AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Generative Retrieval for Unsupervised Text-Based Person Search

Mang Ye, Yucheng Ji, Yang Bai, Min Cao, Siyuan Chai, Bo Du, Min Zhang

TPAMI 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Composed and text-based image retrieval · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Q&A base tier instead of template-based generation (ablation)TierG · CUHK-PEDESR@1: 47.27 -> 54.82Improved
use hard negatives (ISC) instead of random negatives (ablation)TierG intermediate tier · CUHK-PEDESR@1: 53.33 -> 54.58Improved
add stylized expansion instead of direct integration (ablation)TierG advanced tier · CUHK-PEDESR@1: 55.23 -> 55.58Improved
add intermediate and advanced tiers on top of Q&A base tier (ablation)TierG · CUHK-PEDESR@1: 54.82 -> 55.58Improved
add adaptive confidence weighting (ablation)GTR+ retrieval · CUHK-PEDESR@1: 55.58 -> 61.35Improved
use adaptive instead of fixed confidence weighting (ablation)GTR+ retrieval · CUHK-PEDESR@1: 58.72 -> 61.35Improved
replace similarity-based text token masking with adaptive weighting (ablation)GTR+ retrieval · CUHK-PEDESR@1: 55.60 -> 61.35Improved
add random image patch masking (ablation)GTR+ retrieval · CUHK-PEDESR@1: 55.58 -> 56.68Improved
increase hard negative pool from top-1 to top-10 (ablation)TierG intermediate tier · CUHK-PEDESR@1: 57.94 -> 59.50Improved
use K=2 Gaussian components instead of K=1 (ablation)GMM confidence · CUHK-PEDESR@1: 57.29 -> 61.35Improved
increase GMM components from K=2 to K=3 (ablation)GMM confidence · CUHK-PEDESR@1: 61.35 -> 59.31Hurt
pre-train on LargeFine-PersonGTR+ · CUHK-PEDESR@1: 61.35 -> 64.65Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy