Black Re-ID: A Head-shoulder Descriptor for the Challenging Problem of Person Re-Identification

被引:29
作者
Xu, Boqiang [1 ,4 ]
He, Lingxiao [2 ]
Liao, Xingyu [2 ]
Liu, Wu [2 ]
Sun, Zhenan [3 ]
Mei, Tao [2 ]
机构
[1] Univ Chinese Acad Sci, Beijing, Peoples R China
[2] AI Res JD Com, Shanghai, Peoples R China
[3] Chinese Acad Sci, Inst Automat, Beijing, Peoples R China
[4] JD AI Res, Shanghai, Peoples R China
来源
MM '20: PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA | 2020年
基金
中国国家自然科学基金;
关键词
Black person re-identification; Head-shoulder descriptor; Adaptive attention; NETWORK;
D O I
10.1145/3394171.3414056
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Person re-identification (Re-ID) aims at retrieving an input person image from a set of images captured by multiple cameras. Although recent Re-ID methods have made great success, most of them extract features in terms of the attributes of clothing (e.g., color, texture). However, it is common for people to wear black clothes or be captured by surveillance systems in low light illumination, in which cases the attributes of the clothing are severely missing. We call this problem the Black Re-ID problem. To solve this problem, rather than relying on the clothing information, we propose to exploit head-shoulder features to assist person Re-ID. The head-shoulder adaptive attention network (HAA) is proposed to learn the head-shoulder feature and an innovative ensemble method is designed to enhance the generalization of our model. Given the input person image, the ensemble method would focus on the head-shoulder feature by assigning a larger weight if the individual insides the image is in black clothing. Due to the lack of a suitable benchmark dataset for studying the Black Re-ID problem, we also contribute the first Black-reID dataset, which contains 1274 identities in training set. Extensive evaluations on the Black-reID, Market1501 and DukeMTMC-reID datasets show that our model achieves the best result compared with the state-of-the-art Re-ID methods on both Black and conventional Re-ID problems. Furthermore, our method is also proved to be effective in dealing with person Re-ID in similar clothing. Our code and dataset are avaliable on https://github.com/xbq1994/.
引用
收藏
页码:673 / 681
页数:9
相关论文
共 42 条
[1]   Deep-Person: Learning discriminative deep features for person Re-Identification [J].
Bai, Xiang ;
Yang, Mingkun ;
Huang, Tengteng ;
Dou, Zhiyong ;
Yu, Rui ;
Xu, Yongchao .
PATTERN RECOGNITION, 2020, 98
[2]  
Deng J, 2009, PROC CVPR IEEE, P248, DOI 10.1109/CVPRW.2009.5206848
[3]  
Gu Yinzheng, 2018, ARXIV ABS181100202
[4]   Deep Residual Learning for Image Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778
[5]   Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-free Approach [J].
He, Lingxiao ;
Liang, Jian ;
Li, Haiqing ;
Sun, Zhenan .
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :7073-7082
[6]  
He Lingxiao, 2019, Computer Vision and Pattern Recognition
[7]  
Hermans A., 2017, ARXIV ABS170307737
[8]  
Jaderberg M, 2015, ADV NEUR IN, V28
[9]   Human Semantic Parsing for Person Re-identification [J].
Kalayeh, Mahdi M. ;
Basaran, Emrah ;
Gokmen, Muhittin ;
Kamasak, Mustafa E. ;
Shah, Mubarak .
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :1062-1071
[10]  
Kingma DP., 2014, ACS SYM SER