Supervised spatio-temporal neighborhood topology learning for action recognition

doi:10.1109/TCSVT.2013.2248494

科研成果详情

题名	Supervised spatio-temporal neighborhood topology learning for action recognition
作者	Ma，Andy J.1; Yuen，Pong C.1,2; Zou，Wilman W.W.3; Lai，Jian Huang 4,5
发表日期	2013
发表期刊	IEEE Transactions on Circuits and Systems for Video Technology
ISSN/eISSN	1051-8215
卷号	23 期号:8 页码:1447-1460
摘要	Supervised manifold learning has been successfully applied to action recognition, in which class label information could improve the recognition performance. However, the learned manifold may not be able to well preserve both the local structure and global constraint of temporal labels in action sequences. To overcome this problem, this paper proposes a new supervised manifold learning algorithm called supervised spatio-temporal neighborhood topology learning (SSTNTL) for action recognition. By analyzing the topological characteristics in the context of action recognition, we propose to construct the neighborhood topology using both supervised spatial and temporal pose correspondence information. Employing the property in locality preserving projection (LPP), SSTNTL solves the generalized eigenvalue problem to obtain the best projections that not only separates data points from different classes, but also preserves local structures and temporal pose correspondence of sequences from the same class. Experimental results demonstrate that SSTNTL outperforms the manifold embedding methods with other topologies or local discriminant information. Moreover, compared with state-of-the-art action recognition algorithms, SSTNTL gives convincing performance for both human and gesture action recognition. © 1991-2012 IEEE.
关键词	Action recognition manifold learning neighborhood topology learning supervised spatial temporal pose correspondence
DOI	10.1109/TCSVT.2013.2248494
URL	查看来源
语种	英语English
Scopus入藏号	2-s2.0-84881405295
引用统计
文献类型	期刊论文
条目标识符	https://repository.uic.edu.cn/handle/39GCC9TT/6539
专题	北师香港浸会大学
作者单位	1.Department of Computer Science,Hong Kong Baptist University,Kowloon,Hong Kong 2.PBNU-HKBU United International College,Zhuhai,China 3.Institute of Computational Theoretical Studies,Hong Kong Baptist University,Kowloon,Hong Kong 4.School of Information Science and Technology,Sun Yat-Sen University,Guangzhou 510006,China 5.Guangdong Province Key Laboratory of Information Security,Guangzhou 510006,China
推荐引用方式 GB/T 7714	Ma，Andy J.,Yuen，Pong C.,Zou，Wilman W.W.et al. Supervised spatio-temporal neighborhood topology learning for action recognition[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2013, 23(8): 1447-1460.
APA	Ma，Andy J., Yuen，Pong C., Zou，Wilman W.W., & Lai，Jian Huang. (2013). Supervised spatio-temporal neighborhood topology learning for action recognition. IEEE Transactions on Circuits and Systems for Video Technology, 23(8), 1447-1460.
MLA	Ma，Andy J.,et al."Supervised spatio-temporal neighborhood topology learning for action recognition". IEEE Transactions on Circuits and Systems for Video Technology 23.8(2013): 1447-1460.