SOURCE-LINKED INTELLIGENCE

Generative Retrieval for Unsupervised Text-Based Person Search

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

Text-based person search (TBPS) aims to retrieve images of a target person from a large image gallery based on a given natural language description. Most existing methods rely on supervised learning with manually annotated image-text pairs. In this paper, we explore unsupervised TBPS, with only unlabeled images. We propose GTR+, a two-stage generation-then-retrieval framework. In the generation stage, we introduce a tiered description generation framework designed to produce fine-grained and stylistically diverse textual descriptions through a three-tier sequential process. The base tier lever

Read original source ↗ Open in workspace

recordType

paper

region

Global