Abstract
A novel method using the combination of spatio-temporal interest points and spatio-temporal shape contexts for human action description and retrieval is proposed. Both the feature points detection and description are invariant to geometric and photometric changes and intra-class variations. The experimental results show that the proposed descriptor is more effective than brightness gradients based motion descriptors for classifying and retrieving challenging human actions.
Original language | English |
---|---|
DOIs | |
Publication status | Published - 2009 |
Event | IMCE '09 - 1st International Workshop on Interactive Multimedia for Consumer Electronics - Beijing, China Duration: 1 Oct 2009 → … |
Workshop
Workshop | IMCE '09 - 1st International Workshop on Interactive Multimedia for Consumer Electronics |
---|---|
Period | 1/10/09 → … |
Keywords
- Motion descriptor
- spatio-temporal shape context
- action retrieval