Multi-Task GANs for View-Specific Feature Learning in Gait Recognition

doi:10.1109/TIFS.2018.2844819

CASIA OpenIR > 智能感知与计算研究中心

	Multi-Task GANs for View-Specific Feature Learning in Gait Recognition
	He, Yiwei 1,2; Zhang, Junping 1,2; Shan, Hongming 3; Wang, Liang4
发表期刊	IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
	2019
卷号	14 期号:1 页码:102-113
文章类型	Article
摘要	Gait recognition is of great importance in the fields of surveillance and forensics to identify human beings since gait is the unique biometric feature that can be perceived efficiently at a distance. However, the accuracy of gait recognition to some extent suffers from both the variation of view angles and the deficient gait templates. On one hand, the existing cross-view methods focus on transforming gait templates among different views, which may accumulate the transformation error in a large variation of view angles. On the other hand, a commonly used gait energy image template loses temporal information of a gait sequence. To address these problems, this paper proposes multi-task generative adversarial networks (MGANs) for learning view-specific feature representations. In order to preserve more temporal information, we also propose a new multi-channel gait template, called period energy image (PEI). Based on the assumption of view angle manifold, the MGANs can leverage adversarial training to extract more discriminative features from gait sequences. Experiments on OU-ISIR, CASIA-B, and USF benchmark data sets indicate that compared with several recently published approaches, PEI + MGANs achieves competitive performance and is more interpretable to cross-view gait recognition.
关键词	Gait Recognition Cross-view Generative Adversarial Networks Surveillance
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TIFS.2018.2844819
关键词[WOS]	HUMAN IDENTIFICATION ; PERFORMANCE
收录类别	SCI
语种	英语
项目资助者	National Natural Science Foundation of China(61673118) ; Shanghai Pujiang Program(16PJD009)
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000440782400002
引用统计	被引频次：134[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/173211/21841
专题	智能感知与计算研究中心
作者单位	1.Fudan Univ, Shanghai Key Lab Intelligent Informat Proc, Shanghai 200433, Peoples R China 2.Fudan Univ, Sch Comp Sci, Shanghai 200433, Peoples R China 3.Rensselaer Polytech Inst, Dept Biomed Engn, Ctr Biotechnol & Interdisciplinary Studies, Troy, NY 12180 USA 4.Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Percept & Comp, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	He, Yiwei,Zhang, Junping,Shan, Hongming,et al. Multi-Task GANs for View-Specific Feature Learning in Gait Recognition[J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,2019,14(1):102-113.
APA	He, Yiwei,Zhang, Junping,Shan, Hongming,&Wang, Liang.(2019).Multi-Task GANs for View-Specific Feature Learning in Gait Recognition.IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,14(1),102-113.
MLA	He, Yiwei,et al."Multi-Task GANs for View-Specific Feature Learning in Gait Recognition".IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 14.1(2019):102-113.