Oral

Region-of-Interest based Neural Video Compression
Humans do not perceive all parts of a scene with the same resolution, but rather focus on few regions of interest (ROIs). Traditional …
Yura Perugachi-Diaz, Guillaume Sautiere, Davide Abati, Yang Yang, Amirhossein Habibian, Taco S Cohen
PDF Cite
Region-of-Interest based Neural Video Compression
Frame-Exit: Conditional Early Exiting for Efficient Video Recognition
In this paper, we propose a conditional early exiting framework for efficient video recognition. While existing works focus on …
Amir Ghodrati, Babak Ehteshami Bejnordi, Amirhossein Habibian
PDF Cite Code
Frame-Exit: Conditional Early Exiting for Efficient Video Recognition
Videostory: A New Multimedia Embedding for Few-Example Recognition and Translation of Events
This paper proposes a data-driven approach for cross-media retrieval by automatically learning its underlying semantic vocabulary. …
Amirhossein Habibian, Thomas Mensink, Cees GM Snoek
PDF Cite
Videostory: A New Multimedia Embedding for Few-Example Recognition and Translation of Events
Composite Concept Discovery for Zero-shot Video Event Detection
R We consider automated detection of events in video without the use of any visual training examples. A common approach is to represent …
Amirhossein Habibian, Thomas Mensink, Cees GM Snoek
PDF Cite
Composite Concept Discovery for Zero-shot Video Event Detection
Recommendations for Video Event Recognition using Concept Vocabularies
Representing videos using vocabularies composed of concept detectors appears promising for event recognition. While many have recently …
Amirhossein Habibian, Koen EA van de Sande, Cees GM Snoek
PDF Cite
Recommendations for Video Event Recognition using Concept Vocabularies