MULTI-LEVEL BASED PEDESTRIAN ATTRIBUTE RECOGNITION

被引：0

作者：

Yan, Hua-Rui ^{[1
]}

Zhan, Jin-Yu ^{[1
]}

Li, Fan ^{[1
]}

Zhang, Ting ^{[1
]}

Li, Na ^{[1
]}

Li, Zu-Ning ^{[1
]}

机构：

[1] Univ Elect Sci & Technol China, Sch Informat & Software Engn, Chengdu 611731, Peoples R China

来源：

2019 16TH INTERNATIONAL COMPUTER CONFERENCE ON WAVELET ACTIVE MEDIA TECHNOLOGY AND INFORMATION PROCESSING (ICWAMTIP) | 2019年

关键词：

Pedestrian Attribute Recognition; Multi-level Learning; Multi-label Classification;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Pedestrian attribute recognition is a challenging task in computer vision due to its multi-label nature. Many algorithms have been proposed to solve this problem, but a better one is still needed. In this paper, we propose an effective and novel method. Given a multi-label pedestrian image, our Multi-level Aggregate Network (MAN) generates feature maps at three different levels and aggregates three predictions as final output. The proposed network is trained in an end-to-end manner with only image-level annotations. Extensive experiments are performed on the two largest pedestrian attribute datasets i.e. the PETA dataset and PA-100K dataset. We achieve state-of-theart results without other information.

引用

页码：166 / 169

页数：4

共 14 条

[1] Multi-Task CNN Model for Attribute Prediction [J].

Abdulnabi, Abrar H. ;

Wang, Gang ;

Lu, Jiwen ;

Jia, Kui .

IEEE TRANSACTIONS ON MULTIMEDIA, 2015, 17 (11) :1949-1959

[2]

Bourdev L, 2011, IEEE I CONF COMP VIS, P1543, DOI 10.1109/ICCV.2011.6126413

[3] Describing Clothing by Semantic Attributes [J].

Chen, Huizhong ;

Gallagher, Andrew ;

Girod, Bernd .

COMPUTER VISION - ECCV 2012, PT III, 2012, 7574 :609-623

[4] Pedestrian Attribute Recognition At Far Distance [J].

Deng, Yubin ;

Luo, Ping ;

Loy, Chen Change ;

Tang, Xiaoou .

PROCEEDINGS OF THE 2014 ACM CONFERENCE ON MULTIMEDIA (MM'14), 2014, :789-792

[5] DeepCAMP: Deep Convolutional Action & Attribute Mid-Level Patterns [J].

Diba, Ali ;

Pazandeh, Ali Mohammad ;

Pirsiavash, Hamed ;

Gool, Luc Van .

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :3557-3565

[6]

Li DW, 2015, PROCEEDINGS 3RD IAPR ASIAN CONFERENCE ON PATTERN RECOGNITION ACPR 2015, P111, DOI 10.1109/ACPR.2015.7486476

[7] Human Attribute Recognition by Deep Hierarchical Contexts [J].

Li, Yining ;

Huang, Chen ;

Loy, Chen Change ;

Tang, Xiaoou .

COMPUTER VISION - ECCV 2016, PT VI, 2016, 9910 :684-700

[8]

Liu P., 2018, Localization guided learning for pedestrian attribute recognition

[9] HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis [J].

Liu, Xihui ;

Zhao, Haiyu ;

Tian, Maoqing ;

Sheng, Lu ;

Shao, Jing ;

Yi, Shuai ;

Yan, Junjie ;

Wang, Xiaogang .

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, :350-359

[10] Deep Imbalanced Attribute Classification Using Visual Attention Aggregation [J].

Sarafianos, Nikolaos ;

Xu, Xiang ;

Kakadiaris, Ioannis A. .

COMPUTER VISION - ECCV 2018, PT XI, 2018, 11215 :708-725

← 1 2 →