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.
|Publication status||Published - 2009|
|Event||IMCE '09 - 1st International Workshop on Interactive Multimedia for Consumer Electronics - Beijing, China|
Duration: 1 Jan 2009 → …
|Workshop||IMCE '09 - 1st International Workshop on Interactive Multimedia for Consumer Electronics|
|Period||1/01/09 → …|