | Harsch, Lukas; Burgbacher, Johannes; Riedelbauch, Stefan | University of Stuttgart | Poster | PS T3.11 | DAY 4 – January 15, 2021 |
1403 | Handwritten Signature and Text Based User Verification Using Smartwatch | Ramachandra, Raghavendra; Venkatesh, Sushma; Raja, Kiran; Busch, Christoph | NTNU | Poster | PS T2.4 | DAY 3 – January 14, 2021 |
1404 | Compression of YOLOv3 Via Block-Wise and Channel-Wise Pruning for Real-Time and Complicated Autonomous Driving Environment Sensing Applications | Li, Jiaqi; Zhao, Yanan; Gao, Li; Cui, Feng | Beijing Institute of Technology | Poster | PS T3.10 | DAY 4 – January 15, 2021 |
1405 | A Novel Disaster Image Data-Set and Characteristics Analysis Using Attention Model | Niloy, Fahim Faisal; ., Arif; Nayem, Abu Bakar Siddik; Sarker, Anis; Paul, Ovi; Amin, M Ashraful; Ali, Amin Ahsan; Zaber, Moinul Islam; Rahman, AKMMahbubur | Independent University Bangladesh | Poster | PS T3.9 | DAY 3 – January 14, 2021 |
1407 | Image-based table cell detection: a new dataset and an improved detection method | Wei, Dafeng; Lu, Hongtao; Zhou, Yi; Chen, Kai | ShangHai JiaoTong University,China | Poster | PS T4.2 | DAY 2 – January 13, 2021 |
1408 | AOAM: Automatic Optimization of Adjacency Matrix for Graph Convolutional Network | Zhang, Yuhang; Ren, Hongshuai; Ye, Jiexia; Gao, Xitong; Wang, Yang; Ye, Kejiang; Xu, Cheng-Zhong | Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences | Poster | PS T1.4 | DAY 2 – January 13, 2021 |
1409 | Multi-Scale Residual Pyramid Attention Network for Monocular Depth Estimation | Liu, Jing; Zhang, Xiaona; Li, Zhaoxin; Mao, Tianlu | Institute of Computing Technology, Chinese Academy of Sciences | Poster | PS T3.10 | DAY 4 – January 15, 2021 |
1410 | N2D: (Not Too) Deep Clustering Via Clustering the Local Manifold of an Autoencoded Embedding | McConville, Ryan; Santos-Rodriguez, Raul; Piechocki, Robert; Craddock, Ian | University of Bristol | Oral | OS T1.3 – PS T1.6 | DAY 1 – January 12, 2021 – DAY 2 – January 13, ,2021 |
1412 | An Evaluation of DNN Architectures for Page Segmentation of Historical Newspapers | Liebl, Bernhard; Burghardt, Manuel | Leipzig University | Poster | PS T4.1 | DAY 1 – January 12, 2021 |
1413 | S-VoteNet: Deep Hough Voting with Spherical Proposal for 3D Object Detection | Chen, Yanxian; Ma, Huimin; Li, Xi; Luo, Xiong | University of Science and Technology Beijing | Poster | PS T3.10 | DAY 4 – January 15, 2021 |
1416 | Multi-Scale Keypoint Matching | Lotfian, Sina; Foroosh, Hassan | University of Central Florida | Poster | PS T3.9 | DAY 3 – January 14, 2021 |
1417 | Mask-Based Style-Controlled Image Synthesis Using a Mask Style Encoder | Cho, Jaehyeong; Shimoda, Wataru; Yanai, Keiji | The University of Electro-Commnications, Tokyo | Poster | PS T5.7 | DAY 4 – January 15, 2021 |
1421 | Exposing Deepfake Videos by Tracking Eye Movements | Li, Meng; Liu, Beibei; Hu, Yongjian; Wang, Yufei | South China University of Technology | Poster | PS T2.4 | DAY 3 – January 14, 2021 |
1423 | Not 3D Re-ID: Simple Single Stream 2D Convolution for Robust Video Re-Identification | Breckon, Toby; Alsehaim, Aishah | Durham University | Poster | PS T2.4 | DAY 3 – January 14, 2021 |
1424 | Uncertainty Guided Recognition of Tiny Craters on the Moon | Wilhelm, Thorsten; Wöhler, Christian | TU Dortmund University | Poster | PS T3.11 | DAY 4 – January 15, 2021 |
1425 | Multimodal Side-Tuning for Document Classification | Zingaro, Stefano; Lisanti, Giuseppe; Gabbrielli, Maurizio | University of Bologna | Poster | PS T4.1 | DAY 1 – January 12, 2021 |
1427 | Automatic Semantic Segmentation of Structural Elements related to the Spinal Cord in the Lumbar Region by Using Convolutional Neural Networks | Sáenz Gamboa, Jhon Jairo; de la Iglesia-Vaya, Maria; Gómez, Jon Ander | Foundation for the Promotion of Health and Biomedical Research of Valencia Region (FISABIO) | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
1428 | Transformer Reasoning Network for Image-Text Matching and Retrieval | Messina, Nicola; Falchi, Fabrizio; Esuli, Andrea; Amato, Giuseppe | ISTI-CNR | Poster | PS T4.1 | DAY 1 – January 12, 2021 |
1429 | Improving Image Matching with Varied Illumination | Braeger, Sarah; Foroosh, Hassan | University of Central Florida | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
1431 | End-To-End Hierarchical Relation Extraction for Generic Form Understanding | Anh, Nguyen Dang; Hoang, Duc-Thanh; Tran, Quang Bach; Pan, Chih-Wei; Nguyen, Thanh-Dat | Cinnamon-AI-Labs | Poster | PS T4.2 | DAY 2 – January 13, 2021 |
1432 | Exploiting the Logits: Joint Sign Language Recognition and Spell-Correction | Runkel, Christina; Dorenkamp, Stefan; Bauermeister, Hartmut; Möller, Michael | University of Siegen | Poster | PS T2.4 | DAY 3 – January 14, 2021 |
1434 | Learning Defects in Old Movies from Manually Assisted Restoration | Renaudeau, Arthur; Seng, Travis; Carlier, Axel; Durou, Jean-Denis; Pierre, Fabien; Lauze, Francois; Aujol, Jean-François | IRIT | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
1436 | Dual Stream Network with Selective Optimization for Skin Disease Recognition in Consumer Grade Images | Gupta, Krishnam; Rampure, Jaiprasad; Krishnan, Monu; Narayanan, Ajit; Narayan, Nikhil | Mfine | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
1438 | Photometric Stereo with Twin-Fisheye Cameras | Caracotte, Jordan; Morbidi, Fabio; Mouaddib, El Mustapha | Université de Picardie Jules Verne | Poster | PS T3.11 | DAY 4 – January 15, 2021 |
1441 | Depth Videos for the Classification of Micro-Expressions | Rakesh Kumar, Ankith Jain; Bhanu, Bir; Casey, Christopher; Cheung, Sierra; Seitz, Aaron | University of California Riverside | Poster | PS T2.1 | DAY 1 – January 12, 2021 |
1445 | A Neural Lip-Sync Framework for Synthesizing Photorealistic Virtual News Anchors | Zheng, Ruobing; Zhu, Zhou; Song, Bo; Changjiang, Ji | Moviebook | Poster | PS T3.10 | DAY 4 – January 15, 2021 |
1446 | Dealing with Scarce Labelled Data: Semi-Supervised Deep Learning with Mix Match for Covid-19 Detection Using Chest X-Ray Images | Ramirez, Saul; Giri, Raghvendra; Yang, Shengxiang; Moemeni, Armaghan; Umaña, Mario; Elizondo, David; Torrents-Barrena, Jordina; Molina-Cabello, Miguel A. | De Montfort University | Poster | PS T1.7 | DAY 2 – January 13, 2021 |
1449 | Revisiting Adversarial Attacks via Visual Imperceptible Bound | Chhabra, Saheb; Agarwal, Akshay; Singh, Richa; Vatsa, Mayank | IIIT-Delhi | Poster | PS T1.4 | DAY 2 – January 13, 2021 |
1451 | Classification of spatially enriched pixel time series with convolutional neural networks | Chelali, Mohamed; Kurtz, Camille; Puissant, Anne; Vincent, Nicole | Université de Paris | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
1453 | Generalized Iris Presentation Attack Detection Algorithm under Cross-Database Settings | Gupta, Mehak; Singh, Vishal; Agarwal, Akshay; Vatsa, Mayank; Singh, Richa | IIIT Delhi | Poster | PS T2.4 | DAY 3 – January 14, 2021 |
1456 | On the Robustness of 3D Human Pose Estimation | Chen, Zerui; Huang, Yan; Wang, Liang | University of Chinese Academy of Sciences | Oral | OS T2.3 – PS T2.3 | DAY 4 – January 15, 2021 – DAY 2 – January 13, 2021 |
1457 | Single Image Deblurring Using Bi-Attention Network | Yaowei, Li; Luo, Ye; Lu, Jianwei | Tongji University | Poster | PS T3.10 | DAY 4 – January 15, 2021 |
