Chat-Driven Text Generation and Interaction for Person Retrieval

ACL ARR 2025 May Submission3986 Authors

Abstract: 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: \textbf{Multi-Turn Text Generation (MTG)} and \textbf{Multi-Turn Text Interaction (MTI)}. MTG generates rich pseudo-labels through simulated dialogues with multimodal large language models (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.

Paper Type: Long

Research Area: Multimodality and Language Grounding to Vision, Robotics and Beyond

Research Area Keywords: multimodal retrieval, multimodal learning, multimodal language models, person search, vision-language models, cross-modal alignment, query refinement

Contribution Types: NLP engineering experiment, Publicly available software and/or pre-trained models, Data resources

Languages Studied: English

Submission Number: 3986