Channel semantic mutual learning for visible-thermal person re-identification
PLOS ONE · 2024
DOI: 10.1371/journal.pone.0293498 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS ONE, 2024. Verfasst von Yingjie Zhu und 1 weiteren Autor:innen. Beteiligte Einrichtung: College of Software, Xinjiang University, Urumqi, China. Hauptthemen laut MEDLINE: Semantics, Pedestrians. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research and Application of Multilingual and Multimodal Information Content Security, National Natural Science Foundation of China, Autonomous Region Special Research and Development Task.
Abstract (Originalsprache)
Visible-infrared person re-identification (VI-ReID) is a cross-modality retrieval issue aiming to match the same pedestrian between visible and infrared cameras. Thus, the modality discrepancy presents a significant challenge for this task. Most methods employ different networks to extract features that are invariant between modalities. While we propose a novel channel semantic mutual learning network (CSMN), which attributes the difference in semantics between modalities to the difference at the channel level, it optimises the semantic consistency between channels from two perspectives: the local inter-channel semantics and the global inter-modal semantics. Meanwhile, we design a channel-level auto-guided double metric loss (CADM) to learn modality-invariant features and the sample distribution in a fine-grained manner. We conducted experiments on RegDB and SYSU-MM01, and the experimental results validate the superiority of CSMN. Especially on RegDB datasets, CSMN improves the current best performance by 3.43% and 0.5% on the Rank-1 score and mINP value, respectively. The code is available at https://github.com/013zyj/CSMN .
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- College of Software, Xinjiang University, Urumqi, China.
- Xinjiang Multilingual Information Technology Laboratory, Xinjiang University, Urumqi, China.
ORCID-Profile: Wenzhong Yang
Förderung
- Research and Application of Multilingual and Multimodal Information Content Security
- National Natural Science Foundation of China
- Autonomous Region Special Research and Development Task
- Autonomous Region Major Science and Technology Special Project
- Optimization of low-resolution device defect recognition algorithm based on image enhancement
Zitieren
APA
Zhu, Y., & Yang, W. (2024). Channel semantic mutual learning for visible-thermal person re-identification. PLOS ONE. https://doi.org/10.1371/journal.pone.0293498
Vancouver
Zhu Y, Yang W. Channel semantic mutual learning for visible-thermal person re-identification. PLOS ONE. 2024. doi:10.1371/journal.pone.0293498
BibTeX
@article{Zhu2024,
author = {Zhu, Yingjie and Yang, Wenzhong},
title = {Channel semantic mutual learning for visible-thermal person re-identification},
journal = {PLOS ONE},
year = {2024},
doi = {10.1371/journal.pone.0293498}
}
EUVIMED