Meta‐action descriptor for action recognition in RGBD video. Issue 4 (7th March 2017)

• Record Type: Journal Article
• Authors: Huang, Min; Su, Song‐Zhi; Cai, Guo‐Rong; Zhang, Hong‐Bo; Cao, Donglin; Li, Shao‐Zi
• Is Part Of: IET computer vision. Volume 11:Issue 4(2017)
• Page Start: 301
• Page End: 308
• Publication Date: 2017-03-07
• Subjects: gesture recognition -- computer vision -- image colour analysis -- video signal processing; meta-action descriptor -- action recognition -- RGBD video -- computer vision -- local video features -- global video features -- discrimination-based strategies -- discriminative part clustering -- dynamic part clustering -- MSR action dataset; Computer vision -- Periodicals; Pattern recognition systems -- Periodicals; 006.37
• DOI: 10.1049/iet-cvi.2016.0252
• Languages: English
• ISSNs: 1751-9632

Abstract

Abstract : Action recognition is one of the hottest research topics in computer vision. Recent methods represent actions based on global or local video features. These approaches, however, lack semantic structure and may not provide a deep insight into the essence of an action. In this work, the authors argue that semantic clues, such as joint positions and part‐level motion clustering, help verify actions. To this end, a meta‐action descriptor for action recognition in RGBD video is proposed in this study. Specifically, two discrimination‐based strategies – dynamic and discriminative part clustering – are introduced to improve accuracy. Experiments conducted on the MSR Action 3D dataset show that the proposed method significantly outperforms the methods without joint position semantic.