1458 | Detective: An Attentive Recurrent Model for Sparse Object Detection | Kechaou, Amine; Martinez, Manuel; Haurilet, Monica; Stiefelhagen, Rainer | Karlsruhe Institute of Technology | Poster | PS T3.11 | DAY 4 – January 15, 2021 |
1459 | Mutual Alignment between Audiovisual Features for End-To-End Audiovisual Speech Recognition | Liu, Hong; Wang, Yawei; Yang, Bing | Peking University | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
1462 | A Boundary-Aware Distillation Network for Compressed Video Semantic Segmentation | Lu, Hongchao; Deng, Zhidong | Tsinghua University | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
1467 | Attention-Based Deep Metric Learning for Near-Duplicate Video Retrieval | Wang, Kuan-Hsun; Cheng, Chia Chun; Chen, Yi-Ling; Song, Yale; Lai, Shang-Hong | National Tsing Hua University | Oral | OS T3.1 – PS T3.8 | DAY 1 – January 12, 2021 – DAY 3 – January 14, 2021 |
1470 | Multi-Domain Image-To-Image Translation with Adaptive Inference Graph | Nguyen, Phuc; lathuiliere, Stéphane; Ricci, Elisa | Télécom Paris | Poster | PS T1.7 | DAY 2 – January 13, 2021 |
1471 | Revisiting Sequence-To-Sequence Video Object Segmentation with Multi-Task Loss and Skip-Memory | Azimi, Fatemeh; Bischke, Benjamin; Palacio, Sebastian; Raue, Federico; Hees, Jörn; Dengel, Andreas | TU Kaiserslautern | Poster | PS T3.11 | DAY 4 – January 15, 2021 |
1472 | Near-Infrared Depth-Independent Image Dehazing using Haar Wavelets | Laha, Sumit; Sharma, Ankit; Hu, Shengnan; Foroosh, Hassan | University of Central Florida | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
1473 | Ultrasound Image Restoration Using Weighted Nuclear Norm Minimization | Yang, Hanmei; zhang, Heng; Luo, Ye; Lu, Jianwei; Lu, Jian | Tongji University | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
1474 | Story Comparison for Estimating Field of View Overlap in a Video Collection | Malon, Thierry; Chambon, Sylvie; Crouzil, Alain; Charvillat, Vincent | IRIT | Oral | OS T3.1 – PS T3.1 | DAY 1 – January 12, 2021 – DAY 1 – January 12, 2021 |
1475 | Mobile Augmented Reality: Fast, Precise, and Smooth Planar Object Tracking | Matveichev, Dmitri; Lin, Daw-Tung | National Taipei University | Poster | PS T3.10 | DAY 4 – January 15, 2021 |
1477 | A Few-Shot Learning Approach for Historical Ciphered Manuscript Recognition | Souibgui, Mohamed Ali; Fornés, Alicia; Kessentini, Yousri; Tudor, Crina | Computer Vision Center | Oral | OS T4.1 – PS T4.1 | DAY 1 – January 12, 2021 – DAY 1 – January 12, 2021 |
1478 | Lightweight Low-Resolution Face Recognition for Surveillance Applications | Martínez-Díaz, Yoanna; Mendez-Vazquez, Heydi; Luevano, Luis S.; Chang, Leonardo; Gonzalez-Mendoza, Miguel | Advanced Technologies Application Center | Poster | PS T2.1 | DAY 1 – January 12, 2021 |
1479 | Naturally Constrained Online Expectation Maximization | Pamplona, Daniela; Manzanera, Antoine | ENSTA | Poster | PS T1.7 | DAY 2 – January 13, 2021 |
1483 | Epileptic Seizure Prediction: A Semi-Dilated Convolutional Neural Network Architecture | Hussein, Ramy; Lee, Soojin; Ward, Rabab K.; McKeown, Martin | Stanford University | Poster | PS T5.1 | DAY 1 – January 12, 2021 |
1484 | Geographic-Semantic-Temporal Hypergraph Convolutional Network for Traffic Flow Prediction | Wang, Kesu; Chen, Jing; Liao, Shijie; Hou, Jiaxin; Xiong, Qingyu | School of Big Data & Software Engineering, Chongqing University | Poster | PS T1.4 | DAY 2 – January 13, 2021 |
1485 | Enhancing Semantic Segmentation of Aerial Images with Inhibitory Neurons | Ullah, Ihsan; Reilly, Sean; Madden, Michael | School of Computer Science, National University of Ireland Galway | Poster | PS T1.7 | DAY 2 – January 13, 2021 |
1486 | Dynamic Guidance Network for Monocular Depth Estimation | Xing, Xiaoxia; Cai, Yinghao; Wang, Yanqing; Lu, Tao; Yang, Yiping; Wen, Dayong | Institute of Automation, Chinese Academy of Sciences,Beijing, China | Poster | PS T3.10 | DAY 4 – January 15, 2021 |
1487 | DUET: Detection Utilizing Enhancement for Text in Scanned or Captured Documents | Jung, Eun-Soo; Son, HyeongGwan; Oh, Kyusam; Yun, Yongkeun; Kwon, Soonhwan; Kim, Min Soo | Samsung SDS | Poster | PS T4.3 | DAY 3 – January 14, 2021 |
1489 | Enriching Video Captions with Contextual Text | Rimle, Philipp; Dogan, Pelin; Gross, Markus | ETHZ | Poster | PS T3.11 | DAY 4 – January 15, 2021 |
1492 | Evaluation of BERT and ALBERT Sentence Embedding Performance on Downstream NLP Tasks | Choi, Hyunjin; Kim, Judong; Joe, Seongho; Gwon, Youngjune | Samsung SDS | Poster | PS T4.2 | DAY 2 – January 13, 2021 |
1494 | Human-Centric Parsing Network for Human-Object Interaction Detection | Chen, Guanyu; Chen, Chong; Zhao, Zhicheng; Su, Fei | Beijing University of Posts and Telecommunications | Poster | PS T1.4 | DAY 2 – January 13, 2021 |
1497 | On the use of Benford’s law to detect GAN-generated images | Bonettini, Nicolo; Bestagini, Paolo; Milani, Simone; Tubaro, Stefano | Politecnico di Milano | Poster | PS T1.7 | DAY 2 – January 13, 2021 |
1498 | Memetic Evolution of Training Sets with Adaptive Radial Basis Kernels for Support Vector Machines | Nalepa, Jakub; Dudzik, Wojciech; Kawulok, Michal | Silesian University of Technology | Poster | PS T1.7 | DAY 2 – January 13, 2021 |
1502 | MixNet for Generalized Face Presentation Attack Detection | Sanghvi, Nilay; Singh, Sushant; Agarwal, Akshay; Vatsa, Mayank; Singh, Richa | IIIT Delhi | Poster | PS T2.4 | DAY 3 – January 14, 2021 |
1503 | Position-Aware Safe Boundary Interpolation Oversampling | Liu, Yongxu; Liu, Yan | The Hong Kong Polytechnic University | Poster | PS T1.4 | DAY 2 – January 13, 2021 |
1506 | Dual-Memory Model for Incremental Learning: The Handwriting Recognition Use Case | Piot, Mélanie; Bourdolous, Bérangère; Deshayes, Aurelia; Prevost, Lionel; Jordan, Gonzalez | ESIEA | Poster | PS T1.4 | DAY 2 – January 13, 2021 |
1507 | Utilising Visual Attention Cues for Vehicle Detection and Tracking | Hu, Feiyan; Gurram Munirathnam, Venkatesh; O’Connor, Noel E; Smeaton, Alan; Little, Suzanne | Dublin City University | Poster | PS T3.11 | DAY 4 – January 15, 2021 |
1509 | Segmenting Messy Text: Detecting Boundaries in Text Derived from Historical Newspaper Images | Anderson, Carol; Crone, Phil | Ancestry.com | Poster | PS T4.1 | DAY 1 – January 12, 2021 |
1510 | KoreALBERT: Pretraining a Lite BERT Model for Korean Language Understanding | Lee, Hyunjae; Yun, Jaewoong; Hwang, Bongkyu; Joe, Seongho; Min, Seungjai; Gwon, Youngjune | SAMSUNG SDS | Poster | PS T4.2 | DAY 2 – January 13, 2021 |
1511 | VR Sickness Assessment with Perception Prior and Hybrid Temporal Features | Kuo, Po-Chen; Chuang, Li-Chung; Lin, Dong-Yi; LEE, MING-SUI | National Taiwan University | Poster | PS T5.7 | DAY 4 – January 15, 2021 |
1512 | Weakly Supervised Geodesic Segmentation of Egyptian Mummy CT Scans | Hati, Avik; Bustreo, Matteo; Sona, Diego; Murino, Vittorio; Del Bue, Alessio | Istituto Italiano di Tecnologia | Poster | PS T3.9 | DAY 3 – January 14, 2021 |
1513 | Towards Efficient 3D Point Cloud Scene Completion Via Novel Depth View Synthesis | Wang, Haiyan; Yang, Liang; Rong, Xuejian; Tian, Ying-li | CCNY, CUNY | Poster | PS T3.9 | DAY 3 – January 14, 2021 |
