Bootstrapping Joint Bayesian Model for Robust Pace Verification

CORC > 重庆绿色智能技术研究院 > 中国科学院重庆绿色智能技术研究院 > 智能安全技术研究中心

	Bootstrapping Joint Bayesian Model for Robust Pace Verification
	Cheng, Cheng; Xing, Junliang; Feng, Youji; Li, Deling; Zhou, Xiang-Dong
	2016
会议日期	JUN 13-16, 2016
会议地点	Halmstad Univ, Halmstad, SWEDEN
通讯作者	Cheng, C (reprint author), Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Beijing 100864, Peoples R China.
英文摘要	Generative Bayesian models have exhibited good performance on the face verification problem, i.e., determining whether two faces are from the same person. As one of the most representative methods, the Joint Bayesian (JB) model represents two faces jointly by introducing some appropriate priors, providing better separability between different face classes. The EM-like learning algorithm of the JB model, however, are occasionally observed to have unsatisfactory converge property during the iterative training process. In this paper, we present a Bootstrapping Joint Bayesian (BJB) model which demonstrates good converging behavior. The BJB model explicitly addresses the classification difficulties of different classes by gradually re weighting the training samples and driving the Bayesian models to pay more attentions to the hard training samples. Experiments on a new challenging benchmark demonstrate promising results of the proposed model, compared to the baseline Bayesian models.
会议录	2016 INTERNATIONAL CONFERENCE ON BIOMETRICS (ICB)
语种	英语
ISSN号	2376-4201
WOS记录号	WOS:000390841200042
内容类型	会议论文
源URL	[http://119.78.100.138/handle/2HOD01W0/379]
专题	智能安全技术研究中心
作者单位	(1) Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Beijing 100864, Peoples R China; (2) Chinese Acad Sci, Inst Automat, Beijing 100864, Peoples R China
推荐引用方式 GB/T 7714	Cheng, Cheng,Xing, Junliang,Feng, Youji,et al. Bootstrapping Joint Bayesian Model for Robust Pace Verification[C]. 见:. Halmstad Univ, Halmstad, SWEDEN. JUN 13-16, 2016.