Completed part transformer for person re-identification

Zhang, Zhong and He, Di and Liu, Shuang and Xiao, Baihua and Durrani, Tariq S. (2024) Completed part transformer for person re-identification. IEEE Transactions on Multimedia, 26. pp. 2303-2313. ISSN 1520-9210 (https://doi.org/10.1109/tmm.2023.3294816)

[thumbnail of Zhang-etal-IEEE-TOM-2023-Completed-part-transformer-for-person]
Preview
 Text. Filename: Zhang_etal_IEEE_TOM_2023_Completed_part_transformer_for_person.pdf
Accepted Author Manuscript
License: Strathprints license 1.0
Download (1MB)| Preview

Abstract

Recently, part information of pedestrian images has been demonstrated to be effective for person re-identification (ReID), but the part interaction is ignored when using Transformer to learn long-range dependencies. In this paper, we propose a novel transformer network named Completed Part Transformer (CPT) for person ReID, where we design the part transformer layer to learn the completed part interaction. The part transformer layer includes the intra-part layer and the part-global layer, where they consider long-range dependencies from the aspects of the intra-part interaction and the part-global interaction, simultaneously. Furthermore, in order to overcome the limitation of fixed number of the patch tokens in the transformer layer, we propose the Adaptive Refined Tokens (ART) module to focus on learning the interaction between the informative patch tokens in the pedestrian image, which improves the discrimination of the pedestrian representation. Extensive experimental results on four person ReID datasets, i.e., MSMT17, Market1501, DukeMTMC-reID and CUHK03, demonstrate that the proposed method achieves a new state-of-the-art performance, e.g., it achieves 68.0% mAP and 84.6% Rank-1 accuracy on MSMT17.

  • Item type:Article
    ID code:86261
    Dates:
    Date
    Event
    2 February 2024
    Published
    12 July 2023
    Published Online
    9 July 2023
    Accepted
    Notes:© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting /republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
    Subjects:Technology > Electrical engineering. Electronics Nuclear engineering > Electrical apparatus and materials
    Department:Faculty of Engineering > Electronic and Electrical Engineering
    Depositing user: Pure Administrator
    Date deposited:24 Jul 2023 15:29
    Last modified:02 May 2024 01:16
    URI:https://strathprints.strath.ac.uk/id/eprint/86261
CORE (COnnecting REpositories)