Selecting Key Poses on Manifold for Pairwise Action Recognition
- 18 October 2011
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 8 (1) , 168-177
Abstract
In action recognition, bag of visual words based approaches have been shown to be successful, for which the quality of codebook is critical. In a large vocabulary of poses (visual words), some key poses play a more decisive role than others in the codebook. This paper proposes a novel approach for key poses selection, which models the descriptor space utilizing a manifold learning technique to recover the geometric structure of the descriptors on a lower dimensional manifold. A PageRank-based centrality measure is developed to select key poses according to the recovered geometric structure. In each step, a key pose is selected from the manifold and the remaining model is modified to maximize the discriminative power of selected codebook. With the obtained codebook, each action can be represented with a histogram of the key poses. To solve the ambiguity between some action classes, a pairwise subdivision is executed to select discriminative codebooks for further recognition. Experiments on benchmark datasets showed that our method is able to obtain better performance compared with other state-of-the-art methods.Keywords
This publication has 36 references indexed in Scilit:
- Human Action Recognition Using Manifold Learning and Hidden Conditional Random Fields2008
- Visual learning and recognition of sequential data manifolds with applications to human movement analysisComputer Vision and Image Understanding, 2008
- Statistical monitoring of fed-batch process using dynamic multiway neighborhood preserving embeddingChemometrics and Intelligent Laboratory Systems, 2008
- Learning Motion Categories using both Semantic and Structural Information2007
- Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words2006
- Hybrid Models for Human Motion Recognition2005
- Inferring 3D body pose from silhouettes using activity manifold learning2004
- Recognizing human actions: a local SVM approach2004
- Nonlinear Dimensionality Reduction by Locally Linear EmbeddingScience, 2000
- A Global Geometric Framework for Nonlinear Dimensionality ReductionScience, 2000