Research map / Label-efficient and robust learning / Recognition and long-tail
Multi-Channel Pyramid Person Matching Network for Person Re-Identification
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 |
|---|---|---|---|
| fuse semantic-components and color-texture correspondence (ablation) | SC-PPMN and CTM-PPMN · PRID450s | rank-1: 10.14 | Helped |
| fuse semantic-components and color-texture correspondence (ablation) | SC-PPMN and CTM-PPMN · VIPeR | rank-1: 4.31 | Helped |
| fuse semantic-components and color-texture correspondence (ablation) | SC-PPMN and CTM-PPMN · i-LIDS | rank-1: 7.89 | Helped |
| fuse semantic-components and color-texture correspondence (ablation) | SC-PPMN and CTM-PPMN · CUHK03 labelled and detected | rank-1: 0.86; 1.25 | Helped |
| add hard negative mining (ablation) | MC-PPMN · CUHK03 labelled | rank-1: 84.36 -> 86.36 | Helped |
| add hard negative mining (ablation) | MC-PPMN · CUHK03 detected | rank-1: 81.28 -> 81.88 | Helped |
| add hard negative mining (ablation) | MC-PPMN · CUHK01 (100 test IDs) | rank-1: 92.32 -> 93.45 | Helped |
| add hard negative mining (ablation) | SC-PPMN · CUHK03 detected | rank-1: 77.60 -> 80.63 | Hurt |
| use only semantic-components correspondence instead of fused channels (ablation) | MC-PPMN · CUHK03 labelled | rank-1: 85.50 -> 86.36 | Hurt |
| use only color-texture correspondence instead of fused channels (ablation) | MC-PPMN · CUHK03 labelled | rank-1: 76.58 -> 86.36 | Hurt |
| use only semantic-components correspondence instead of fused channels (ablation) | MC-PPMN · PRID2011 | rank-1: 32.00 -> 34.00 | Hurt |
| use only color-texture correspondence instead of fused channels (ablation) | MC-PPMN · PRID2011 | rank-1: 12.00 -> 34.00 | Hurt |
Closest papers by meaning
- Deep Neural Networks with Inexact Matching for Person Re-Identification (NeurIPS 2016 · similarity 0.90)
- Interaction-And-Aggregation Network for Person Re-Identification (CVPR 2019 · similarity 0.89)
- Horizontal Pyramid Matching for Person Re-Identification (AAAI 2019 · similarity 0.88)
- Efficient and Deep Person Re-Identification Using Multi-Level Similarity (CVPR 2018 · similarity 0.88)
- Resource Aware Person Re-Identification Across Multiple Resolutions (CVPR 2018 · similarity 0.88)
- Joint Learning of Single-Image and Cross-Image Representations for Person Re-Identification (CVPR 2016 · similarity 0.88)
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.