The Community for Technology Leaders
Applications of Computer Vision, IEEE Workshop on (2013)
Clearwater Beach, FL, USA USA
Jan. 15, 2013 to Jan. 17, 2013
ISSN: 1550-5790
ISBN: 978-1-4673-5053-2
pp: 339-346
Jingen Liu , SRI International Sarnoff Princeton, NJ, USA 08540
Qian Yu , SRI International Sarnoff Princeton, NJ, USA 08540
Omar Javed , SRI International Sarnoff Princeton, NJ, USA 08540
Saad Ali , SRI International Sarnoff Princeton, NJ, USA 08540
Amir Tamrakar , SRI International Sarnoff Princeton, NJ, USA 08540
Ajay Divakaran , SRI International Sarnoff Princeton, NJ, USA 08540
Hui Cheng , SRI International Sarnoff Princeton, NJ, USA 08540
Harpreet Sawhney , SRI International Sarnoff Princeton, NJ, USA 08540
ABSTRACT
We propose to use action, scene and object concepts as semantic attributes for classification of video events in InTheWild content, such as YouTube videos. We model events using a variety of complementary semantic attribute features developed in a semantic concept space. Our contribution is to systematically demonstrate the advantages of this concept-based event representation (CBER) in applications of video event classification and understanding. Specifically, CBER has better generalization capability, which enables to recognize events with a few training examples. In addition, CBER makes it possible to recognize a novel event without training examples (i.e., zero-shot learning). We further show our proposed enhanced event model can further improve the zero-shot learning. Furthermore, CBER provides a straightforward way for event recounting/understanding. We use the TRECVID Multimedia Event Detection (MED11) open source event definitions and datasets as our test bed and show results on over 1400 hours of videos.
INDEX TERMS
Semantics, Detectors, Training, Vectors, Feature extraction, Kernel, Visualization
CITATION

J. Liu et al., "Video event recognition using concept attributes," Applications of Computer Vision, IEEE Workshop on(WACV), Clearwater Beach, FL, USA USA, 2013, pp. 339-346.
doi:10.1109/WACV.2013.6475038
95 ms
(Ver 3.3 (11022016))