AI Paper Atlas

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

Do Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians

Shizhen Zhao, Changxin Gao, Jun Zhang, Hao Cheng, Chuchu Han, Xinyang Jiang, Xiaowei Guo, Wei-Shi Zheng, Nong Sang, Xing Sun

ECCV 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 64 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 QGAB (ablation)Baseline · PI-PRWrank-1: 34.7 -> 38.9Improved
add QGAB (ablation)Baseline · PI-CUHK-SYSUrank-1: 72.5 -> 73.9Improved
add MPSL on top of QGAB (ablation)Baseline + QGAB · PI-PRWmAP: 38.0 -> 40.1Improved
add MPSL on top of QGAB (ablation)Baseline + QGAB · PI-CUHK-SYSUrank-1: 73.9 -> 76.2Improved
add GRAM on top of QGAB (ablation)Baseline + QGAB · PI-PRWrank-1: 38.9 -> 41.8Improved
add GRAM on top of QGAB (ablation)Baseline + QGAB · PI-CUHK-SYSUmAP: 72.3 -> 75.0Improved
add MPSL on top of QGAB + GRAM (ablation)Baseline + QGAB + GRAM · PI-PRWrank-1: 41.8 -> 42.7Improved
add MPSL on top of QGAB + GRAM (ablation)Baseline + QGAB + GRAM · PI-CUHK-SYSUrank-1: 77.9 -> 79.1Improved
add MPSL on top of QGAB + GRAM (ablation)Baseline + QGAB + GRAM · PI-CUHK-SYSUrank-10: 91.0 -> 91.9Mixed
add multi-label learning method HCP instead of strong baselineStrong Baseline · PI-PRWrank-1: 34.7 -> 30.2Hurt
apply PISNet to single-person Re-IDBaseline · Market-1501rank-1: 94.5 -> 95.6Improved
apply PISNet to single-person Re-IDBaseline · DukeMTMC-ReIDrank-1: 86.4 -> 88.8Improved

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