Computer Vision, IEEE International Conference on (2011)
Nov. 6, 2011 to Nov. 13, 2011
Tian Lan , School of Computing Science, Simon Fraser University, Canada
Yang Wang , Dept. of Computer Science, UIUC, USA
Greg Mori , School of Computing Science, Simon Fraser University, Canada
In this paper we develop an algorithm for action recognition and localization in videos. The algorithm uses a figure-centric visual word representation. Different from previous approaches it does not require reliable human detection and tracking as input. Instead, the person location is treated as a latent variable that is inferred simultaneously with action recognition. A spatial model for an action is learned in a discriminative fashion under a figure-centric representation. Temporal smoothness over video sequences is also enforced. We present results on the UCF-Sports dataset, verifying the effectiveness of our model in situations where detection and tracking of individuals is challenging.
G. Mori, Tian Lan and Yang Wang, "Discriminative figure-centric models for joint action localization and recognition," 2011 IEEE International Conference on Computer Vision (ICCV 2011)(ICCV), Barcelona, 2011, pp. 2003-2010.