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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add QGAB (ablation) | Baseline · PI-PRW | rank-1: 34.7 -> 38.9 | Improved |
| add QGAB (ablation) | Baseline · PI-CUHK-SYSU | rank-1: 72.5 -> 73.9 | Improved |
| add MPSL on top of QGAB (ablation) | Baseline + QGAB · PI-PRW | mAP: 38.0 -> 40.1 | Improved |
| add MPSL on top of QGAB (ablation) | Baseline + QGAB · PI-CUHK-SYSU | rank-1: 73.9 -> 76.2 | Improved |
| add GRAM on top of QGAB (ablation) | Baseline + QGAB · PI-PRW | rank-1: 38.9 -> 41.8 | Improved |
| add GRAM on top of QGAB (ablation) | Baseline + QGAB · PI-CUHK-SYSU | mAP: 72.3 -> 75.0 | Improved |
| add MPSL on top of QGAB + GRAM (ablation) | Baseline + QGAB + GRAM · PI-PRW | rank-1: 41.8 -> 42.7 | Improved |
| add MPSL on top of QGAB + GRAM (ablation) | Baseline + QGAB + GRAM · PI-CUHK-SYSU | rank-1: 77.9 -> 79.1 | Improved |
| add MPSL on top of QGAB + GRAM (ablation) | Baseline + QGAB + GRAM · PI-CUHK-SYSU | rank-10: 91.0 -> 91.9 | Mixed |
| add multi-label learning method HCP instead of strong baseline | Strong Baseline · PI-PRW | rank-1: 34.7 -> 30.2 | Hurt |
| apply PISNet to single-person Re-ID | Baseline · Market-1501 | rank-1: 94.5 -> 95.6 | Improved |
| apply PISNet to single-person Re-ID | Baseline · DukeMTMC-ReID | rank-1: 86.4 -> 88.8 | Improved |
Closest papers by meaning
- Attention Disturbance and Dual-Path Constraint Network for Occluded Person Re-identification (AAAI 2024 · similarity 0.86)
- Mixed High-Order Attention Network for Person Re-Identification (ICCV 2019 · similarity 0.86)
- Person Re-Identification Using Heterogeneous Local Graph Attention Networks (CVPR 2021 · similarity 0.86)
- Joint Detection and Identification Feature Learning for Person Search (CVPR 2017 · similarity 0.86)
- Salience-Guided Cascaded Suppression Network for Person Re-Identification (CVPR 2020 · similarity 0.85)
- Person Search via A Mask-guided Two-stream CNN Model (ECCV 2018 · similarity 0.85)
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.