1519 | DeepBEV: A Conditional Adversarial Network for Birds Eye View Generation | Fraser, Helmi; Wang, Sen | Heriot-Watt University | Poster | PS T3.9 | DAY 3 – January 14, 2021 |
1520 | Learning to Rank for Active Learning: A Listwise Approach | Li, Minghan; Liu, Xialei; Van de Weijer, Joost; Raducanu, Bogdan | Universitat Autonoma de Barcelona | Oral | OS T1.5 – PS T1.12 | DAY 3 – January 14, 2021 – DAY 3 – January 14, 2021 |
1522 | An Empirical Analysis of Visual Features for Multiple Object Tracking in Urban Scenes | Miah, Mehdi; Pepin, Justine; Saunier, Nicolas; Bilodeau, Guillaume-Alexandre | Ecole polytechnique de Montréal | Poster | PS T5.1 | DAY 1 – January 12, 2021 |
1528 | Recognizing Bengali Word Images – A Zero-Shot Learning Perspective | Chanda, Sukalpa; Haitink, Daniël Arjen Willem; Prasad, Prashant Kumar; Baas, Jochem; Pal, Umapada; Schomaker, Lambert | Østfold University College | Poster | PS T4.1 | DAY 1 – January 12, 2021 |
1529 | Dynamic Low-Light Image Enhancement for Object Detection Via End-To-End Training | Guo, Haifeng; Lu, Tong; Wu, Yirui | State Key Laboratory for Software Technology, Nanjing University | Poster | PS T5.5 | DAY 3 – January 14, 2021 |
1532 | End-To-End Training of a Two-Stage Neural Network for Defect Detection | Bo, Jakob; Tabernik, Domen; Skocaj, Danijel | University of Ljubljana | Poster | PS T1.7 | DAY 2 – January 13, 2021 |
1534 | Translation Resilient Opportunistic WiFi Sensing | Bocus, Mohammud; Li, Wenda; Paulavi;Ius, Jonas; McConville, Ryan; Santos-Rodriguez, Raul; Chetty, Kevin; Piechocki, Robert | University of Bristol | Poster | PS T2.4 | DAY 3 – January 14, 2021 |
1538 | Galaxy Image Translation with Semi-Supervised Noise-Reconstructed Generative Adversarial Networks | Lin, Qiufan; Fouchez, Dominique; Pasquet, Jérôme | Aix Marseille Univ., CNRS/IN2P3, CPPM | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1540 | Multi-Scale Relational Reasoning with Regional Attention for Visual Question Answering | Ma, Yuntao; Lu, Tong; Wu, Yirui | State Key Laboratory for Software Technology, Nanjing University | Poster | PS T3.10 | DAY 4 – January 15, 2021 |
1544 | Automatic Annotation of Corpora For Emotion Recognition Through Facial Expressions Analysis | Mircoli, Alex; Diamantini, Claudia; Potena, Domenico; Storti, Emanuele | Università Politecnica delle Marche | Poster | PS T5.8 | DAY 4 – January 15, 2021 |
1549 | Improved Time-Series Clustering with UMAP Dimension Reduction Method | Pealat, Clément; Bouleax, Guillaume; Cheutet, Vincent | Univ Lyon, INSA-Lyon, DISP | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1551 | Generative Deep-Neural-Network Mixture Modeling with Semi-Supervised MinMax+EM Learning | Pande, Nilay; Awate, Suyash | Indian Institute of Technology (IIT) Bombay | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1552 | Deep Learning-Based Type Identification of Volumetric MRI Sequences | De Mello, Jean Pablo; Paixão, Thiago; Berriel, Rodrigo; Reyes, Mauricio; De Souza, Alberto F.; Badue, Claudine; Oliveira-Santos, Thiago | Universidade Federal do Espírito Santo | Poster | PS T5.8 | DAY 4 – January 15, 2021 |
1553 | A Framework for Local Outlier Detection from Spatio-Temporal Trajectory Datasets | Cai, Xumin; Aydin, Berkay; Ji, Anli; Angryk, Rafal | Georgia State University | Oral | OS T1.8 – PS T1.16 | DAY4 – January 15, 2021 – DAY 4 – January 15, 2021 |
1555 | BCAU-Net: A Novel Architecture with Binary Channel Attention Module for MRI Brain Segmentation | Zhu, Yongpei; Zhou, Zicong; Liao, Guojun; Yuan, Kehong | Tsinghua University | Poster | PS T5.5 | DAY 3 – January 14, 2021 |
1556 | Generation of Hypergraphs from the N-Best Parsing of 2D-Probabilistic Context-Free Grammars for Mathematical Expression Recognition | Ernesto, Noya; Sánchez, Joan Andreu; Benedi, Jose Miguel | Universitat Politecnica de Valencia | Poster | PS T4.1 | DAY 1 – January 12, 2021 |
1558 | Global-Local Attention Network for Semantic Segmentation in Aerial Images | Li, Minglong; shan, lianlei; Wang, Weiqiang | University of Chinese Academy of Sciences | Poster | PS T3.10 | DAY 4 – January 15, 2021 |
1559 | Graph Spectral Feature Learning for Mixed Data of Categorical and Numerical Type | Sahoo, Saswata; Chakraborty, Souradip | Gartner | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1562 | Distinctive 3D Local Deep Descriptors | Poiesi, Fabio; Boscaini, Davide | Fondazione Bruno Kessler | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1563 | Assessing the Severity of Health States Based on Social Media Posts | Yadav, Shweta; Sain, Joy Prakash; Sheth, Amit; Ekbal, Asif; Saha, Sriparna; Bhattacharyya, Pushpak | IIT Patna | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1567 | Longitudinal Feature Selection and Feature Learning for Parkinsons Disease Diagnosis and Prediction | Huang, Zhongwei; Lei, Haijun; Li, Shiqi; Xiao, Xiaohua; Lei, Yi; Tan, En-Leng; Lei, Baiying | Shenzhen University | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1568 | Appliance identification using a histogram post-processing of 2D local binary patterns for smart grid applications | Himeur, Yassine; Alsalemi, Abdullah; Bensaali, Faycal; Amira, Abbes | Qatar University | Poster | PS T5.8 | DAY 4 – January 15, 2021 |
1570 | Weakly Supervised Learning through Rank-Based Contextual Measures | Camacho Presotto, João Gabriel; Pascotti Valem, Lucas; Gomes de Sá, Nikolas; Pedronette, Daniel Carlos Guimaraes; Papa, Joao Paulo | UNESP – São Paulo State University | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1571 | Real Time Fencing Move Classification and Detection at Touch Time During a Fencing Match | Sunal, Cem Ekin; Willcocks, Chris G.; Obara, Boguslaw | Durham University | Oral | OS T1.6 – PS T1.14 | DAY 3 – January 14, 2021 – DAY 4 – January 15, 2021 |
1574 | Attentive Visual Semantic Specialized Network for Video Captioning | Perez-Martin, Jesus; Bustos, Benjamin; Pérez, Jorge | University of Chile | Poster | PS T3.9 | DAY 3 – January 14, 2021 |
1575 | On-Device Text Image Super Resolution | Jain, Dhruval; Prabhu, Arun; Ramena, Gopi; Goyal, Manoj; Mohanty, Debi; Purre, Naresh; Moharana, Sukumar | Samsung Research Institute Bangalore | Poster | PS T5.8 | DAY 4 – January 15, 2021 |
1582 | Towards Tackling Multi-Label Imbalances in Remote Sensing Imagery | Koßmann, Dominik; Wilhelm, Thorsten; Fink, Gernot | TU Dortmund University | Poster | PS T3.9 | DAY 3 – January 14, 2021 |
1585 | Multi-Resolution Fusion and Multi-Scale Input Priors Based Crowd Counting | Sajid, Usman; Ma, Wenchi; Wang, Guanghui | University of Kansas | Poster | PS T3.9 | DAY 3 – January 14, 2021 |
1589 | Gaussian Convolution Angles: Invariant Vein and Texture Descriptors for Butterfly Species Identification | Chen, Xin; Wang, Bin; Gao, Yongsheng | Griffith University | Poster | PS T3.4 | DAY 2 – January 13, 2021 |
1590 | Tackling Occlusion in Siamese Tracking with Structured Dropouts | Gupta, Deepak; Gavves, Efstratios; Smeulders, Arnold | University of Amsterdam | Poster | PS T3.9 | DAY 3 – January 14, 2021 |
1591 | Attention Based Coupled Framework for Road and Pothole Segmentation | Masihullah, Shaik; Garg, Ritu; Mukherjee, Prerana; Ray, Anupama | IIIT Sri City | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
1595 | Variational Capsule Encoder | RaviPrakash, Harish; Anwar, Syed; Bagci, Ulas | University of Central Florida | Poster | PS T1.12 | DAY 3 – January 14, 2021 |
