Cross Euclidean-to-Riemannian Metric Learning with Application to Face Recognition from Video

doi:10.1109/TPAMI.2017.2776154

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	Cross Euclidean-to-Riemannian Metric Learning with Application to Face Recognition from Video
	Wang, Ruiping 2; Chen, Xilin 2; Huang, Zhiwu 4; Van Gool, Luc 3,4; Shan, Shiguang 1,2
刊名	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
	2018-12-01
卷号	40 期号:12 页码:2827-2840
关键词	Riemannian manifold video-based face recognition cross Euclidean-to-Riemannian metric learning
ISSN号	0162-8828
DOI	10.1109/TPAMI.2017.2776154
英文摘要	Riemannian manifolds have been widely employed for video representations in visual classification tasks including video-based face recognition. The success mainly derives from learning a discriminant Riemannian metric which encodes the non-linear geometry of the underlying Riemannian manifolds. In this paper, we propose a novel metric learning framework to learn a distance metric across a Euclidean space and a Riemannian manifold to fuse average appearance and pattern variation of faces within one video. The proposed metric learning framework can handle three typical tasks of video-based face recognition: Video-to-Still, Still-to-Video and Video-to-Video settings. To accomplish this new framework, by exploiting typical Riemannian geometries for kernel embedding, we map the source Euclidean space and Riemannian manifold into a common Euclidean subspace, each through a corresponding high-dimensional Reproducing Kernel Hilbert Space (RKHS). With this mapping, the problem of learning a cross-view metric between the two source heterogeneous spaces can be converted to learning a single-view Euclidean distance metric in the target common Euclidean space. By learning information on heterogeneous data with the shared label, the discriminant metric in the common space improves face recognition from videos. Extensive experiments on four challenging video face databases demonstrate that the proposed framework has a clear advantage over the state-of-the-art methods in the three classical video-based face recognition scenarios.
资助项目	973 Program[2015CB351802] ; Natural Science Foundation of China[61390511] ; Natural Science Foundation of China[61379083] ; Natural Science Foundation of China[61650202] ; Natural Science Foundation of China[61402443] ; Natural Science Foundation of China[61672496] ; Frontier Science Key Research Project CAS[QYZDJ-SSW-JSC009] ; Youth Innovation Promotion Association CAS[2015085]
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE COMPUTER SOC
WOS记录号	WOS:000449355500003
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/4331]
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Shan, Shiguang
作者单位	1.CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 3.Katholieke Univ Leuven, VIS Lab, B-3000 Leuven, Belgium 4.Swiss Fed Inst Technol, Comp Vis Lab, CH-8092 Zurich, Switzerland
推荐引用方式 GB/T 7714	Wang, Ruiping,Chen, Xilin,Huang, Zhiwu,et al. Cross Euclidean-to-Riemannian Metric Learning with Application to Face Recognition from Video[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2018,40(12):2827-2840.
APA	Wang, Ruiping,Chen, Xilin,Huang, Zhiwu,Van Gool, Luc,&Shan, Shiguang.(2018).Cross Euclidean-to-Riemannian Metric Learning with Application to Face Recognition from Video.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,40(12),2827-2840.
MLA	Wang, Ruiping,et al."Cross Euclidean-to-Riemannian Metric Learning with Application to Face Recognition from Video".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 40.12(2018):2827-2840.