Putting poses on manifold for action recognition

OPT OpenIR > 空间光学技术研究室

	Putting poses on manifold for action recognition
	CaoXianbin; NingBo; YanPingkun; LiXuelong; Cao Xianbin
	2011
会议名称	21st IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2011
会议录名称	2011 IEEE International Workshop on Machine Learning for Signal Processing - Proceedings of MLSP 2011
会议日期	September 18, 2011 - September 21, 2011
会议地点	Beijing, China
出版地	445 Hoes Lane - P.O.Box 1331, Piscataway, NJ 08855-1331, United States
会议主办者	IEEE; IEEE Signal Processing Society
出版者	IEEE Computer Society
产权排序	3
摘要	In action recognition, bag of words based approaches have been shown to be successful, for which the quality of codebook is critical. This paper proposes a novel approach to select key poses for the codebook, which models the descriptor space utilizing manifold learning to recover the geometric structure of the descriptors on a lower dimensional manifold space. A PageRank based centrality measure is developed to select key poses on the manifold. In each step, a key pose is selected and the remaining model is modified to maximize the discriminative power of selected codebook. In classification, the ambiguity of each action couple is evaluated through cross validation. An additional subdivision will be executed for ambiguous pairs. Experiments on ut-tower dataset showed that our method is able to obtain better performance than the state-of-the-art methods.
关键词	Action Recognition Key Poses Bag Of Words Manifold Leaning Centrality Measure
作者部门	光学影像分析与学习中心
收录类别	EI
ISBN号	9781457716232
语种	英语
文献类型	会议论文
条目标识符	http://ir.opt.ac.cn/handle/181661/20116
专题	空间光学技术研究室
通讯作者	Cao Xianbin
推荐引用方式 GB/T 7714	CaoXianbin,NingBo,YanPingkun,et al. Putting poses on manifold for action recognition[C]. 445 Hoes Lane - P.O.Box 1331, Piscataway, NJ 08855-1331, United States:IEEE Computer Society,2011.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Putting poses on man（248KB）			限制开放	--	请求全文