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

被引:25
|
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 50 条
  • [1] Sparse Re-Id: Block Sparsity for Person Re-Identification
    Karanam, Srikrishna
    Li, Yang
    Radke, Richard J.
    2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2015,
  • [2] TransPose Re-ID: transformers for pose invariant person Re-identification
    Perwaiz, Nazia
    Shahzad, Muhammad
    Fraz, Muhammad Moazam
    JOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE, 2023,
  • [3] Open Set Person Re-identification Framework on Closed Set Re-Id Systems
    Vidanapathirana, Madhawa
    Sudasingha, Imesha
    Kanchana, Pasindu
    Vidanapathirana, Jayan
    Perera, Indika
    2017 IEEE 2ND INTERNATIONAL CONFERENCE ON SIGNAL AND IMAGE PROCESSING (ICSIP), 2017, : 66 - 71
  • [4] TrADe Re-ID - Live Person Re-Identification using Tracking and Anomaly Detection
    Machaca, Luigy
    Oliver Sumari H, F.
    Huaman, Jose
    Clua, Esteban
    Guerin, Joris
    2022 21ST IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS, ICMLA, 2022, : 449 - 454
  • [5] Color-Unrelated Head-Shoulder Networks for Fine-Grained Person Re-identification
    Xu, Boqiang
    Liang, Jian
    He, Lingxiao
    Wu, Jinlin
    Fan, Chao
    Sun, Zhenan
    ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2023, 19 (06)
  • [6] Multi-Pose Learning based Head-Shoulder Re-identification
    Li, Jia
    Zhai, Yunpeng
    Wang, Yaowei
    Shi, Yemin
    Tian, Yonghong
    IEEE 1ST CONFERENCE ON MULTIMEDIA INFORMATION PROCESSING AND RETRIEVAL (MIPR 2018), 2018, : 238 - 243
  • [7] Hierarchical Gaussian Descriptor for Person Re-Identification
    Matsukawa, Tetsu
    Okabe, Takahiro
    Suzuki, Einoshin
    Sato, Yoichi
    2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 1363 - 1372
  • [8] Event-driven Re-Id: A New Benchmark and Method Towards Privacy-Preserving Person Re-Identification
    Ahmad, Shafiq
    Scarpellini, Gianluca
    Morerio, Pietro
    Del Bue, Alessio
    2022 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WORKSHOPS (WACVW 2022), 2022, : 459 - 468
  • [9] Attention-disentangled re-ID network for unsupervised domain adaptive re-identification
    Wang, Lun
    Huang, Jiapeng
    Huang, Luoqi
    Wang, Fei
    Gao, Changxin
    Li, Jinsheng
    Xiao, Fei
    Luo, Dapeng
    KNOWLEDGE-BASED SYSTEMS, 2024, 304
  • [10] Aerial-Ground Person Re-ID
    Nguyen, Huy
    Nguyen, Kien
    Sridharan, Sridha
    Fookes, Clinton
    2023 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, ICME, 2023, : 2585 - 2590