UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

HOH-Net: High-Order Hierarchical Middle-Feature Learning Network for Visible-Infrared Person Re-Identification

Qiu, Liuxiang; Chen, Si; Xue, Jing-Hao; Wang, Da-Han; Zhu, Shunzhi; Yan, Yan; (2025) HOH-Net: High-Order Hierarchical Middle-Feature Learning Network for Visible-Infrared Person Re-Identification. IEEE Transactions on Circuits and Systems for Video Technology pp. 1-16. 10.1109/tcsvt.2025.3609840. (In press). Green open access

[thumbnail of LiuxiangQiu-TCSVT-2025.pdf]
Preview
Text
LiuxiangQiu-TCSVT-2025.pdf - Accepted Version

Download (9MB) | Preview

Abstract

Visible-infrared person re-identification (VI-ReID) is a cross-modality retrieval task that aims to match images of the same person across visible (VIS) and infrared (IR) modalities. Existing VI-ReID methods ignore high-order structure information of features and struggle to learn a reliable common feature space due to the modality discrepancy between VIS and IR images. To alleviate the above issues, we propose a novel high-order hierarchical middle-feature learning network (HOH-Net) for VI-ReID. We introduce a high-order structure learning (HSL) module to explore the high-order relationships of short- and long-range feature nodes, for significantly mitigating model collapse and effectively obtaining discriminative features. We further develop a fine-coarse graph attention alignment (FCGA) module, which efficiently aligns multi-modality feature nodes from node-level and region-level perspectives, ensuring reliable middle-feature representations. Moreover, we exploit a hierarchical middle-feature agent learning (HMAL) loss to hierarchically reduce the modality discrepancy at each stage of the network by using the agents of middle features. The proposed HMAL loss also exchanges detailed and semantic information between low- and high-stage networks. Finally, we introduce a modality-range identity-center contrastive (MRIC) loss to minimize the distances between VIS, IR, and middle features. Extensive experiments demonstrate that the proposed HOH-Net yields state-of-the-art performance on the image-based and video-based VI-ReID datasets. The code is available at: https://github.com/Jaulaucoeng/HOS-Net.

Type: Article
Title: HOH-Net: High-Order Hierarchical Middle-Feature Learning Network for Visible-Infrared Person Re-Identification
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/tcsvt.2025.3609840
Publisher version: https://doi.org/10.1109/tcsvt.2025.3609840
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions.
Keywords: Visible-infrared person re-identification, highorder structure, middle-feature learning
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science
URI: https://discovery.ucl.ac.uk/id/eprint/10214171
Downloads since deposit
2Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item