Discriminative multi-scale adjacent feature for person re-identification

被引:0
|
作者
Mengzan Qi
Sixian Chan
Feng Hong
Yuan Yao
Xiaolong Zhou
机构
[1] Zhejiang University of Technology,College of Computer Science and Technology
[2] Zhejiang Shuren University,School of Information Science and Technology
[3] University of Nottingham Ningbo China,School of Computer Science
[4] Quzhou University,College of Electrical and Information Engineering
来源
Complex & Intelligent Systems | 2024年 / 10卷
关键词
Person re-identification; Feature extraction; Feature aggregation; Discriminative feature;
D O I
暂无
中图分类号
学科分类号
摘要
Recently, discriminative and robust identification information has played an increasingly critical role in Person Re-identification (Re-ID). It is a fact that the existing part-based methods demonstrate strong performance in the extraction of fine-grained features. However, their intensive partitions lead to semantic information ambiguity and background interference. Meanwhile, we observe that the body with different structural proportions. Hence, we assume that aggregation with the multi-scale adjacent features can effectively alleviate the above issues. In this paper, we propose a novel Discriminative Multi-scale Adjacent Feature (MSAF) learning framework to enrich semantic information and disregard background. In summary, we establish multi-scale interaction in two stages: the feature extraction stage and the feature aggregation stage. Firstly, a Multi-scale Feature Extraction (MFE) module is designed by combining CNN and Transformer structure to obtain the discriminative specific feature, as the basis for the feature aggregation stage. Secondly, a Jointly Part-based Feature Aggregation (JPFA) mechanism is revealed to implement adjacent feature aggregation with diverse scales. The JPFA contains Same-scale Feature Correlation (SFC) and Cross-scale Feature Correlation (CFC) sub-modules. Finally, to verify the effectiveness of the proposed method, extensive experiments are performed on the common datasets of Market-1501, CUHK03-NP, DukeMTMC, and MSMT17. The experimental results achieve better performance than many state-of-the-art methods.
引用
收藏
页码:4557 / 4569
页数:12
相关论文
共 50 条
  • [21] Soft Pseudo-Label and Multi-Scale Feature Fusion for Person Re-Identification
    Chen Hao
    Zhang Baohua
    Lu Xiaoqi
    Gu Yu
    Wang Yueming
    Liu Xin
    Ren Yan
    Li Jianjun
    Zhang Ming
    LASER & OPTOELECTRONICS PROGRESS, 2022, 59 (24)
  • [22] Discriminative Spatial Feature Learning for Person Re-Identification
    Peng, Peixi
    Tian, Yonghong
    Huang, Yangru
    Wang, Xiangqian
    An, Huilong
    MM '20: PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, 2020, : 274 - 283
  • [23] Person re-identification based on multi-scale global feature and weight-driven part feature
    Tang, Qingwei
    Yan, Pu
    Chen, Jie
    Shao, Hui
    Wang, Fuyu
    Wang, Gang
    AI COMMUNICATIONS, 2022, 35 (03) : 207 - 223
  • [24] Multi-scale Deep Learning Architectures for Person Re-identification
    Qian, Xuelin
    Fu, Yanwei
    Jiang, Yu-Gang
    Xiang, Tao
    Xue, Xiangyang
    2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, : 5409 - 5418
  • [25] Person re-identification based on multi-scale convolutional network
    Yang, XiuJie
    Chen, Ping
    MULTIMEDIA TOOLS AND APPLICATIONS, 2020, 79 (13-14) : 9299 - 9313
  • [26] Person re-identification based on multi-scale constraint network
    Li, Sishang
    Liu, Xueliang
    Zhao, Ye
    Wang, Meng
    PATTERN RECOGNITION LETTERS, 2020, 138 : 403 - 409
  • [27] Person Re-Identification by Deep Learning Multi-Scale Representations
    Chen, Yanbei
    Zhu, Xiatian
    Gong, Shaogang
    2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2017), 2017, : 2590 - 2600
  • [28] Person re-identification based on multi-scale convolutional network
    XiuJie Yang
    Ping Chen
    Multimedia Tools and Applications, 2020, 79 : 9299 - 9313
  • [29] MULTI-SCALE DEEP FEATURE FUSION FOR VEHICLE RE-IDENTIFICATION
    Cheng, Yiting
    Zhang, Chuanfa
    Gu, Kangzheng
    Qi, Lizhe
    Gan, Zhongxue
    Zhang, Wenqiang
    2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 1928 - 1932
  • [30] Discriminative Feature Learning With Foreground Attention for Person Re-Identification
    Zhou, Sanping
    Wang, Jinjun
    Meng, Deyu
    Liang, Yudong
    Gong, Yihong
    Zheng, Nanning
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 28 (09) : 4671 - 4684