Action recognition using graph embedding and the co-occurrence matrices descriptor

Abstract

Recognizing actions from a monocular video is a very hot topic in computer vision recently. In this paper, we propose a new representation of actions, the co-occurrence matrices descriptor, on the intrinsic shape manifold learned by graph embedding. The co-occurrence matrices descriptor captures more temporal information than the bag of words (histogram) descriptor which only considers the spatial information, thus boosting the classification accuracy. In addition, we compare the performance of the co-occurrence matrices descriptor on different manifolds learned by various graph-embedding methods. Graph-embedding methods preserve as much of the significant structure of the high-dimensional data as possible in the low-dimensional map. The results show that nonlinear algorithms are more robust than linear ones. Furthermore, we conclude that the label information plays a critical role in learning more discriminating manifolds.

Keywords:

• action recognition
• graph embedding
• co-occurrence matrices
• human silhouette
• bag of words

2010 AMS Subject Classifications :

• 68Txx
• 68Uxx

Acknowledgements

The work described in this article was supported partially by the grants from the National Natural Science Foundation of China (NSFC, grant nos. 61002040, 60903115) and partially by NSFC-GuangDong (grant no. 10171782619-2000007).