Saved in:
Bibliographic Details
Main Author: Xie, Zequn
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.18625
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917223869710336
author Xie, Zequn
author_facet Xie, Zequn
contents Text-Based Person Search (TBPS) aims to retrieve pedestrian images from large galleries using natural language descriptions. This task, essential for public safety applications, is hindered by cross-modal discrepancies and ambiguous user queries. We introduce CONQUER, a two-stage framework designed to address these challenges by enhancing cross-modal alignment during training and adaptively refining queries at inference. During training, CONQUER employs multi-granularity encoding, complementary pair mining, and context-guided optimal matching based on Optimal Transport to learn robust embeddings. At inference, a plug-and-play query enhancement module refines vague or incomplete queries via anchor selection and attribute-driven enrichment, without requiring retraining of the backbone. Extensive experiments on CUHK-PEDES, ICFG-PEDES, and RSTPReid demonstrate that CONQUER consistently outperforms strong baselines in both Rank-1 accuracy and mAP, yielding notable improvements in cross-domain and incomplete-query scenarios. These results highlight CONQUER as a practical and effective solution for real-world TBPS deployment. Source code is available at https://github.com/zqxie77/CONQUER.
format Preprint
id arxiv_https___arxiv_org_abs_2601_18625
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CONQUER: Context-Aware Representation with Query Enhancement for Text-Based Person Search
Xie, Zequn
Computer Vision and Pattern Recognition
Text-Based Person Search (TBPS) aims to retrieve pedestrian images from large galleries using natural language descriptions. This task, essential for public safety applications, is hindered by cross-modal discrepancies and ambiguous user queries. We introduce CONQUER, a two-stage framework designed to address these challenges by enhancing cross-modal alignment during training and adaptively refining queries at inference. During training, CONQUER employs multi-granularity encoding, complementary pair mining, and context-guided optimal matching based on Optimal Transport to learn robust embeddings. At inference, a plug-and-play query enhancement module refines vague or incomplete queries via anchor selection and attribute-driven enrichment, without requiring retraining of the backbone. Extensive experiments on CUHK-PEDES, ICFG-PEDES, and RSTPReid demonstrate that CONQUER consistently outperforms strong baselines in both Rank-1 accuracy and mAP, yielding notable improvements in cross-domain and incomplete-query scenarios. These results highlight CONQUER as a practical and effective solution for real-world TBPS deployment. Source code is available at https://github.com/zqxie77/CONQUER.
title CONQUER: Context-Aware Representation with Query Enhancement for Text-Based Person Search
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.18625