Research map / Detection and segmentation / CNN features
Hierarchical Online Instance Matching for Person Search
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| HOIM vs QEEPS | person search · CUHK-SYSU | mAP: 88.9 -> 89.7 | Helped |
| HOIM vs QEEPS | person search · PRW | top-1: 76.7 -> 80.4 | Helped |
| add focal loss (ablation) | OIM-base · CUHK-SYSU | mAP: 83.6 -> 85.1 | Helped |
| replace FIFO queue with Selective Memory Refreshment (ablation) | OIM-base + focal · CUHK-SYSU | mAP: 85.1 -> 85.5 | Helped |
| use hierarchical HOIM loss instead of separate R-CNN cls + OIM losses (ablation) | OIM-base + focal + SMR · CUHK-SYSU | mAP: 85.5 -> 89.7 | Helped |
| add re-ID loss head to Faster R-CNN (ablation) | Faster R-CNN detector · CUHK-SYSU | detection AP: -11.18 (OIM) vs -1.35 (HOIM) | Hurt |
| refine OIM with BN, large batch, LR warm-up (ablation) | OIM · CUHK-SYSU | mAP: 75.5 -> 83.6 | Helped |
Closest papers by meaning
- Joint Detection and Identification Feature Learning for Person Search (CVPR 2017 · similarity 0.92)
- Diverse Knowledge Distillation for End-to-End Person Search (AAAI 2021 · similarity 0.89)
- Norm-Aware Embedding for Efficient Person Search (CVPR 2020 · similarity 0.89)
- Distilled Person Re-Identification: Towards a More Scalable System (CVPR 2019 · similarity 0.88)
- Cheb-GR: Rethinking K-nearest Neighbor Search in Re-ranking for Person Re-identification (CVPR 2025 · similarity 0.87)
- Divide and Conquer: Hybrid Pre-training for Person Search (AAAI 2024 · similarity 0.87)
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.