SILHOUETTE-BASED VIEW-EMBEDDINGS FOR GAIT RECOGNITION UNDER MULTIPLE VIEWS

被引：21

作者：

Chai, Tianrui ^{[1
]}

Mei, Xinyu ^{[1
]}

Li, Annan ^{[1
]}

Wang, Yunhong ^{[1
]}

机构：

[1] Beihang Univ, Sch Comp Sci & Engn, State Key Lab Virtual Real Technol & Syst, Beijing 100191, Peoples R China

来源：

2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | 2021年

基金：

中国国家自然科学基金;

关键词：

Gait recognition; silhouette-based; view-embedding; cross-view; multi-task;

D O I：

10.1109/ICIP42928.2021.9506238

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Gait recognition under multiple views is an important computer vision and pattern recognition task. In the emerging convolutional neural network based approaches, the information of view angle is ignored to some extent. Instead of direct view estimation and training view-specific recognition models, we propose a compatible framework that can embed view information into existing architectures of gait recognition. The embedding is simply achieved by a selective projection layer. Experimental results on two large public datasets show that the proposed framework is very effective.

引用

页码：2319 / 2323

页数：5

共 24 条

[1]

[Anonymous], 2020, ACM MM, DOI DOI 10.1109/SCAM51674.2020.00011

[2] Coupled Bilinear Discriminant Projection for Cross-View Gait Recognition [J].

Ben, Xianye ;

Gong, Chen ;

Zhang, Peng ;

Yan, Rui ;

Wu, Qiang ;

Meng, Weixiao .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2020, 30 (03) :734-747

[3] Coupled Patch Alignment for Matching Cross-View Gaits [J].

Ben, Xianye ;

Gong, Chen ;

Zhang, Peng ;

Jia, Xitong ;

Wu, Qiang ;

Meng, Weixiao .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 28 (06) :3142-3157

[4]

Chao HQ, 2019, AAAI CONF ARTIF INTE, P8126

[5] Instance-aware Semantic Segmentation via Multi-task Network Cascades [J].

Dai, Jifeng ;

He, Kaiming ;

Sun, Jian .

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :3150-3158

[6] GaitPart: Temporal Part-based Model for Gait Recognition [J].

Fan, Chao ;

Peng, Yunjie ;

Cao, Chunshui ;

Liu, Xu ;

Hou, Saihui ;

Chi, Jiannan ;

Huang, Yongzhen ;

Li, Qing ;

He, Zhiqiang .

2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2020), 2020, :14213-14221

[7] Individual recognition using Gait Energy Image [J].

Han, J ;

Bhanu, B .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2006, 28 (02) :316-322

[8] Multi-Task GANs for View-Specific Feature Learning in Gait Recognition [J].

He, Yiwei ;

Zhang, Junping ;

Shan, Hongming ;

Wang, Liang .

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2019, 14 (01) :102-113

[9] View-Invariant Discriminative Projection for Multi-View Gait-Based Human Identification [J].

Hu, Maodi ;

Wang, Yunhong ;

Zhang, Zhaoxiang ;

Little, James J. ;

Huang, Di .

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2013, 8 (12) :2034-2045

[10] Recognizing Gaits Across Views Through Correlated Motion Co-Clustering [J].

Kusakunniran, Worapan ;

Wu, Qiang ;

Zhang, Jian ;

Li, Hongdong ;

Wang, Liang .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2014, 23 (02) :696-709

← 1 2 3 →