Chat-Driven Text Generation and Interaction for Person Retrieval

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Xie, Zequn, Wang, Chuxin, Cai, Sihang, Wang, Yeqiang, Wang, Shulei, Jin, Tao
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916978764021760
author Xie, Zequn
Wang, Chuxin
Cai, Sihang
Wang, Yeqiang
Wang, Shulei
Jin, Tao
author_facet Xie, Zequn
Wang, Chuxin
Cai, Sihang
Wang, Yeqiang
Wang, Shulei
Jin, Tao
contents Text-based person search (TBPS) enables the retrieval of person images from large-scale databases using natural language descriptions, offering critical value in surveillance applications. However, a major challenge lies in the labor-intensive process of obtaining high-quality textual annotations, which limits scalability and practical deployment. To address this, we introduce two complementary modules: Multi-Turn Text Generation (MTG) and Multi-Turn Text Interaction (MTI). MTG generates rich pseudo-labels through simulated dialogues with MLLMs, producing fine-grained and diverse visual descriptions without manual supervision. MTI refines user queries at inference time through dynamic, dialogue-based reasoning, enabling the system to interpret and resolve vague, incomplete, or ambiguous descriptions - characteristics often seen in real-world search scenarios. Together, MTG and MTI form a unified and annotation-free framework that significantly improves retrieval accuracy, robustness, and usability. Extensive evaluations demonstrate that our method achieves competitive or superior results while eliminating the need for manual captions, paving the way for scalable and practical deployment of TBPS systems.
format Preprint
id arxiv_https___arxiv_org_abs_2509_12662
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Chat-Driven Text Generation and Interaction for Person Retrieval
Xie, Zequn
Wang, Chuxin
Cai, Sihang
Wang, Yeqiang
Wang, Shulei
Jin, Tao
Computation and Language
I.2.7; I.4.9
Text-based person search (TBPS) enables the retrieval of person images from large-scale databases using natural language descriptions, offering critical value in surveillance applications. However, a major challenge lies in the labor-intensive process of obtaining high-quality textual annotations, which limits scalability and practical deployment. To address this, we introduce two complementary modules: Multi-Turn Text Generation (MTG) and Multi-Turn Text Interaction (MTI). MTG generates rich pseudo-labels through simulated dialogues with MLLMs, producing fine-grained and diverse visual descriptions without manual supervision. MTI refines user queries at inference time through dynamic, dialogue-based reasoning, enabling the system to interpret and resolve vague, incomplete, or ambiguous descriptions - characteristics often seen in real-world search scenarios. Together, MTG and MTI form a unified and annotation-free framework that significantly improves retrieval accuracy, robustness, and usability. Extensive evaluations demonstrate that our method achieves competitive or superior results while eliminating the need for manual captions, paving the way for scalable and practical deployment of TBPS systems.
title Chat-Driven Text Generation and Interaction for Person Retrieval
topic Computation and Language
I.2.7; I.4.9
url https://arxiv.org/abs/2509.12662