Name:
Publisher version
View Source
Access full-text PDFOpen Access
View Source
Check access options
Check access options
Issue Date
2014-02-20Subjects
Laplacian group sparse codinghigh-level representation
structural information
action recognition
Metadata
Show full item recordAbstract
Recently, many local-feature based methods have been proposed for feature learning to obtain a better high-level representation of human behavior. Most of the previous research ignores the structural information existing among local features in the same video sequences, while it is an important clue to distinguish ambiguous actions. To address this issue, we propose a Laplacian group sparse coding for human behavior representation. Unlike traditional methods such as sparse coding, our approach prefers to encode a group of relevant features simultaneously and meanwhile allow as less atoms as possible to participate in the approximation so that video-level sparsity is guaranteed. By incorporating Laplacian regularization the method is capable to ensure the similar approximation of closely related local features and the structural information is successfully preserved. Thus, a compact but discriminative human behavior representation is achieved. Besides, the objective of our model is solved with a closed-form solution, which reduces the computational cost significantly. Promising results on several popular benchmark datasets prove the efficiency and effectiveness of our approach. © 2014 Elsevier Ltd.Citation
Zhang X, Yang H, Jiao LC, Yang Y, Dong F (2014) 'Laplacian group sparse modeling of human actions', Pattern Recognition, 47 (8), pp.2689-2701.Publisher
Elsevier LtdJournal
Pattern RecognitionType
ArticleLanguage
enISSN
0031-3203ae974a485f413a2113503eed53cd6c53
10.1016/j.patcog.2014.02.007