1596 | Audio-Based Near-Duplicate Video Retrieval with Audio Similarity Learning | Avgoustinakis, Pavlos; Kordopatis-Zilos, Giorgos; Papadopoulos, Symeon; Symeonidis, Andreas L.; Kompatsiaris, Ioannis | CENTRE FOR RESEARCH & TECHNOLOGY – HELLAS | Poster | PS T5.7 | DAY 4 – January 15, 2021 |
1597 | Drift anticipation with forgetting to improve evolving fuzzy system | Leroy, Clément; Anquetil, Eric; Girard, Nathalie | Univ Rennes 1, CNRS, IRISA | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1598 | Improving Mix-And-Separate Training in Audio-Visual Sound Source Separation with an Object Prior | Nguyen, Quan; Richter, Julius; Lauri, Mikko; Gerkmann, Timo; Frintrop, Simone | University of Hamburg | Oral | OS T5.4 – PS T5.6 | DAY 3 – January 14, 2021 – DAY 3 – January 14, 2021 |
1600 | Hcore-Init: Neural Network Initialization Based on Graph Degeneracy | Limnios, Stratis; Dasoulas, George; Thilikos, Dimitrios; Vazirgiannis, Michalis | Ecole Polytechnique | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1601 | Vision-Based Multi-Modal Framework for Action Recognition | Beddiar, Djamila Romaissa; Oussalah, Mourad; Nini, Brahim | University of Oulu | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1602 | Efficient Shadow Detection and Removal using Synthetic Data with Domain Adaptation | Guo, Rui; Ayinde, Babajide; Sun, Hao | Toyota Motor North America, R&D InfoTech Labs | Poster | PS T1.12 | DAY 3 – January 14, 2021 |
1604 | Attribute-Based Quality Assessment for Demographic Estimation in Face Videos | Becerra-Riera, Fabiola; Morales-González, Annette; Mendez-Vazquez, Heydi; Dugelay, Jean-Luc | Advanced Technologies Application Center | Oral | OS T2.2 – PS T2.5 | DAY 3 – January 14, 2021 – DAY 4 – January 15, 2021 |
1605 | Background Invariance by Adversarial Learning | Cruz, Ricardo; Prates, Ricardo M.; Simas Filho, Eduardo F.; Pinto Costa, Joaquim F.; Cardoso, Jaime S. | INESC TEC & FEUP | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
1608 | Conditional-UNet: A Condition-aware Deep Model for Coherent Human Activity Recognition From Wearables | Zhang, Liming; Zhang, Wenbin; Japkowicz, Nathalie | George Mason University | Poster | PS T1.12 | DAY 3 – January 14, 2021 |
1615 | Attention-Driven Body Pose Encoding for Human Activity Recognition | Debnath, Bappaditya; O’Brien, Mary R.; Kumar, Swagat; Behera, Ardhendu | Edge Hill University | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1616 | Object Detection on Monocular Images with Two-Dimensional Canonical Correlation Analysis | Yu, Zifan; You, Suya | University of Southern California | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
1622 | Estimating Static and Dynamic Brain Networks by Kulback-Leibler Divergence from fMRI Data | Degirmendereli, Gonul; Yarman Vural, Fatos | Middle East Technical University | Oral | OS T5.5 – PS T5.8 | DAY 4 – January 15, 2021 – DAY 4 – January 15, 2021 |
1623 | Price Suggestion for Online Second-Hand Items | Han, Liang; Yin, Zhaozheng; Xia, Zhurong; Guo, Li; Tang, Mingqian; Jin, Rong | Stony Brook University | Poster | PS T1.12 | DAY 3 – January 14, 2021 |
1624 | Detecting Marine Species in Echograms Via Traditional, Hybrid, and Deep Learning Frameworks | Tunai, Porto Marques; Rezvanifar, Alireza; Cote, Melissa; Branzan Albu, Alexandra; Ersahin, Kaan; Mudge, Todd; Gauthier, Stephane | University of Victoria | Poster | PS T5.1 | DAY 1 – January 12, 2021 |
1626 | Ancient Document Layout Analysis: Autoencoders Meet Sparse Coding | Davoudi, Homa; Fiorucci, Marco; Traviglia, Arianna | Istituto Italiano di Tecnologia (IIT) | Poster | PS T4.1 | DAY 1 – January 12, 2021 |
1630 | A Multi-task Contextual Atrous Residual Network for Brain Tumor Detection & Segmentation | Le, Ngan; Yamazaki, Kashu; Kha Gia, Quach; Truong, Thanh-Dat; Savvides, Marios | University of Arkansas | Poster | PS T5.1 | DAY 1 – January 12, 2021 |
1631 | Computational Data Analysis for First Quantization Estimation on JPEG Double Compressed Images | Battiato, Sebastiano; Giudice, Oliver; Guarnera, Francesco; Puglisi, Giovanni | University of Catania | Poster | PS T5.7 | DAY 4 – January 15, 2021 |
1635 | Unsupervised 3D Human Pose Estimation in Multi-view-multi-pose Video | Sun, Cheng; Thomas, Diego; Kawasaki, Hiroshi | Kyushu University | Poster | PS T3.7 | DAY 3 – January 14, 2021 |
1636 | Learning Dictionaries of Kinematic Primitives for Action Classification | Vignolo, Alessia; Noceti, Nicoletta; Sciutti, Alessandra; Odone, Francesca; Sandini, Giulio | Istituto Italiano di Tecnologia | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
1638 | Interpolation in Auto Encoders with Bridge Processes | Ringqvist, Carl; Butepage, Judith; Kjellstrom, Hedvig; Hult, Henrik | Royal Institute of Technology | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1639 | Unsupervised Feature Learning for Event Data: Direct vs Inverse Problem Formulation | Kostadinov, Dimche; Scaramuzza, Davide | University of Zurich, Robotics and Perception Group | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
1640 | One-Shot Representational Learning for Joint Biometric and Device Authentication | Banerjee, Sudipta; Ross, Arun | Michigan State University | Poster | PS T2.1 | DAY 1 – January 12, 2021 |
1643 | Cam-Softmax for Discriminative Deep Feature Learning | Suveges, Tamas; McKenna, Stephen James | University of Dundee | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
1644 | Color, Edge, and Pixel-Wise Explanation of Predictions Based onInterpretable Neural Network Model | Jung, Jay Hoon; Kwon, YoungMin | The State University of New York at Korea | Poster | PS T1.3 | DAY 2 – January 13, 2021 |
1646 | Makeup Style Transfer on Low-Quality Images with Weighted Multi-Scale Attention | Organisciak, Daniel; Ho, Edmond S. L.; Shum, Hubert P. H. | Northumbria University | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1647 | 3D Attention Mechanism for Fine-Grained Classification of Table Tennis Strokes Using a Twin Spatio-Temporal Convolutional Neural Networks | Martin, Pierre-Etienne; Benois-Pineau, Jenny; Péteri, Renaud; Morlier, Julien | Univ. Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR 5800, F-33400, Talence, France | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1648 | Boundaries of Single-Class Regions in the Input Space of Piece-Wise Linear Neural Networks | Jung, Jay Hoon; Kwon, YoungMin | The State University of New York at Korea | Oral | OS T1.7 – PS T1.9 | DAY 4 – January 15, 2021 – DAY 3 January 14, 2021 |
1649 | Subspace Clustering for Action Recognition with Covariance Representations and Temporal Pruning | Paoletti, Giancarlo; Cavazza, Jacopo; Beyan, Cigdem; Del Bue, Alessio | Istituto Italiano di Tecnologia | Oral | OS T1.3 – PS T1.5 | DAY 1 – January 12, 2021 – DAY 2 – January 13, 2021 |
1652 | Recognizing American Sign Language Nonmanual Signal Grammar Errors in Continuous Videos | Vahdani, Elahe; Jing, Longlong; Tian, Ying-li; Huenerfauth, Matt | CCNY, CUNY | Poster | PS T2.1 | DAY 1 – January 12, 2021 |
1653 | Planar 3D Transfer Learning for End to End Unimodal MRI Unbalanced Data Segmentation | Kolarik, Martin; Burget, Radim; Travieso-Gonzalez, Carlos M.; Kocica, Jan | Brno University of Technology | Oral | OS T1.6 – PS T1.15 | DAY 3 – January 14, 2021 – DAY 4 – January 15, 2021 |
