Learning latent temporal structure for complex event detection
Authors:
- 1 June 2012
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1250-1257
Abstract
In this paper, we tackle the problem of understanding the temporal structure of complex events in highly varying videos obtained from the Internet. Towards this goal, we utilize a conditional model trained in a max-margin framework that is able to automatically discover discriminative and interesting segments of video, while simultaneously achieving competitive accuracies on difficult detection and recognition tasks. We introduce latent variables over the frames of a video, and allow our algorithm to discover and assign sequences of states that are most discriminative for the event. Our model is based on the variable-duration hidden Markov model, and models durations of states in addition to the transitions between states. The simplicity of our model allows us to perform fast, exact inference using dynamic programming, which is extremely important when we set our sights on being able to process a very large number of videos quickly and efficiently. We show promising results on the Olympic Sports dataset [16] and the 2011 TRECVID Multimedia Event Detection task [18]. We also illustrate and visualize the semantic understanding capabilities of our model.Keywords
This publication has 23 references indexed in Scilit:
- Efficient additive kernels via explicit feature maps2010
- Weakly supervised discriminative localization and classification: a joint learning process2009
- Machine Recognition of Human Activities: A SurveyIEEE Transactions on Circuits and Systems for Video Technology, 2008
- Learning realistic human actions from movies2008
- Unsupervised Learning of Human Action Categories Using Spatial-Temporal WordsInternational Journal of Computer Vision, 2008
- Hidden Conditional Random FieldsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- Coupled Hidden Semi Markov Models for Activity Recognition2007
- Conditional models for contextual human motion recognitionComputer Vision and Image Understanding, 2006
- On Space-Time Interest PointsInternational Journal of Computer Vision, 2005
- Recognizing human actions: a local SVM approach2004