AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Knowing Where to Focus: Attention-Guided Alignment for Text-based Person Search

Lei Tan, Weihao Li, Pingyang Dai, Jie Chen, Liujuan Cao, Rongrong Ji

IJCV 2026 · Vision-language and multimodal › Cross-modal learning · approach: Probabilistic embeddings for cross-modal retrieval · 4 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 Attention-Guided Mask (AGM) instead of random masking (ablation)baseline · CUHK-PEDESRank-1 / mAP: 76.03 -> 77.58 R@1; 69.23 -> 70.50 mAPImproved
add Text Enrichment Module (TEM) (ablation)baseline · CUHK-PEDESRank-1: 76.03 -> 76.87Improved
add TEM on top of AGM (ablation)AGM · CUHK-PEDESRank-1 / mAP: 77.58 -> 78.36 R@1; 70.50 -> 70.72 mAPImproved
mask only semantically vacuous words (Picked) instead of no MLM (ablation)baseline · CUHK-PEDESRank-1: 76.03 -> 75.50Hurt
random masking MLM vs no MLM (ablation)baseline · CUHK-PEDESRank-1: 76.03 -> 76.51Improved
replace random masking with AGM (lower vacuous ratio) (ablation)MLM · CUHK-PEDESRank-1: 76.51 -> 77.58Improved
use EMA aggregation of layer class attention instead of mean (ablation)AGM · CUHK-PEDESRank-1: 78.18 -> 78.36Improved
use EMA aggregation instead of last-layer attention (ablation)AGM · CUHK-PEDESRank-1: 78.08 -> 78.36Improved
vary TEM replacement probability p_tem from 0.1 to 0.4 (ablation)TEM · CUHK-PEDESRank-1: 78.23 -> 78.39 -> 78.36 -> 78.11No clear effect
vary number of TEM candidate words k (3, 5, 10) (ablation)TEM · CUHK-PEDESRank-1: 78.00 -> 78.36 -> 78.05Mixed
vary EMA beta (0.90, 0.95, 0.99) (ablation)AGM · CUHK-PEDESRank-1: 78.21 -> 78.36 -> 77.95Mixed
raise lower bound alpha1 of masking probability from -0.05 to 0.1 (ablation)AGM · CUHK-PEDESRank-1: 76.03 -> 75.50 -> 76.51 -> 77.58Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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