Manifold-constrained coding and sparse representation for human action recognition

详细信息    查看全文

• 作者：Xiangrong Zhang^a ; ^{xrzhang@mail.xidian.edu.cn}Author Vitae ; Yang Yang^a ; ^{smileyoyon@126.com}Author Vitae ; L.C. Jiao^aAuthor Vitae ; Feng Dong^bAuthor Vitae
• 关键词：Human action recognition ; Local manifold-constrained coding ; Sparse representation ; Bag-of-features model ; Spatio-temporal local features
• 刊名：Pattern Recognition
• 出版年：2013
• 出版时间：July, 2013
• 年：2013
• 卷：46
• 期：7
• 页码：1819-1831
• 全文大小：2071 K

文摘

Due to its various applications, human action recognition has been widely studied and achieved tremendous progress. However, how to learn an accurate and discriminative behavior representation based on the extracted features remains as a challenging problem. In this paper, we present an effective coding scheme that can discover the manifold structure of the learned features with an l₂-norm regularization. Coupled with a local constraint, the proposed coding scheme, which has an analytical solution can learn an accurate, compact and yet discriminative behavior representation. After the behavior representations are obtained, the action recognition problem is formulated as a sparse linear representation of an overcomplete dictionary constructed by labeled behavior representations. The same manifold l₂-norm regularization is also employed in this stage. The reconstruction error associated with each class is used for classification. Experimental results demonstrate the effectiveness of the proposed approach on several public datasets including various physical actions and facial expressions.