Research map / Label-efficient and robust learning / Recognition and long-tail
Similarity Learning With Spatial Constraints 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 |
|---|---|---|---|
| add spatially constrained local similarities to global similarity (ablation) | SCSP · VIPeR | rank-1 matching rate (%): 48.10 -> 53.54 | Helped |
| add spatially constrained local similarities to global similarity (ablation) | SCSP · GRID | rank-1 matching rate (%): 19.20 -> 24.24 | Helped |
| add spatially constrained local similarities to global similarity (ablation) | SCSP · 3DPES | rank-1 matching rate (%): 52.86 -> 57.29 | Helped |
| add spatially constrained local similarities to global similarity (ablation) | SCSP · Market-1501 | rank-1 matching rate (%): 51.10 -> 51.90 | Helped |
| add global similarity to integrated local similarity (ablation) | SCSP · VIPeR | rank-1 matching rate (%): 51.04 -> 53.54 | Helped |
| add global similarity to integrated local similarity (ablation) | SCSP · GRID | rank-1 matching rate (%): 22.72 -> 24.24 | Helped |
| add global similarity to integrated local similarity (ablation) | SCSP · 3DPES | rank-1 matching rate (%): 54.91 -> 57.29 | Helped |
| add global similarity to integrated local similarity (ablation) | SCSP · Market-1501 | rank-1 matching rate (%): 49.55 -> 51.90 | Helped |
| use 4 local stripes rather than one global region (ablation) | SCSP with cue C1 · VIPeR | rank-1 matching rate (%): 37.31 -> 43.70 | Helped |
| use 16 stripes instead of 4 (ablation) | SCSP with cue C1 · VIPeR | rank-1 matching rate (%): 43.70 -> 44.75 | Helped |
| use 32 stripes instead of 4 (ablation) | SCSP with cue C1 · VIPeR | rank-1 matching rate (%): 43.70 -> 44.84 | Helped |
| integrate four visual cues rather than use cue C1 alone (ablation) | L-All · VIPeR | rank-1 matching rate (%): 43.70 -> 51.04 | Helped |
Closest papers by meaning
- Deep Spatial Feature Reconstruction for Partial Person Re-Identification: Alignment-Free Approach (CVPR 2018 · similarity 0.89)
- Relation-Aware Global Attention for Person Re-Identification (CVPR 2020 · similarity 0.88)
- Improving Person Re-Identification via Pose-Aware Multi-Shot Matching (CVPR 2016 · similarity 0.88)
- Diversity Regularized Spatiotemporal Attention for Video-Based Person Re-Identification (CVPR 2018 · similarity 0.88)
- A Pose-Sensitive Embedding for Person Re-Identification With Expanded Cross Neighborhood Re-Ranking (CVPR 2018 · similarity 0.88)
- Large Scale Similarity Learning Using Similar Pairs for Person Verification (AAAI 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.