Discovering latent attributes for human action recognition in depth sequence. Issue 20 (1st September 2014)

• Record Type: Journal Article
• Authors: Su, Yuting; Jia, Pingping; Liu, An‐An; Yang, Zhaoxuan
• Is Part Of: Electronics letters. Volume 50:Issue 20(2014)
• Page Start: 1436
• Page End: 1438
• Publication Date: 2014-09-01
• Subjects: image sequences -- object recognition -- solid modelling; latent attribute discovery -- human action recognition -- depth sequence -- latent attribute model -- LAM -- bodywise action attributes -- partwise action attributes -- action modelling -- hidden layer design -- graphical structure; Electronics -- Periodicals; 621.381
• DOI: 10.1049/el.2014.1316
• Languages: English
• ISSNs: 0013-5194

Abstract

Abstract : A method for human action recognition in depth sequence by discovering latent attributes is proposed. Specifically, a latent attribute model to take advantage of the partwise and bodywise action attributes and their concurrence for action modelling is presented. This model can avoid the explicit definition of a completed action attribute set by designing a hidden layer as latent attributes. Moreover, the relationship between pairwise attributes can be adaptively learned in terms of the specific graphical structure without human intervention. Extensive experiments on two popular datasets and a new dataset TJU show the superiority of the proposed method over the state‐of‐the‐arts.