Graph convolution-based feature disentanglement for visible-infrared person re-identification

Ren Lou, Muyu Wang*, Yihao Shen, Sanyuan Zhao, Xinyuan Wang, Yueqi Zhou, Fangfang Li, Qiangqiang Xiang

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

We propose a graph convolution-based disentanglement algorithm that is well-performed in the task of cross-modal person re-identification between visible and infrared images. Given the image of an individual in one modality, the problem to be addressed is whether the same person also appears in images from another modality. To tackle this issue, the main idea of our proposed method is to disentangle image features into modality-related and modality-invariant features, thereby alleviating feature discrepancies across different modal images. Unlike traditional disentanglement methods, our proposed graph convolution-based approach abandons the use of generative adversarial networks and employs attention mechanisms for initial disentanglement, followed by optimization of disentangled features using graph convolution. Comprehensive experimental results on the RegDB dataset and SYSU MM01 dataset demonstrate the superiority of our method in terms of effectiveness and efficiency.

源语言英语
主期刊名International Conference on Optics, Electronics, and Communication Engineering, OECE 2024
编辑Yang Yue
出版商SPIE
ISBN(电子版)9781510685437
DOI
出版状态已出版 - 2024
活动2024 International Conference on Optics, Electronics, and Communication Engineering, OECE 2024 - Wuhan, 中国
期限: 26 7月 202428 7月 2024

出版系列

姓名Proceedings of SPIE - The International Society for Optical Engineering
13395
ISSN(印刷版)0277-786X
ISSN(电子版)1996-756X

会议

会议2024 International Conference on Optics, Electronics, and Communication Engineering, OECE 2024
国家/地区中国
Wuhan
时期26/07/2428/07/24

指纹

探究 'Graph convolution-based feature disentanglement for visible-infrared person re-identification' 的科研主题。它们共同构成独一无二的指纹。

引用此

Lou, R., Wang, M., Shen, Y., Zhao, S., Wang, X., Zhou, Y., Li, F., & Xiang, Q. (2024). Graph convolution-based feature disentanglement for visible-infrared person re-identification. 在 Y. Yue (编辑), International Conference on Optics, Electronics, and Communication Engineering, OECE 2024 文章 1339543 (Proceedings of SPIE - The International Society for Optical Engineering; 卷 13395). SPIE. https://doi.org/10.1117/12.3049214