Show simple item record

dc.contributor.authorZhang, Xiangrong
dc.contributor.authorYang, Hao
dc.contributor.authorJiao, L.C.
dc.contributor.authorYang, Yang
dc.contributor.authorDong, Feng
dc.date.accessioned2020-08-17T08:40:54Z
dc.date.available2020-08-17T08:40:54Z
dc.date.issued2014-02-20
dc.identifier.citationZhang X, Yang H, Jiao LC, Yang Y, Dong F (2014) 'Laplacian group sparse modeling of human actions', Pattern Recognition, 47 (8), pp.2689-2701.en_US
dc.identifier.issn0031-3203
dc.identifier.doi10.1016/j.patcog.2014.02.007
dc.identifier.urihttp://hdl.handle.net/10547/624417
dc.description.abstractRecently, 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.en_US
dc.language.isoenen_US
dc.publisherElsevier Ltden_US
dc.relation.urlhttps://www.sciencedirect.com/science/article/abs/pii/S0031320314000594en_US
dc.rightsGreen - can archive pre-print and post-print or publisher's version/PDF
dc.subjectLaplacian group sparse codingen_US
dc.subjecthigh-level representationen_US
dc.subjectstructural informationen_US
dc.subjectaction recognitionen_US
dc.titleLaplacian group sparse modeling of human actionsen_US
dc.typeArticleen_US
dc.contributor.departmentXidian Universityen_US
dc.contributor.departmentUniversity of Bedfordshireen_US
dc.identifier.journalPattern Recognitionen_US
dc.date.updated2020-08-17T08:36:35Z
dc.description.note


Files in this item

Thumbnail
Name:
Publisher version

This item appears in the following Collection(s)

Show simple item record