Semi-Supervised Tensor-Based Graph Embedding Learning and Its Application to Visual Discriminant Tracking

doi:10.1109/TPAMI.2016.2539944

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 视频内容安全

	Semi-Supervised Tensor-Based Graph Embedding Learning and Its Application to Visual Discriminant Tracking
	Hu, Weiming1 ; Gao, Jin1 ; Xing, Junliang1 ; Zhang, Chao1 ; Maybank, Stephen 2; Weiming Hu
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
	2017
卷号	39 期号:1 页码:172-188
文章类型	Article
摘要	An appearance model adaptable to changes in object appearance is critical in visual object tracking. In this paper, we treat an image patch as a two-order tensor which preserves the original image structure. We design two graphs for characterizing the intrinsic local geometrical structure of the tensor samples of the object and the background. Graph embedding is used to reduce the dimensions of the tensors while preserving the structure of the graphs. Then, a discriminant embedding space is constructed. We prove two propositions for finding the transformation matrices which are used to map the original tensor samples to the tensor-based graph embedding space. In order to encode more discriminant information in the embedding space, we propose a transfer-learning-based semi-supervised strategy to iteratively adjust the embedding space into which discriminative information obtained from earlier times is transferred. We apply the proposed semi-supervised tensor-based graph embedding learning algorithm to visual tracking. The new tracking algorithm captures an object's appearance characteristics during tracking and uses a particle filter to estimate the optimal object state. Experimental results on the CVPR 2013 benchmark dataset demonstrate the effectiveness of the proposed tracking algorithm.
关键词	Discriminant Tracking Tensor Samples Semi-supervised Learning Graph Embedding Space
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TPAMI.2016.2539944
关键词[WOS]	OBJECT TRACKING ; DIMENSIONALITY REDUCTION ; REPRESENTATION ; FRAMEWORK
收录类别	SCI
语种	英语
项目资助者	973 basic research program of China(2014CB349303) ; Natural Science Foundation of China(61472421 ; Strategic Priority Research Program of the CAS(XDB02070003) ; 61370185)
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000390421300015
引用统计	被引频次：35[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/11102
专题	多模态人工智能系统全国重点实验室_视频内容安全
通讯作者	Weiming Hu
作者单位	1.Chinese Acad Sci, CAS Ctr Excellence Brain Sci & Intelligence Techn, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China 2.Birkbeck Coll, Dept Comp Sci & Informat Syst, Malet St, London WC1E 7HX, England
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Hu, Weiming,Gao, Jin,Xing, Junliang,et al. Semi-Supervised Tensor-Based Graph Embedding Learning and Its Application to Visual Discriminant Tracking[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2017,39(1):172-188.
APA	Hu, Weiming,Gao, Jin,Xing, Junliang,Zhang, Chao,Maybank, Stephen,&Weiming Hu.(2017).Semi-Supervised Tensor-Based Graph Embedding Learning and Its Application to Visual Discriminant Tracking.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,39(1),172-188.
MLA	Hu, Weiming,et al."Semi-Supervised Tensor-Based Graph Embedding Learning and Its Application to Visual Discriminant Tracking".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 39.1(2017):172-188.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
PAMI16SSTrack.pdf（7133KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载