1654 | PRF-Ped: Multi-Scale Pedestrian Detector with Prior-Based Receptive Field | Tan, Yuzhi; Yao, Hongxun; Li, Haoran; Lu, Xiusheng; Xie, Haozhe | Harbin Institute of Technology | Poster | PS T3.7 | DAY 3 – January 14, 2021 |
1656 | Force Banner for the recognition of spatial relations | Deléarde, Robin; Kurtz, Camille; WENDLING, Laurent; Dejean, Philippe | Université de Paris, LIPADE EA 2517 | Oral | OS T5.2 – PS T5.2 | DAY 1 – January 12, 2021 – DAY 1 – January 12, 2021 |
1657 | Algorithm Recommendation for Data Streams | Martins Camboim de Sá, Jáder; Luis Debiaso Rossi, Andre; Enrique de Almeida Prado Alves Batista, Gustavo; Paulo Faina Garcia, Luís | University of Brasilia | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1658 | Multiple Future Prediction Leveraging Synthetic Trajectories | Berlincioni, Lorenzo; Becattini, Federico; Seidenari, Lorenzo; Del Bimbo, Alberto | University of Florence | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1659 | A Quantitative Evaluation Framework of Video De-Identification Methods | Bursic, Sathya; D’Amelio, Alessandro; Granato, Marco; Grossi, Giuliano; Lanzarotti, Raffaella | Università degli Studi di Milano | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1665 | Watch Your Strokes: Improving Handwritten Text Recognition with Deformable Convolutions | Cojocaru, Iulian; Cascianelli, Silvia; Baraldi, Lorenzo; Corsini, Massimiliano; Cucchiara, Rita | University of Modena and Reggio Emilia | Poster | PS T4.1 | DAY 1 – January 12, 2021 |
1668 | Computing Stable Resultant-Based Minimal Solvers by Hiding a Variable | Bhayani, Snehal; Kukelova, Zuzana; Heikkilä, Janne | University of Oulu | Oral | OS T3.6 – PS T3.11 | DAY 4 – January 15, 2021 – DAY 4 – January 15, 2021 |
1669 | A Detection-based Approach to Multiview Action Classification in Infants | Pacheco, Carolina; Mavroudi, Effrosyni; Kokkoni, Elena; Tanner, Herbert; Vidal, Rene | Johns Hopkins University | Oral | OS T2.1 – PS T2.1 | DAY 1 – January 12, 2021 |
1670 | Fine-tuning Convolutional Neural Networks: a comprehensive guide and benchmark analysis for Glaucoma Screening | Mvoulana, Amed; Kachouri, Rostom; Akil, Mohamed | Université Gustave Eiffel | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
1671 | Quantifying the Use of Domain Randomization | Ani, Mohammad; Basevi, Hector; Leonardis, Ales | University of Birmingham | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
1672 | Knowledge Distillation is beyond model compression | Zonooz, Bahram; Arani, Elahe; Zonooz, Bahram | Navinfo Europe | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1674 | NephCNN: A deep-learning framework for vessel segmentation in nephrectomy laparoscopic videos | Casella, Alessandro; Moccia, Sara; Carlini, Chiara; Frontoni, Emanuele; De Momi, Elena; Mattos, Leonardo | Istituto Italiano di Tecnologia, Politecnico di Milano | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
1675 | PolyLaneNet: Lane Estimation Via Deep Polynomial Regression | Tabelini, Lucas; Berriel, Rodrigo; Paixão, Thiago; Badue, Claudine; De Souza, Alberto F.; Oliveira-Santos, Thiago | Universidade Federal do Espírito Santo | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
1676 | Concept Embedding through Canonical Forms: A Case Study on Zero-Shot ASL Recognition | Kamzin, Azamat; Amperyani, Apurupa; Sukhapalli, Prasanth; Banerjee, Ayan; Gupta, Sandeep | Arizona State University | Poster | PS T2.1 | DAY 1 – January 12, 2021 |
1677 | Viability of Optical Coherence Tomography for Iris Presentation Attack Detection | Sharma, Renu; Ross, Arun | Michigan State University | Poster | PS T2.1 | DAY 1 – January 12, 2021 |
1678 | DR2S: Deep Regression with Region Selection for Camera Quality Evaluation | Tworski, Marcelin; lathuiliere, Stéphane; Belkarfa, Salim; Fiandrotti, Attilio; Cagnazzo, Marco | Télécom Paris | Poster | PS T5.6 | DAY 3 – January 14, 2021 |
1679 | Categorizing the Feature Space for Two-Class Imbalance Learning | Sicilia, Rosa; Cordelli, Ermanno; Soda, Paolo | Università Campus Bio-Medico di Roma | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1688 | Offset Curves Loss for Imbalanced Problem in Medical Segmentation | Le, Ngan; Le, Trung; Bui, Duc Toan; Luu, Khoa; Savvides, Marios | University of Arkansas | Poster | PS T5.1 | DAY 1 – January 12, 2021 |
1689 | Evaluation of Anomaly Detection Algorithms for the Real-World Applications | Ivanovska, Marija; Tabernik, Domen; Skocaj, Danijel; Pers, Janez | University of Ljubljana | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1690 | ResNet-like Architecture with Low Hardware Requirements | Limonova, Elena; Alfonso, Daniil; Nikolaev, Dmitry; Arlazarov, Vladimir V. | FRC CSC RAS, Smart Engines Service LLC | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1693 | Assortative-Constrained Stochastic Block Models | Gribel, Daniel; Vidal, Thibaut; Gendreau, Michel | Pontificia Universidade Catolica do Rio de Janeiro | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1697 | Auto Encoding Explanatory Examples with Stochastic Paths | Ojeda Marin, Cesar Ali; Sanchez, Ramses J.; Cvejoski, Kostadin; Georgiev, Bogdan | TU Berlin | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1698 | Label or Message: A Large-Scale Experimental Survey of Texts and Objects Co-Occurrence | Takeshita, Koki; Shioyama, Juntaro; Uchida, Seiichi | Kyushu Uiversity | Oral | OS T 4.2 – PS T4.3 | DAY 4 – January 15, 2021 – DAY 3 – January 14, 2021 |
1700 | On Morphological Hierarchies for Image Sequences | Tuna, Caglayan; Giros, Alain; Merciol, François; Lefèvre, Sébastien | Université Bretagne Sud | Poster | PS T5.8 | DAY 4 – January 15, 2021 |
1702 | Local Clustering with Mean Teacher for Semi-Supervised Learning | Chen, Zexi; Dutton, Benjamin; Ramachandra, Bharathkumar; Wu, Tianfu; Vatsavai, Ranga Raju | North Carolina State University | Oral | OS T1.3 – PS T1.8 | DAY 1 – January 12, 2021 – DAY 2 – January 13, 2021 |
1703 | Wireless Localisation in WiFi Using Novel Deep Architectures | Li, Peizheng; Cui, Han; Khan, Aftab; Raza, Usman; Piechocki, Robert; Doufexi, Angela; Farnham, Tim | Univeristy of Bristol, Toshiba Europe Ltd. | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1704 | Class-Incremental Learning with Pre-Allocated Fixed Classifiers | Pernici, Federico; Bruni, Matteo; Baecchi, Claudio; Turchini, Francesco; Del Bimbo, Alberto | University of Florence | Poster | PS T1.15 | DAY 4 – January 15, 2021 |
1705 | Global Image Sentiment Transfer | An, Jie; Chen, Tianlang; Zhang, Songyang; Luo, Jiebo | University of Rochester | Poster | PS T3.7 | DAY 3 – January 14, 2021 |
1710 | Surface Material Dataset for Robotics Applications (SMDRA): A Dataset with Friction Coefficient and RGB-D for Surface Segmentation | Noh, Donghun; Nam, Hyunwoo; Ahn, Min Sung; Chae, Hosik; Lee, Sangjoon; Gillespie, Kyle; Hong, Dennis | University of California, Los Angeles | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
1715 | Equation Attention Relationship Network (EARN) : A Geometric Deep Metric Framework for Learning Similar Math Expression Embedding | Ahmed, Saleem; Davila, Kenny; Setlur, Srirangaraj; Govindaraju, Venu | University at Buffalo | Poster | PS T4.1 | DAY 1 – January 12, 2021 |
