ROGLE: Robust Global-Local Alignment with Automated Region Supervision for Text-Based Person Search

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xie, Zequn, Jia, Xibei, Cai, Sihang, Wang, Shulei, Jin, Tao
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911739522580480
author Xie, Zequn
Jia, Xibei
Cai, Sihang
Wang, Shulei
Jin, Tao
author_facet Xie, Zequn
Jia, Xibei
Cai, Sihang
Wang, Shulei
Jin, Tao
contents Text-Based Person Search (TBPS) aims to retrieve pedestrian images using natural language queries. However, existing TBPS models, especially those based on CLIP, struggle with fine-grained understanding due to global representational bias and semantic sparsity inherited from training on short captions. This results in weak fine-grained alignment, exacerbated by the scarcity of region-level annotations. To address this, we propose ROGLE (Robust Global-Local Embedding), a unified framework that overcomes reliance on costly manual annotations through an automated Region-to-Sentence Matching (RSM) strategy. RSM automatically mines pseudo region-sentence pairs for scalable fine-grained supervision. Furthermore, ROGLE employs a multi-granular learning strategy that fuses global contrastive learning with region-level local alignment. We also introduce the P-VLG Benchmark, a large-scale dataset constructed by curating and enriching images from established public benchmarks. It features over 100,000 annotated regions and rich long-form captions, making it the first TBPS benchmark to support both global and local assessment protocols. Extensive experiments show that ROGLE significantly outperforms existing approaches, particularly on challenging long-form queries. Code and the P-VLG benchmark will be made publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2606_01825
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ROGLE: Robust Global-Local Alignment with Automated Region Supervision for Text-Based Person Search
Xie, Zequn
Jia, Xibei
Cai, Sihang
Wang, Shulei
Jin, Tao
Computer Vision and Pattern Recognition
Multimedia
Text-Based Person Search (TBPS) aims to retrieve pedestrian images using natural language queries. However, existing TBPS models, especially those based on CLIP, struggle with fine-grained understanding due to global representational bias and semantic sparsity inherited from training on short captions. This results in weak fine-grained alignment, exacerbated by the scarcity of region-level annotations. To address this, we propose ROGLE (Robust Global-Local Embedding), a unified framework that overcomes reliance on costly manual annotations through an automated Region-to-Sentence Matching (RSM) strategy. RSM automatically mines pseudo region-sentence pairs for scalable fine-grained supervision. Furthermore, ROGLE employs a multi-granular learning strategy that fuses global contrastive learning with region-level local alignment. We also introduce the P-VLG Benchmark, a large-scale dataset constructed by curating and enriching images from established public benchmarks. It features over 100,000 annotated regions and rich long-form captions, making it the first TBPS benchmark to support both global and local assessment protocols. Extensive experiments show that ROGLE significantly outperforms existing approaches, particularly on challenging long-form queries. Code and the P-VLG benchmark will be made publicly available.
title ROGLE: Robust Global-Local Alignment with Automated Region Supervision for Text-Based Person Search
topic Computer Vision and Pattern Recognition
Multimedia
url https://arxiv.org/abs/2606.01825