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

Zheng, Feng, Shao, Ling, Song, Zhan and Chen, Xi (2011) Action recognition using graph embedding and the co-occurrence matrices descriptor. International Journal of Computer Mathematics, 88 (18). pp. 3896-3914. ISSN 0020-7160

Full text not available from this repository. (Request a copy)
Official URL:


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.

Item Type: Article
Uncontrolled Keywords: action recognition, graph embedding, co-occurrence matrices, human silhouette, bag of words, 68Txx, 68Uxx
Subjects: G400 Computer Science
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Related URLs:
Depositing User: Paul Burns
Date Deposited: 10 Jun 2015 15:44
Last Modified: 12 Oct 2019 22:30

Actions (login required)

View Item View Item


Downloads per month over past year

View more statistics