1717 | Accuracy-Perturbation Curves for Evaluation of Adversarial Attack and Defence Methods | ircelj, Jaka; Skocaj, Danijel | University of Ljubljana | Poster | PS T1.15 | DAY 4 – January 15, 2021 |
1719 | Tensorized Feature Spaces for Feature Explosion | Pasricha, Ravdeep; Devineni, Pravallika; Papalexakis, Evangelos; Kannan, Ramakrishnan | University of California Riverside | Poster | PS T1.12 | DAY 3 – January 14, 2021 |
1721 | Switching Dynamical Systems with Deep NeuralNetworks | Ojeda Marin, Cesar Ali; Cvejoski, Kostadin; Georgiev, Bogdan; Sanchez, Ramses J. | BIT, University of Bonn | Poster | PS T1.15 | DAY 4 – January 15, 2021 |
1723 | From Early Biological Models to CNNs: Do They Look Where Humans Look? | Cadoni, Marinella Iole; Lagorio, Andrea; Grosso, Enrico; Tan, Jia Huei; Chan, Chee Seng | Università di Sassari | Poster | PS T1.15 | DAY 4 – January 15, 2021 |
1725 | Motion and Region aware Adversarial Learning for Fall Detection with Thermal Imaging | Mehta, Vineet; Dhall, Abhinav; Pal, Sujata; Khan, Shehroz | Indian Institute of Technology, Ropar | Poster | PS T1.15 | DAY 4 – January 15, 2021 |
1727 | Self-Supervised Learning with Graph Neural Networks for Region of Interest Retrieval in Histopathology | Ozen, Yigit; Aksoy, Selim; Kosemehmetoglu, Kemal; Onder, Sevgen; Uner, Aysegul | Bilkent University | Poster | PS T5.8 | DAY 4 – January 15, 2021 |
1728 | In Depth Semantic Scene Completion | Gillsjö, David; Åström, Kalle | Lund University | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
1731 | Extending Single Beam Lidar to Full Resolution by Fusing with Single Image Depth Estimation | Lu, Yawen; Wang, Yuxing; Parikh, Devarth; Xin, Yuan; Lu, Guoyu | Rochester Institute of Technology | Oral | OS T5.4 – PS T5.4 | DAY 3 – January 14, 2021. – DAY 2 – January 13, 2021 |
1737 | Social Network Analysis Using Knowledge-Graph Embeddings and Convolution Operations | Molokwu, Bonaventure Chidube; Shuvo, Shaon Bhatta; Kobti, Ziad; Kar, Narayan C. | University of Windsor | Poster | PS T1.12 | DAY 3 – January 14, 2021 |
1738 | Temporal Pulses Driven Spiking Neural Network for Time and Power Efficient Object Recognition in Autonomous Driving | Wang, Wei; Zhou, Shibo; Li, Jingxi; Li, Xiaohua; Yuan, Junsong; Jin, Zhanpeng | University at Buffalo | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
1741 | Interpretable Emotion Classification Using Temporal Convolutional Models | Gund, Manasi Bharat; Bharadwaj, Abhiram Ravi; Nwogu, Ifeoma | Rochester Institute of Technology | Poster | PS T2.1 | DAY 1 – January 12, 2021 |
1742 | Partially Monotone Dependence | Khryashchev, Denis; Vo, Huy; Haralick, Robert | City University of New York, Graduate Center | Oral | OS T5.3 – PS T5.4 | DAY 2 – January 13, 2021 – DAY 2 – January 13, 2021 |
1743 | JT-MGCN: Joint-Temporal Motion Graph Convolutional Network for Skeleton-Based Action Recognition | Nam, Suekyeong; Lee, Seungkyu | kyunghee university | Oral | OS T2.1 – PS T2.2 | DAY 1 – January 12, 2021 – DAY 2 – January 13, 2021 |
1745 | XGBoost to Interpret the Opioid Patients StateBased on Cognitive and Physiological Measures | Dehzangi, Omid; Shokouhmand, Arash; Ramadan, Jad; Finomore, Victor; Nasrabadi, Nasser M.; Rezai, Ali | West Virginia University | Poster | PS T5.1 | DAY 1 – January 12, 2021 |
1747 | Mutual Information Based Method for Unsupervised Disentanglement of Video Representation | P, Aditya Sreekar; Tiwari, Ujjwal; Namboodiri, Anoop | International Institute of Information Technology, Hyderabad | Poster | PS T1.15 | DAY 4 – January 15, 2021 |
1749 | Energy Minimum Regularization in Continual Learning | Li, Xiaobin; Wang, Weiqiang | University of Chinese Academy of Sciences | Poster | PS T1.12 | DAY 3 – January 14, 2021 |
1750 | Attentive Hybrid Feature Based a Two-Step Fusion for Facial Expression Recognition | Weng, Jun; Yang, Yang; Tan, Zichang; Lei, Zhen | Institute of Automation, Chinese Academy of Sciences | Poster | PS T2.4 | DAY 3 – January 14, 2021 |
1751 | SPA: Stochastic Probability Adjustment for System Balance of Unsupervised SNNs | Yang, Xingyu; Meng, Mingyuan; Xiao, Shanlin; Yu, Zhiyi | Sun Yat-sen University | Poster | PS T1.12 | DAY 3 – January 14, 2021 |
1757 | OCT Image Segmentation Using NeuralArchitecture Search and SRGAN | Omid Dehzangi, Saba Heidari, Annahita Amireskandari, Nasser M. Nasrabadi, Ali Rezai | West Virginia University | Poster | PS T5.1 | DAY 1 – January 12, 2021 |
1758 | Rotation Invariant Aerial Image Retrieval with Group Convolutional Metric Learning | Chung, Hyunseung; Nam, Woo-Jeoung; Lee, Seong-Whan | Korea University | Poster | PS T1.3 | DAY 2 – January 13, 2021 |
1762 | Automatic Tuberculosis Detection Using Chest X-Ray Analysis with Position Enhanced Structural Information | Nkouanga, Hermann Jepdjio; Vajda, Szilard | Central Washington University | Poster | PS T5.1 | DAY 1 – January 12, 2021 |
1763 | Video Lightening with Dedicated CNN Architecture | Wang, Li-Wen; Siu, Wan-Chi; Liu, Zhi-Song; Li, Chu-Tak; Lun, P. K. Daniel | Hong Kong Polytechnic University | Poster | PS T5.5 | DAY 3 – January 14, 2021 |
1765 | Vision-Based Layout Detection from Scientific Literature Using Recurrent Convolutional Neural Networks | Yang, Huichen; Hsu, William | Kansas State University | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
1766 | Surface IR Reflectance Estimation and Material Recognition Using ToF Camera | Lee, SeokYeong; Lee, Seungkyu | kyunghee university | Poster | PS T3.7 | DAY 3 – January 14, 2021 |
1769 | Semi-Supervised Person Re-Identification by Attribute Similarity Guidance | Hong, Peixian; Wu, Ancong; Zheng, Wei-Shi | Sun Yat-sen University | Poster | PS T2.4 | DAY 3 – January 14, 2021 |
1771 | Dimensionality Reduction for Data Visualization and Linear Classification, and the Trade-off between Robustness and Classification Accuracy | Becker, Martin; Lippel, Jens; Zielke, Thomas | Hochschule Düsseldorf – University of Applied Sciences | Poster | PS T1.15 | DAY 4 – January 15, 2021 |
1772 | Supervised Classification Using Graph-based Space Partitioning for Multiclass Problems | Yanev, Nicola; Valev, Ventzeslav; Krzyzak, Adam; Ben Suliman, Karima | Concordia University | Poster | PS T1.12 | DAY 3 – January 14, 2021 |
1773 | Quality-Based Representation for Unconstrained Face Recognition | Méndez-Llanes, Nelson; Castillo-Rosado, Katy; Mendez-Vazquez, Heydi; Tistarelli, Massimo | Advanced Technologies Application Center | Oral | OS T2.2 – PS T2.5 | DAY 3 – January 14, 2021 – DAY 4 – January 15, 2021 |
1783 | Unsupervised Sound Source Localization From Audio-Image Pairs Using Input Gradient Map | Tanaka, Tomohiro; Shinozaki, Takahiro | Tokyo Institute of Technology | Poster | PS T1.3 | DAY 2 – January 13, 2021 |
1785 | Thermal Image Enhancement using Generative Adversarial Network for Pedestrian Detection | Marnissi, Mohamed Amine; Fradi, Hajer; Sahbani, Anis; Essoukri Ben Amara, Najoua | University of Sousse | Poster | PS T2.4 | DAY 3 – January 14, 2021 |
1787 | Probability Guided Maxout | Ferrari, Claudio; Berretti, Stefano; Del Bimbo, Alberto | University of Florence | Poster | PS T1.15 | DAY 4 – January 15, 2021 |
1788 | 3D Dental Biometrics: Automatic Pose-invariant Dental Arch Extraction and Matching | Xin Zhong; Zhang, Zhiyuan | Technology and Research (A*S | Poster | PS T2.5 | DAY 4 – January 15, 2021 |
