P-CLIP: Progressive Discrepancy Learning for One-Shot Text-to-Image Person Re-Identification
IEEE Transactions on Image Processing · 2026 · 35 · 317-331
DOI: 10.1109/tip.2025.3648582 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Chengji Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 64 Literaturangaben. Gefördert von: National Natural Science Foundation of China, China Postdoctoral Science Foundation, Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning.
Abstract (Originalsprache)
One-shot Text-to-Image Person Re-Identification (One-shot TIReID) aims to construct a TIReID model using only a single labeled image-text pair per identity, along with a large pool of unlabeled person images. While supervised learning in text-to-image person re-identification has demonstrated high effectiveness, the requirement for extensive annotated data, both in terms of identities and corresponding textual descriptions, makes it impractical for large-scale camera networks. One-shot TIReID presents a promising approach to reduce the annotation burden. The primary challenge in one-shot TIReID lies in establishing consistent visual-textual correspondences across diverse viewing conditions, particularly in the absence of cross-view paired data. To address this challenge, we propose a novel progressive discrepancy learning framework, termed P-CLIP, which aims to establish a shared embedding space that is robust to view-specific biases. To achieve this goal, we dynamically construct multi-view image-text pairs based on a single labeled pair and simultaneously project the multi-view data into a unified embedding space. Specifically, we propose a Progressive Multi-View Generation method (MVG) to generate multiple noisy views from a single labeled instance for training. To mitigate cross-view ambiguities, we introduce a Cross-View Discrepancy Learning module (CDL) that leverages the discrepancies among different views to guide the learning of cross-view visual-textual correspondences. This approach effectively integrates multimodal error correction into the person re-identification domain. Furthermore, to enhance the effectiveness of visual-textual correspondence learning, we propose a Compact Cross-Modal Matching Loss (CCM), which suppresses unmatched pairs while emphasizing matched ones. Extensive experiments were conducted on three benchmark datasets, and the experimental results demonstrate the effectiveness of our proposed method. The data and codes are available at https://github.com/Itachjw/P-CLIP/tree/main.
Förderung
- National Natural Science Foundation of China
- China Postdoctoral Science Foundation
- Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning
Zitieren
APA
Wang, C., Dong, M., Ye, M., Sun, H., & Jiang, X. (2026). P-CLIP: Progressive Discrepancy Learning for One-Shot Text-to-Image Person Re-Identification. IEEE Transactions on Image Processing, 35, 317-331. https://doi.org/10.1109/tip.2025.3648582
Vancouver
Wang C, Dong M, Ye M, Sun H, Jiang X. P-CLIP: Progressive Discrepancy Learning for One-Shot Text-to-Image Person Re-Identification. IEEE Transactions on Image Processing. 2026;35:317-331. doi:10.1109/tip.2025.3648582
BibTeX
@article{Wang2026,
author = {Wang, Chengji and Dong, Ming and Ye, Mang and Sun, Hao and Jiang, Xingpeng},
title = {P-CLIP: Progressive Discrepancy Learning for One-Shot Text-to-Image Person Re-Identification},
journal = {IEEE Transactions on Image Processing},
year = {2026},
volume = {35},
pages = {317--331},
doi = {10.1109/tip.2025.3648582}
}
EUVIMED