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...

• Type: Conference
• Year: 2009
• Where: ICCV
• Authors: Zhe Lin, Zhuolin Jiang, Larry S. Davis
• Keywords: Computer Vision, ICCV 2009, Shape-Motion Prototype Trees