1796 | Rotation Detection in Finger Vein Biometrics using CNNs | Prommegger, Bernhard; Wimmer, Georg; Uhl, Andreas | University of Salzburg | Poster | PS T2.5 | DAY 4 – January 15, 2021 |
1797 | Classification and Feature Selection Using a Primal-Dual Method and Projections on Structured Constraints | Barlaud, Michel; Chambolle, Antonin; Caillau, Jean_Baptiste | CNRS/University of Nice-Sophia Antipolis | Poster | PS T1.15 | DAY 4 – January 15, 2021 |
1801 | Deep Learning on Active Sonar Data Using Bayesian Optimization for Hyperparameter Tuning | Berg, Henrik; Hjelmervik, Karl Thomas | Norwegian Defence Research Establishment | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1804 | Compact CNN Structure Learning by Knowledge Distillation | Ahmed, Waqar; Zunino, Andrea; Morerio, Pietro; Murino, Vittorio | Istituto Italiano di Tecnologia (IIT) | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1808 | Chebyshev-Harmonic-Fourier-Moments and Deep CNNs for Detecting Forged Handwriting | Nandanwar, Lokesh; Palaiahnakote, Shivakumara; Sayani, Kundu; Pal, Umapada; Lu, Tong; Lopresti, Daniel | National University of Singapore | Poster | PS T4.2 | DAY 2 – January 13, 2021 |
1809 | Matching of Matching-Graphs a Novel Approach for Graph Classification | Fuchs, Mathias; Riesen, Kaspar | University of Bern | Poster | PS T1.11 | DAY 3 – January 14, 2021 |
1813 | Multi-Scale Deep Pixel Distribution Learning for Concrete Crack Detection | Wu, Xuanyi; Ma, Jianfei; Sun, Yu; zhao, Chenqiu; Basu, Anup | University of Alberta | Poster | PS T5.1 | DAY 1 – January 12, 2021 |
1818 | A Benchmark Dataset for Segmenting Liver, Vasculature and Lesions from Large-Scale Computed Tomography Data | Wang, Bo; Yan, Qingsen; Xu, Zhengqing; Jingyang, Ai; Shuo, Jin; Wei, Zhao; Xu, Wei; Zhang, Liang; You, Zheng | Northwestern Ployteachnical University | Poster | PS T5.5 | DAY 3 – January 14, 2021 |
1820 | Are Multiple Cross-Correlation Identities Better Than Just Two? Improving the Estimate of Time Differences-Of-Arrivals from Blind Audio Signals | Greco, Danilo; Cavazza, Jacopo; Del Bue, Alessio | Università degli Studi di Genova | Poster | PS T5.2 | DAY 1 – January 12, 2021 |
1823 | A Joint Representation Learning and Feature Modeling Approach for One-class Recognition | Perera, Pramuditha; Patel, Vishal | Johns Hopkins University | Poster | PS T1.12 | DAY 3 – January 14, 2021 |
1828 | Scene Text Detection with Selected Anchors | Zhu, Anna; Du, Hang; Xiong, ShengWu | WUHAN UNIVERSITY OF TECHNOLOGY | Poster | PS T4.3 | DAY 3 – January 14, 2021 |
1830 | Joint Semantic-Instance Segmentation of 3D Point Clouds: Instance Separation and Semantic Fusion | Zhong, Min; Zeng, Gang | Peking University | Poster | PS T3.7 | DAY 3 – January 14, 2021 |
1831 | Enhanced Vote Network for 3D Object Detection in Point Clouds | Zhong, Min; Zeng, Gang | Peking University | Poster | PS T3.7 | DAY 3 – January 14, 2021 |
1834 | Local Grouped Invariant Order Pattern for Grayscale-Inversion and Rotation Invariant Texture Classification | Huang, Yankai; Song, Tiecheng; Li, Shuang; Han, Yuanjing | Chongqing University of Posts and Telecommunications | Poster | PS T5.5 | DAY 3 – January 14, 2021 |
1835 | End-To-End Deep Learning Methods for Automated Damage Detection in Extreme Events at Various Scales | Bai, Yongsheng; Sezen, Halil; Yilmaz, Alper | Ohio State University | Poster | PS T1.12 | DAY 3 – January 14, 2021 |
1838 | NetCalib: A Novel Approach for LiDAR-Camera Auto-Calibration Based on Deep Learning | Wu, Shan; Hadachi, Amnir; Vivet, Damien; Prabhakar, Yadu | University of Tartu | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
1839 | Vehicle Classification from Profile Measures | Patanè, Marco; Fusiello, Andrea | University of Udine | Oral | OS T3.5 – PS T3.10 | DAY 4 – January 15, 2021 – DAY 4 – January 15, 2021 |
1846 | MFI: Multi-Range Feature Interchange for Video Action Recognition | Bai, Sikai; Wang, Qi; Li, Xuelong | Northwestern Polytechnical University | Poster | PS T2.5 | DAY 4 – January 15, 2021 |
1847 | Segmentation of Axillary and Supraclavicular Tumoral Lymph Nodes in PET/CT: A Hybrid CNN/Component-Tree Approach | Farfan Cabrera, Diana Lucia; Gogin, Nicolas; Morland, David; Naegel, Benoît; Papathanassiou, Dimitri; Passat, Nicolas | Université de Reims, GE Healthcare | Oral | OS T5.5 – PS T5.8 | DAY 4 – January 15, 2021 – DAY 4 – January 15, 2021 |
1849 | RSAC: Regularized Subspace Approximation Classifier for Lightweight Continuous Learning | Ho, Chih-Hsing; Tsai, Shang-Ho | National Chiao Tung University | Poster | PS T1.12 | DAY 3 – January 14, 2021 |
1857 | Hybrid Cascade Point Search Network for High Precision Chart Component Detection | Luo, Junyu; Wang, Jinpeng; Lin, Chin-Yew | Microsoft Research | Poster | PS T4.2 | DAY 2 – January 13, 2021 |
1860 | Tackling Contradiction Detection in German Using Machine Translation and End-to-End Recurrent Neural Networks | Pielka, Maren; Sifa, Rafet; Hillebrand, Lars Patrick; Biesner, David; Ramamurthy, Rajkumar; Ladi, Anna; Bauckhage, Christian | Fraunhofer IAIS | Poster | PS T4.1 | DAY 1 – January 12, 2021 |
1861 | Multi-Graph Convolutional Network for Relationship-Driven Stock Movement Prediction | Ye, Jiexia; Zhao, Juanjuan; Ye, Kejiang; Xu, Cheng-Zhong | Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences | Poster | PS T1.12 | DAY 3 – January 14, 2021 |
1862 | End-To-End Multi-Task Learning for Lung Nodule Segmentation and Diagnosis | Chen, Wei; Wang, Qiuli; Yang, Dan; Zhang, Xiaohong; Liu, Chen; Li, Yucong | Chongqing University | Oral | OS T5.5 – PS T5.3 | DAY 4 – January 15, 2021 – DAY 2 – January 13, 2021 |
1863 | Joint Supervised and Self-Supervised Learning for 3D Real World Challenges | Alliegro, Antonio; Boscaini, Davide; Tommasi, Tatiana | Politecnico di Torino | Oral | OS T1.3 – PS T1.6 | DAY 1 – January 12, 2021 – DAY 2 January 13, 2021 |
1864 | Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detection | Rippel, Oliver; Mertens, Patrick; Merhof, Dorit | RWTH Aachen University | Poster | PS T1.12 | DAY 3 – January 14, 2021 |
1867 | On the Minimal Recognizable Image Patch | Fonaryov, Mark; Lindenbaum, Michael | Technion | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
1870 | Dual-Mode Iterative Denoiser: Tackling the Weak Label for Anomaly Detection | Lin, Shuheng; Yang, Hua | Shanghai Jiao Tong University | Poster | PS T3.7 | DAY 3 – January 14, 2021 |
1872 | Verifying the Causes of Adversarial Examples | Li, Honglin; Fan, Yifei; Ganz, Frieder; Yezzi, Anthony; Barnaghi, Payam | Georgia Institute of Technology | Poster | PS T1.12 | DAY 3 – January 14, 2021 |
1876 | Domain Generalized Person Re-Identification Via Cross-Domain Episodic Learning | Lin, Ci-Siang; Cheng, Yuan Chia; Wang, Yu-Chiang Frank | National Taiwan University | Poster | PS T3.7 | DAY 3 – January 14, 2021 |
1877 | Dual-MTGAN: Stochastic and Deterministic Motion Transfer for Image-To-Video Synthesis | Yang, Fu-En; Chang, Jing-Cheng; Lee, Yuan-Hao; Wang, Yu-Chiang Frank | National Taiwan University | Poster | PS T1.12 | DAY 3 – January 14, 2021 |
1878 | Fast Determination of Melanin Based on Skin Hyperspectral Reflectance | Li, Shiwei; Ardabilian, Mohsen; Zine, Abdelmalek | Ecole Centrale de Lyon | Poster | PS T5.2 | DAY 1 – January 12, 2021 |
