TY - GEN
T1 - Learning action dictionaries from video
AU - Turaga, Pavan
AU - Chellappa, Rama
N1 - Copyright:
Copyright 2009 Elsevier B.V., All rights reserved.
PY - 2008
Y1 - 2008
N2 - Summarizing the contents of a video containing human activities is an important problem in computer vision and has important applications in automated surveillance systems. Summarizing a video requires one to identify and learn a 'vocabulary' of action-phrases corresponding to specific events and actions occurring in the video. We propose a generative model for dynamic scenes containing human activities as a composition of independent action-phrases - each of which is derived from an underlying vocabulary. Given a long video sequence, we propose a completely unsupervised approach to learn the vocabulary. Once the vocabulary is learnt, a video segment can be decomposed into a collection of phrases for summarization. We then describe methods to learn the correlations between activities and sequentiality of events. We also propose a novel method for building invariances to spatial transforms in the summarization scheme.
AB - Summarizing the contents of a video containing human activities is an important problem in computer vision and has important applications in automated surveillance systems. Summarizing a video requires one to identify and learn a 'vocabulary' of action-phrases corresponding to specific events and actions occurring in the video. We propose a generative model for dynamic scenes containing human activities as a composition of independent action-phrases - each of which is derived from an underlying vocabulary. Given a long video sequence, we propose a completely unsupervised approach to learn the vocabulary. Once the vocabulary is learnt, a video segment can be decomposed into a collection of phrases for summarization. We then describe methods to learn the correlations between activities and sequentiality of events. We also propose a novel method for building invariances to spatial transforms in the summarization scheme.
KW - Activity analysis
KW - Video summarization
UR - http://www.scopus.com/inward/record.url?scp=69949123416&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=69949123416&partnerID=8YFLogxK
U2 - 10.1109/ICIP.2008.4712102
DO - 10.1109/ICIP.2008.4712102
M3 - Conference contribution
AN - SCOPUS:69949123416
SN - 1424417643
SN - 9781424417643
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 1704
EP - 1707
BT - 2008 IEEE International Conference on Image Processing, ICIP 2008 Proceedings
T2 - 2008 IEEE International Conference on Image Processing, ICIP 2008
Y2 - 12 October 2008 through 15 October 2008
ER -