Video event recognition using concept attributes

• Published in: 2013 IEEE Workshop on Applications of Computer Vision (WACV) pp. 339 - 346
• Main Authors: Jingen Liu, Qian Yu, Javed, O., Ali, S., Tamrakar, A., Divakaran, A., Hui Cheng, Sawhney, H.
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01.01.2013
• Subjects: Classification; Computer vision; Detectors; Feature extraction; Kernel; Learning; Multimedia; Semantics; Training; Vectors; Video data; Visualization; Workshops
• ISBN: 9781467350532; 1467350532
• ISSN: 1550-5790; 1550-5790
• DOI: 10.1109/WACV.2013.6475038

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.