Signals 4 · free daily AI digest

Generative Retrieval for Unsupervised Text-Based Person Search

Paper recorded by Signals 4 on 2026-09-11 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-11 on arXiv · recorded by Signals 4 on 2026-09-14

Category: cs.CV · 计算机视觉 · first seen 2026-09-14

Abstract

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 st

Read on arXiv →

#66 most recent of 237 cs.CV papers we have recorded · ↑ newer: Investigating Temporal Motion Features for Pose-to-Text Indian Sign La · ↓ older: Fast and Faithful: Principled Conditional Flow Matching for Inverse Pr
Cite this page: Generative Retrieval for Unsupervised Text-Based Person Search: the #66 most recent of 237 cs.CV papers we have recorded (as of 2026-09-11). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/generative-retrieval-for-unsupervised-text-based-person-search.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CV papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions