We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Meta-action descriptor for action recognition in RGBD video.
- Authors
Min Huang; Song-Zhi Su; Guo-Rong Cai; Hong-Bo Zhang; Donglin Cao; Shao-Zi Li
- 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.
- Subjects
HUMAN facial recognition software; COMPUTER vision; SEMANTIC Web; IMAGE analysis; COLOR image processing
- Publication
IET Computer Vision (Wiley-Blackwell), 2017, Vol 11, Issue 4, p301
- ISSN
1751-9632
- Publication type
Article
- DOI
10.1049/iet-cvi.2016.0252