Recognizing Actions by Shape-Motion Prototype Trees

11 years 11 months ago
Recognizing Actions by Shape-Motion Prototype Trees
A prototype-based approach is introduced for action recognition. The approach represents an action as a se- quence of prototypes for efficient and flexible action match- ing in long video sequences. During training, first, an ac- tion prototype tree is learned in a joint shape and motion space via hierarchical k-means clustering; then a look- up table of prototype-to-prototype distances is generated. During testing, based on a joint likelihood model of the actor location and action prototype, the actor is tracked while a frame-to-prototype correspondence is established by maximizing the joint likelihood, which is efficiently per- formed by searching the learned prototype tree; then ac- tions are recognized using dynamic prototype sequence matching. Distance matrices used for sequence matching are rapidly obtained by look-up table indexing, which is an order of magnitude faster than brute-force computation of frame-to-frame distances. Our approach enables ro- bust actio...
Zhe Lin, Zhuolin Jiang, Larry S. Davis
Added 13 Jul 2009
Updated 10 Jan 2010
Type Conference
Year 2009
Where ICCV
Authors Zhe Lin, Zhuolin Jiang, Larry S. Davis
Comments (0)