A Coupled Hidden Markov Random Field model for simultaneous face clustering and tracking in videos

doi:10.1016/j.patcog.2016.10.022

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 多媒体计算与图形学团队

	A Coupled Hidden Markov Random Field model for simultaneous face clustering and tracking in videos
	Wu, Baoyuan 1,2; Hu, Bao-Gang1 ; Ji, Qiang 3
刊名	PATTERN RECOGNITION
	2017-04-01
卷号	64 期号:2 页码:361-373
关键词	Face Clustering Face Tracking Coupled Hidden Markov Random Field
DOI	10.1016/j.patcog.2016.10.022
文献子类	Article
英文摘要	Face clustering and face tracking are two areas of active research in automatic facial video processing. They, however, have long been studied separately, despite the inherent link between them. In this paper, we propose to perform simultaneous face clustering and face tracking from real world videos. The motivation for the proposed research is that face clustering and face tracking can provide useful information and constraints to each other, thus can bootstrap and improve the performances of each other. To this end, we introduce a Coupled Hidden Markov Random Field (CHMRF) to simultaneously model face clustering, face tracking, and their interactions. We provide an effective algorithm based on constrained clustering and optimal tracking for the joint optimization of cluster labels and face tracking. We demonstrate significant improvements over state-ofthe-art results in face clustering and tracking on several videos.
WOS研究方向	Computer Science ; Engineering
语种	英语
WOS记录号	WOS:000392682400029
资助机构	China Scholarship Council (CSC) ; CSC ; RPI ; US National Science Foundation (NSF)(1145152) ; National Natural Science Foundation of China (NSFC)(61273196 ; 61573348)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/14363]
专题	自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.King Abdullah Univ Sci & Technol, Visual Comp Ctr, Thuwal 239556900, Saudi Arabia 3.Rensselaer Polytech Inst, Dept Elect Comp & Syst Engn, Troy, NY 12180 USA
推荐引用方式 GB/T 7714	Wu, Baoyuan,Hu, Bao-Gang,Ji, Qiang. A Coupled Hidden Markov Random Field model for simultaneous face clustering and tracking in videos[J]. PATTERN RECOGNITION,2017,64(2):361-373.
APA	Wu, Baoyuan,Hu, Bao-Gang,&Ji, Qiang.(2017).A Coupled Hidden Markov Random Field model for simultaneous face clustering and tracking in videos.PATTERN RECOGNITION,64(2),361-373.
MLA	Wu, Baoyuan,et al."A Coupled Hidden Markov Random Field model for simultaneous face clustering and tracking in videos".PATTERN RECOGNITION 64.2(2017):361-373.