AI Paper Atlas

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

ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Language

Zhe Wang, Zhiyuan Fang, Jun Wang, Yezhou Yang

ECCV 2020 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded scene text and structure · 266 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 segmentation loss to ID-loss baseline (ablation)ViTAA baseline · CUHK-PEDES testR@1: 29.68 -> 30.93Improved
add attribute alignment to ID-loss baseline (ablation)ViTAA baseline · CUHK-PEDES testR@1: 29.68 -> 31.40Improved
add attribute alignment to segmentation model (ablation)ViTAA · CUHK-PEDES testR@1: 30.93 -> 39.26Improved
add global alignment to ID-loss baseline (ablation)ViTAA baseline · CUHK-PEDES testR@1: 29.68 -> 52.27Improved
add segmentation and attribute alignment to global alignment (ablation)ViTAA · CUHK-PEDES testR@1: 52.27 -> 55.97Improved
add segmentation and attribute alignment to global alignment (ablation)ViTAA · CUHK-PEDES testR@10: 81.61 -> 83.52Improved
add global alignment to segmentation + attribute alignment (ablation)ViTAA · CUHK-PEDES testR@1: 39.26 -> 55.97Improved
increase K in K-reciprocal sampling beyond 8 (ablation)ViTAA · CUHK-PEDES testR@1 and R@10: best R@1 and R@10 is achieved when K is set to 8Hurt
use ViTAA instead of GALMperson search · CUHK-PEDES testR@1: 54.12 -> 55.97Improved
use ViTAA instead of MIAperson search · CUHK-PEDES testR@1: 53.10 -> 55.97Improved

Later papers that compared with this method

2 later accepted papers report ViTAA as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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