Author Archives: admin

Book on Multimodal Behavior Analysis in the Wild published!

The book “Multimodal Behavior Analysis in the Wild“, Edited by Xavier Alameda-Pineda, Elisa Ricci and Nicu Sebe has now been published. We contributed a chapter on “Wearable systems for improving tourist experience” which gathers and extends our contribution on context … Continue reading

Posted in Uncategorized | Comments Off on Book on Multimodal Behavior Analysis in the Wild published!

ICPR 2018 Paper Accepted

Our work on adaptive compression for object detection algorithms has been accepted for publication at ICPR 2018.  Video compression algorithms have been designed aiming at pleasing human viewers, and are driven by video quality metrics that are designed to account for the … Continue reading

Posted in Uncategorized | Comments Off on ICPR 2018 Paper Accepted

ICCV ’17 Paper Accepted!

Our paper on Deep Generative Adversarial Compression Artifact Removal, has been accepted for publication at ICCV 2017.  In the following figure we can see how our GAN can recover details in a compressed image (left). Note how texture and edges … Continue reading

Posted in Uncategorized | Comments Off on ICCV ’17 Paper Accepted!

Indexing Quantized Ensembles of Exemplar-SVMs with Rejecting Taxonomies accepted in Multimedia Tools and Applications

Ensembles of Exemplar-SVMs have been introduced as a framework for Object Detection but have rapidly found a large interest in a wide variety of computer vision applications such as mid-level feature learning, tracking and segmentation. To guarantee its effectiveness though, … Continue reading

Posted in Uncategorized | Comments Off on Indexing Quantized Ensembles of Exemplar-SVMs with Rejecting Taxonomies accepted in Multimedia Tools and Applications

Spatio-Temporal Closed-Loop approach published on IEEE Transaction on Image Processing

Object detection is one of the most important tasks of computer vision. It is usually performed evaluating locations of an image that are more likely to contain the object of interest. The interplay of detectors and proposal algorithms has not … Continue reading

Posted in Uncategorized | Comments Off on Spatio-Temporal Closed-Loop approach published on IEEE Transaction on Image Processing

Action Localization based on Clustered Trajectories published on Computer Vision and Image Understanding

Our representation allows to perform partial matching between videos obtaining a robust similarity measure. This approach is extremely useful in sport videos where multiple entities are involved in the activities. Many existing works perform person detection, tracking and often require … Continue reading

Posted in Uncategorized | Comments Off on Action Localization based on Clustered Trajectories published on Computer Vision and Image Understanding

About me

I received a Laurea degree in computer engineering (MSc) from the University of Florence, with a thesis on human action recognition in 2008. I obtained my PhD degree working at the Media Integration and Communication Center of University of Florence under the supervision of … Continue reading

Posted in Uncategorized | Leave a comment