Sciweavers

Share
ICCV
2011
IEEE

Discriminative Figure-Centric Models for Joint Action Localization and Recognition

8 years 9 months ago
Discriminative Figure-Centric Models for Joint Action Localization and Recognition
In this paper we develop an algorithm for action recognition and localization in videos. The algorithm uses a figurecentric 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.
Tian Lan, Yang Wang, Greg Mori
Added 11 Dec 2011
Updated 11 Dec 2011
Type Journal
Year 2011
Where ICCV
Authors Tian Lan, Yang Wang, Greg Mori
Comments (0)
books