Research map / Label-efficient and robust learning / Recognition and long-tail
Sample-Specific SVM Learning for Person Re-Identification
Check 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 |
|---|---|---|---|
| Use sample-specific SVMs rather than one fixed SVM (ablation) | Person re-identification with LOMO features · VIPeR | rank-1 recognition rate: 34.65% to 42.66% | Helped |
| Use sample-specific SVMs rather than one fixed SVM (ablation) | Person re-identification with LOMO features · QMUL GRID | rank-1 recognition rate: 16.24% to 22.40% | Helped |
| Use sample-specific SVMs rather than one fixed SVM (ablation) | Person re-identification with LOMO features · PRID 450S | rank-1 recognition rate: 52.58% to 60.49% | Helped |
| Use sample-specific SVMs rather than one fixed SVM (ablation) | Person re-identification with LOMO features · CUHK01 | rank-1 recognition rate: 57.34% to 65.97% | Helped |
| Add the full feature map, including the probe and gallery features, to feature difference (ablation) | Sample-specific SVM matching · VIPeR | rank-1 recognition rate: 39.75% to 42.66% | Helped |
| Add the full feature map, including the probe and gallery features, to feature difference (ablation) | Sample-specific SVM matching · QMUL GRID | rank-1 recognition rate: 16.56% to 22.40% | Helped |
| Add the full feature map, including the probe and gallery features, to feature difference (ablation) | Sample-specific SVM matching · PRID 450S | rank-1 recognition rate: 57.96% to 60.49% | Helped |
| Add the full feature map, including the probe and gallery features, to feature difference (ablation) | Sample-specific SVM matching · CUHK01 | rank-1 recognition rate: 56.26% to 65.97% | Helped |
| Use LSSCDL rather than SCDL for dictionary learning (ablation) | Sample-specific SVM matching · VIPeR | rank-1 recognition rate: 40.82% to 42.66% | Helped |
| Use LSSCDL rather than SCDL for dictionary learning (ablation) | Sample-specific SVM matching · QMUL GRID | rank-1 recognition rate: 20.88% to 22.40% | Helped |
| Use LSSCDL rather than SCDL for dictionary learning (ablation) | Sample-specific SVM matching · PRID 450S | rank-1 recognition rate: 56.58% to 60.49% | Helped |
| Use LSSCDL rather than SCDL for dictionary learning (ablation) | Sample-specific SVM matching · CUHK01 | rank-1 recognition rate: 59.40% to 65.97% | Helped |
Closest papers by meaning
- Learning Heterogeneous Dictionary Pair with Feature Projection Matrix for Pedestrian Video Retrieval via Single Query Image (AAAI 2017 · similarity 0.89)
- Learning a Discriminative Null Space for Person Re-Identification (CVPR 2016 · similarity 0.89)
- Distilled Person Re-Identification: Towards a More Scalable System (CVPR 2019 · similarity 0.88)
- Discriminative Semi-Coupled Projective Dictionary Learning for Low-Resolution Person Re-Identification (AAAI 2018 · similarity 0.88)
- From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization (CVPR 2025 · similarity 0.86)
- Cheb-GR: Rethinking K-nearest Neighbor Search in Re-ranking for Person Re-identification (CVPR 2025 · similarity 0.86)
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.