AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

VIPerson: Flexibly Generating Virtual Identity for Person Re-Identification

Xiao-Wen Zhang, Delong Zhang, Yi-Xing Peng, Zhi Ouyang, Jingke Meng, Wei-Shi Zheng

ICCV 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Cross-modality and occlusion re-identification · 3 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 camera-realistic style realization (ablation)VIPerson · Market1501 direct transferrank-1: 33.6 -> 66.5Improved
add camera-realistic style realization (ablation)VIPerson · MSMT17 direct transferrank-1: 7.5 -> 32.5Improved
add scene variations (segment-and-paste) (ablation)VIPerson · MSMT17 direct transferrank-1: 0.9 -> 7.5Improved
add scene variations (segment-and-paste) (ablation)VIPerson · Market1501 direct transferrank-1: 11.7 -> 33.6Improved
add pose variations (ablation)VIPerson · MSMT17 direct transferrank-1: 20.5 -> 32.5Improved
add pose variations (ablation)VIPerson · Market1501 direct transferrank-1: 39.8 -> 66.5Improved
add hard identities via text embedding dropout (ablation)VIPerson · MSMT17 and Market1501 (5000 identities)rank-1Improved
increase number of identities from 1000 to 3000, then further (ablation)VIPerson · MSMT17 and Market1501rank-1Mixed
increase intra-ID group scale (ablation)VIPerson · MSMT17 and Market1501rank-1Improved
use VIPerson* with target-scenario pose, scene and style informationVIPerson · MSMT17 direct transferrank-1: 32.5 -> 34.3Improved
use VIPerson instead of UnrealPerson for direct transferUnrealPerson · MSMT17 direct transferrank-1: 26.8 -> 32.5Improved
pre-train on VIPerson instead of UnrealPerson before fine-tuningUnrealPerson · MSMT17 supervised fine-tuningrank-1: 74.5 -> 76.5Improved

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