1880 | Filtered Batch Normalization | Horváth, András; Al-Afandi, Jalal | Peter Pazmany Catholic Unviersity | Poster | PS T1.12 | DAY 3 – January 14, 2021 |
1883 | Trajectory Representation Learning for Multi-Task NMRDP Planning | Jarboui, Firas; Perchet, Vianney | ENS paris saclay; ANEO | Poster | PS T1.12 | DAY 3 – January 14, 2021 |
1884 | Facetwise Mesh Refinement for Multi-View Stereo | Romanoni, Andrea; Matteucci, Matteo | Politecnico di Milano | Oral | OS T3.3 – PS T3.5 | DAY 3 – January 14, 2021 – DAY 2 – January 13, 2021 |
1887 | Deep Fusion of RGB and NIR Paired Images Using Convolutional Neural Networks | Jung, Cheolkon | Xidian University | Poster | PS T5.5 | DAY 3 – January 14, 2021 |
1888 | Large-Scale Historical Watermark Recognition: Dataset and a New Consistency-Based Approach | Shen, Xi; Pastrolin, Ilaria; Bounou, Oumayma; Gidaris, Spyros; Smith, Marc; Poncet, Olivier; AUBRY, Mathieu | Ecole des Ponts ParisTech | Poster | PS T4.1 | DAY 1 – January 12, 2021 |
1889 | Learning Low-Shot Generative Networks for Cross-Domain Data | Kao, Hsuan-Kai; Lee, Cheng-Che; Chiu, Wei-Chen | National Chiao Tung University | Poster | PS T1.12 | DAY 3 – January 14, 2021 |
1893 | Edge-Guided CNN for Denoising Images from Portable Ultrasound Devices | Ma, Yingnan; Yang, Fei; Basu, Anup | University of Alberta | Poster | PS T5.1 | DAY 1 – January 12, 2021 |
1895 | A Two-Step Approach to Lidar-Camera Calibration | Su, Yingna; Ding, Yaqing; Yang, Jian; kong, hui | Nanjing University of Science and Technology | Poster | PS T3.7 | DAY 3 – January 14, 2021 |
1896 | RONELD: Robust Neural Network Output Enhancement for Active Lane Detection | Chng, Zhe Ming; Lew, Joseph Mun Hung; Lee, Jimmy Addison | Georgia Institute of Technology | Poster | PS T3.7 | DAY 3 – January 14, 2021 |
1897 | MEAN: A Multi-Element Attention based Network for Scene Text Recognition | Yan, Ruijie; Peng, Liangrui; Xiao, Shanyu; Yao, Gang; Min, Jaesik | Tsinghua University | Poster | PS T4.3 | DAY 3 – January 14, 2021 |
1899 | Quaternion Capsule Networks | Özcan, Bar; Knl, Furkan; Kirac, Mustafa Furkan | Özyeğin University | Poster | PS T1.12 | DAY 3 – January 14, 2021 |
1903 | Making Every Label Count: Handling Semantic Imprecision by Integrating Domain Knowledge | Brust, Clemens-Alexander; Barz, Björn; Denzler, Joachim | Friedrich Schiller University Jena | Poster | PS T1.15 | DAY 4 – January 15, 2021 |
1904 | Self-Supervised Domain Adaptation with Consistency Training | Xiao, Liang; Xu, Jiaolong; Zhao, Dawei; Wang, Zhiyu; Wang, Li; Nie, Yiming; Dai, Bin | Computer Vision Center | Poster | PS T1.15 | DAY 4 – January 15, 2021 |
1905 | GraphBGS: Background Subtraction Via Recovery of Graph Signals | Giraldo Zuluaga, Jhony Heriberto; Bouwmans, Thierry | University of La Rochelle | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
1907 | Spatial-Aware GAN for Unsupervised Person Re-identification | Zhan, Fangneng; Zhang, Changgong | Nanyang Technological University | Poster | PS T1.15 | DAY 4 – January 15, 2021 |
1914 | Semantic Segmentation for Pedestrian Detection from Motion in Temporal Domain | Cheng, Guo; Zheng, Jiang Yu | Indiana UniversityPurdue University Indianapolis | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
1920 | Occlusion-Tolerant and Personalized 3D Human Pose Estimation in RGB Images | Qammaz, Ammar; Argyros, Antonis | University of Crete | Poster | PS T3.2 | DAY 1 – January 12, 2021 |
1921 | How Important Are Faces for Person Re-Identification? | Dietlmeier, Julia; Antony, Joseph; McGuinness, Kevin; O’Connor, Noel E | Dublin City University | Poster | PS T1.15 | DAY 4 – January 15, 2021 |
1923 | EAGLE: Large-Scale Vehicle Detection Dataset in Real-World Scenarios Using Aerial Imagery | Azimi, Seyed Majid; Bahmanyar, Reza; Henry, Corentin; Franz, Kurz | German Aerospace Center (DLR) | Oral | OS T1.8 – PS T1.16 | DAY 4 – January 15, 2021 – DAY 4 – January 15, 2021 |
1925 | Mutually Guided Dual-Task Network for Scene Text Detection | Zhao, Mengbiao; Feng, Wei; Yin, Fei; Zhang, Xu-Yao; Liu, Cheng-Lin | Institution of Automation of Chinese Academy of Sciences | Oral | OS T 4.2 – PS T4.3 | DAY 4 – January 15, 2021 – DAY 3 – January 14, 2021 |
1926 | Visibility Restoration in Infra-Red Images | Fourt, Olivier; Tarel, Jean-Philippe | Univ. Gustave Eiffel | Poster | PS T5.4 | DAY 2 – January 13, 2021 |
1927 | Foreground-Focused Domain Adaption for Object Detection | Yang, Yuchen; Ray, Nilanjan | University of Alberta | Oral | OS T1.8 – PS T1.15 | DAY 4 – January 15, 2021 – DAY 4 – January 15, 2021 |
1931 | Transitional Asymmetric Non-Local Neural Networks for Real-World Dirt Road Segmentation | Wang, Yooseung; Park, Jihun | Agency for Defense Development | Poster | PS T3.7 | DAY 3 – January 14, 2021 |
1932 | Leveraging Sequential Pattern Information for Active Learning from Sequential Data | Fidalgo-Merino, Raul; Gabrielli, Lorenzo; Checchi, Enrico | European Commission, Joint Research Centre (JRC), Ispra, Italy | Poster | PS T1.15 | DAY 4 – January 15, 2021 |
1933 | To Honor Our Heroes: Analysis of the Obituaries of Australians Killed in Action in WWI and WWII | Cheong, Marc; Alfano, Mark | University of Melbourne | Poster | PS T4.2 | DAY 2 – January 13, 2021 |
1934 | Joint Face Alignment and 3D Face Reconstruction with Efficient Convolution Neural Networks | Li, Keqiang; Wu, Huaiyu; Shang, Xiuqin; Shen, Zhen; Xiong, Gang; Dong, Xisong; Hu, Bin; Wang, Fei-Yue | Chinese Academy of Sciences | Poster | PS T3.7 | DAY 3 – January 14, 2021 |
1937 | T-SVD Based Non-Convex Tensor Completion and Robust Principal Component Analysis | Li, Tao; Ma, Jinwen | Peking University | Poster | PS T1.15 | DAY 4 – January 15, 2021 |
1941 | On the Information of Feature Maps and Pruning of Deep Neural Networks | Soltani, Mohammadreza; Wu, Suya; Ding, Jie; Ravier, Robert; Tarokh, Vahid | Duke University | Poster | PS T1.12 | DAY 3 – January 14, 2021 |
1943 | Pose Variation Adaptation for Person Re-Identification | Zhang, Lei; Jiang, Na; Diao, Qishuai; Xu, Yue; Zhou, Zhong; Wu, Wei | State Key Lab of Virtual Reality Technology and Systems, Beihang University | Poster | PS T3.7 | DAY 3 – January 14, 2021 |
1946 | GazeMAE: General Representations of Eye Movements Using a Micro-Macro Autoencoder | Bautista, Louise Gillian C.; Naval, Prospero | University of the Philippines | Poster | PS T2.5 | DAY 4 – January 15, 2021 |
1947 | DFH-GAN: A Deep Face Hashing with Generative Adversarial Network | Zhou, Lanxiang; Wang, Yifei; Xiao, Bo; Xu, Qianfang | Beijing University of Posts and Telecommunications | Poster | PS T5.2 | DAY 1 – January 12, 2021 |
1948 | Towards Robust Learning with Different Label Noise Distributions | Ortego, Diego; Arazo, Eric; Albert, Paul; O’Connor, Noel E; McGuinness, Kevin | Dublin City University | Oral | OS T1.2 – PS T1.2 | DAY 1 – January 12, 2021 – DAY 1 – January 12, 2021 |
1950 | Tarsier: Evolving Noise Injection inSuper-Resolution GANs | Roziere, Baptiste; Rakotonirina, Nathanaël Carraz; Hosu, Vlad; Andry, Rasoanaivo; Lin, Hanhe; couprie, camille; Teytaud, Olivier | Facebook AI Research and Paris-Dauphine University | Poster | PS T5.2 | DAY 1 – January 12, 2021 |
1951 | Towards Explaining Adversarial Examples Phenomenon in Artificial Neural Networks | Barati, Ramin; Safabakhsh, Reza; Rahmati, Mohammad | University of Amirkabir | Poster | PS T1.15 |