Session 1: Medical and Industrial Imaging

  • S1.1 Lung nodules segmentation in CT scans by DeepHealth toolkit
    Marco Aldinucci, Barbara Cantalupo, Iacopo Colonnelli, Marco Grangetto, Riccardo Renzulli, Enzo Tartaglione
    paper, additional material
  • S1.2 Machine learning for risk analysis of Urinary Tract Infection in people with dementia,
    Honglin Li, Payam Barnaghi, Severin Skillman, David Sharp, Ramin Nilforooshan, Helen Rostill
    paper
  • S1.3 Respiratory rate estimation using a low-resolution infrared sensor array
    Ouday Hanosh, Rashid Ansari, Yusuf Ozturk, A. Enis Cetin,
    paper, additional material
  • S1.5 Direct Motion Segmentation from Emulated Asynchronous Camera Events
    Andrew C. Freeman, Ketan Mayer-Patel, Montek Singh,
    paper, additional material
  • S1.6 A Fully Automated Process for Semiconductor Technology Analysis through SEM Cross-Sections
    Matthias Ludwig, Bernhard Lippmann, Ann-Christin Bette, Claus Lenz,
    paper, additional material
  • S1.7 BOE Digital Human: Visualize Your Life Data,
    Nan Liu, Chuan Wang, Xinyu Miao, Hua Bai, Yunan Wang, Limin Yang, Yiming Lei, Wei Zhang, Hong Wang
    paper

Session 2: Tracking, Detection and Surveillance

  • S2.1 Multimodal trajectory prediction in the CARLA simulator,
    Francesco Marchetti, Federico Becattini, Lorenzo Seidenari Alberto Del Bimbo
    paper, additional material
  • S2.2 Semantic Segmentation for Pedestrian Detection from Motion in Temporal Domain,
    Guo Cheng, Jiang Yu Zheng
    paper, additional material
  • S2.3 Suspicious Activity Detection,
    Yumna Zahid, Muhammad A. Tahir, Mohammad Samran Elahi, Mohsin Ali, and Muhammad N. Durrani
    paper
  • S2.4 Inter-Homines: Distance-Based Risk Estimation,
    Matteo Fabbri, Fabio Lanzi, Riccardo Gasparini, Simone Calderara, Lorenzo Baraldi and Rita Cucchiara
    paper, additional material
  • S2.5 Autonomous Platform based on Small-Scale Car for Versatile Data Collection and Algorithm Verification,
    Jakob Valtl, Javier Mendez, Manuel Pegalajar Cuellar, Vadim Issakov,
    paper
  • S2.6 Hardware-software Implementation of quantised Siamese Neural Networks for Energy Efficient Real-Time Object Tracking – a demo,
    Dominika Przewlocka-Rus, Daniel Gacek, Tomasz Kryjak,
    paper
  • S2.7 Deep Learning based video analytics solutions running on board of smart cameras,
    Vincenzo Carletti, Antonio Greco, Alessia Saggese, Mario Vento,
    paper

Session 3: Forensics and Biometrics

  • S3.1 Scalable, Person-Agnostic Deepfake Detection In the Wild
    Iacopo Masi, Kenneth Nadeau, Yash Doshi, Joe Mathai, Wael AbdAlmgaeed
    paper, additional material
  • S3.2 The Interplay of Speech and Lip Movements
    Prajwal K R, Rudrabha Mukhopadhyay, Sindhu Hegde, Vinay Namboodiri, C.V. Jawahar
    paper, additional material
  • S3.3 DeepFake Cracker: a novel tool for deepfake video detection
    Irene Amerini, Luca Maiano, Roberto Caldelli, Leonardo Galteri, Alberto del Bimbo
    paper
  • S3.4 Silhouette Body Measurement Benchmarks,
    Song Yan, Johan Wirta, Joni-Kristian Kamarainen,
    paper, additional material 1, additional material 2
  • S3.5 Cross-modal, Cross-domain Biometric Systems
    Ali Akbari, Ammarah Farooq, Syed Safwan Khalid, Chiho Chan, Junaid Awan, Zhenhua Feng, Tiangyang Xu, Soroush Fatemifar, Lei Ju, Muhammad Awais, Josef Kittler
    paper
  • S3.6 Children’s Online Arabic Handwriting Quality Evaluation & Analysis
    Hanen Akouaydi, Yahia Hamdi, Houcine Boubaker, Adel M. Alimi,
    paper, additional material
  • S3.7 Pipeline for XAI based Automatic Audio Call Audit
    Upasana Tiwari, Rupayan Chakraborty, Sumit Divolia, Sunil Kumar Kopparapu
    paper, additional material

Session 4: Machine Learning and Multimedia

  • S4.1 TimeAtlas – a Time Series Data Manipulation Tool for Python
    Fredéric Montet, Lorenz Rychener, Jean Hennebert, Jean-Philippe Bacher
    paper
  • S4.2 Structured Sparsity on Embedded Devices
    Enzo Tartaglione, Gianmarco Nuzzarello, Andrea Bragagnolo and Marco Grangetto
    paper, additional material
  • S4.3 XPlainIT – A demonstrator for explaining deep learning models trained over structured data
    Susan Mckeever, Ihsan Ullah, Andre Rios
    paper, additional material
  • S4.4
    From Tinkering to Engineering: Measurements in Tensorflow Playground
    Axel Harstad, Henrik Hoeiness, Gerald Friedland
    paper
  • S4.5 Two Demonstrations of the Machine Translation Applications to Historical Documents
    Miguel Domingo and Francisco Casacuberta
    paper
  • S4.5 Two Demonstrations of the Machine Translation Applications to Historical Documents
    Miguel Domingo and Francisco Casacuberta
    paper
  • S4.6 Data Collection for Contextual and Visual Question Answering in the Cultural Heritage Domain
    Francesco Vannoni, Pietro Bongini, Federico Becattini, Andrew David Bagdanov, Alberto Del Bimbo
    paper
  • S4.7 Creating automatic storytelling videos from still images: a semantically-aware approach
    Ines N. Teixeira, Paula Viana, Maria Teresa Andrade, Pedro Carvalho†, Luìs Vilac, Jose Pedro Pinto , Tiago Costa, Stamatis Rapanakis, Pieter P. Jonker
    paper