T2I-VeRW: Part-level Fine-grained Perception for Text-to-Image Vehicle Retrieval

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Xiao, Wang, Ziwen, Kong, Weizhe, Wu, Wentao, Li, Yuehang, Zheng, Aihua, Li, Chenglong, Tang, Jin
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910197865250816
author Wang, Xiao
Wang, Ziwen
Kong, Weizhe
Wu, Wentao
Li, Yuehang
Zheng, Aihua
Li, Chenglong
Tang, Jin
author_facet Wang, Xiao
Wang, Ziwen
Kong, Weizhe
Wu, Wentao
Li, Yuehang
Zheng, Aihua
Li, Chenglong
Tang, Jin
contents Vehicle Re-identification (Re-ID) aims to retrieve the most similar image to a given query from images captured by non-overlapping cameras. Extending vehicle Re-ID from image-only queries to text-based queries enables retrieval in real-world scenarios where only a witness description of the target vehicle is available. In this paper, we propose PFCVR, a Part-level Fine-grained Cross-modal Vehicle Retrieval model for text-to-image vehicle re-identification. PFCVR constructs locally paired images and texts at the part level and introduces learnable part-query tokens that aggregate both part-specific and full-sentence context before aligning with visual part features. On top of this explicit local alignment, a bi-directional mask recovery module lets each modality reconstruct its masked content under the guidance of the other, implicitly bridging local correspondences into global feature alignment. Furthermore, we construct a new large-scale dataset called T2I-VeRW, which contains 14,668 images covering 1,796 vehicle identities with fine-grained part-level annotations. Experimental results on the T2I-VeRI dataset show that PFCVR achieves 29.2\% Rank-1 accuracy, improving over the best competing method by +3.7\% percentage points. On the newly proposed T2I-VeRW benchmark, PFCVR achieves 55.2\% Rank-1 accuracy, outperforming a comprehensive set of recent state-of-the-art methods. Source code will be released on https://github.com/Event-AHU/Neuromorphic_ReID
format Preprint
id arxiv_https___arxiv_org_abs_2605_06012
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle T2I-VeRW: Part-level Fine-grained Perception for Text-to-Image Vehicle Retrieval
Wang, Xiao
Wang, Ziwen
Kong, Weizhe
Wu, Wentao
Li, Yuehang
Zheng, Aihua
Li, Chenglong
Tang, Jin
Computer Vision and Pattern Recognition
Artificial Intelligence
Vehicle Re-identification (Re-ID) aims to retrieve the most similar image to a given query from images captured by non-overlapping cameras. Extending vehicle Re-ID from image-only queries to text-based queries enables retrieval in real-world scenarios where only a witness description of the target vehicle is available. In this paper, we propose PFCVR, a Part-level Fine-grained Cross-modal Vehicle Retrieval model for text-to-image vehicle re-identification. PFCVR constructs locally paired images and texts at the part level and introduces learnable part-query tokens that aggregate both part-specific and full-sentence context before aligning with visual part features. On top of this explicit local alignment, a bi-directional mask recovery module lets each modality reconstruct its masked content under the guidance of the other, implicitly bridging local correspondences into global feature alignment. Furthermore, we construct a new large-scale dataset called T2I-VeRW, which contains 14,668 images covering 1,796 vehicle identities with fine-grained part-level annotations. Experimental results on the T2I-VeRI dataset show that PFCVR achieves 29.2\% Rank-1 accuracy, improving over the best competing method by +3.7\% percentage points. On the newly proposed T2I-VeRW benchmark, PFCVR achieves 55.2\% Rank-1 accuracy, outperforming a comprehensive set of recent state-of-the-art methods. Source code will be released on https://github.com/Event-AHU/Neuromorphic_ReID
title T2I-VeRW: Part-level Fine-grained Perception for Text-to-Image Vehicle Retrieval
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2605.06012