Selecting Key Poses on Manifold for Pairwise Action Recognition

CORC > 西安光学精密机械研究所 > 中国科学院西安光学精密机械研究所 > 光学影像学习与分析中心

	Selecting Key Poses on Manifold for Pairwise Action Recognition
	Cao, Xianbin 1,2; Ning, Bo 1; Yan, Pingkun 3; Li, Xuelong 3
刊名	ieee transactions on industrial informatics
	2012-02-01
卷号	8 期号:1 页码:168-177
关键词	Action recognition bag of words centrality measure key poses manifold leaning
ISSN号	1551-3203
产权排序	3
合作状况	国内
英文摘要	in action recognition, bag of visual words based approaches have been shown to be successful, for which the quality of codebook is critical. in a large vocabulary of poses (visual words), some key poses play a more decisive role than others in the codebook. this paper proposes a novel approach for key poses selection, which models the descriptor space utilizing a manifold learning technique to recover the geometric structure of the descriptors on a lower dimensional manifold. a pagerank-based centrality measure is developed to select key poses according to the recovered geometric structure. in each step, a key pose is selected from the manifold and the remaining model is modified to maximize the discriminative power of selected codebook. with the obtained codebook, each action can be represented with a histogram of the key poses. to solve the ambiguity between some action classes, a pairwise subdivision is executed to select discriminative codebooks for further recognition. experiments on benchmark datasets showed that our method is able to obtain better performance compared with other state-of-the-art methods.
学科主题	automation & control systems ; computer science ; interdisciplinary applications ; engineering ; industrial
WOS标题词	science & technology ; technology
类目[WOS]	automation & control systems ; computer science, interdisciplinary applications ; engineering, industrial
研究领域[WOS]	automation & control systems ; computer science ; engineering
关键词[WOS]	nonlinear dimensionality reduction ; human motion ; human movement
收录类别	SCI ; EI
语种	英语
WOS记录号	WOS:000299526800019
公开日期	2012-09-03
内容类型	期刊论文
源URL	[http://ir.opt.ac.cn/handle/181661/20248]
专题	西安光学精密机械研究所_光学影像学习与分析中心
作者单位	1.Univ Sci & Technol China, Hefei 230026, Peoples R China 2.BeiHang Univ, Beijing 100083, Peoples R China 3.Chinese Acad Sci, Ctr Opt Imagery Anal & Learning, State Key Lab Transient Opt & Photon, Xian Inst Opt & Precis Mech, Xian 710119, Peoples R China
推荐引用方式 GB/T 7714	Cao, Xianbin,Ning, Bo,Yan, Pingkun,et al. Selecting Key Poses on Manifold for Pairwise Action Recognition[J]. ieee transactions on industrial informatics,2012,8(1):168-177.
APA	Cao, Xianbin,Ning, Bo,Yan, Pingkun,&Li, Xuelong.(2012).Selecting Key Poses on Manifold for Pairwise Action Recognition.ieee transactions on industrial informatics,8(1),168-177.
MLA	Cao, Xianbin,et al."Selecting Key Poses on Manifold for Pairwise Action Recognition".ieee transactions on industrial informatics 8.1(2012):168-177.