Research map / Graph learning / Knowledge and temporal graphs
Person Re-Identification Using Heterogeneous Local Graph Attention Networks
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 corresponding-part inter-local neighbors (ablation) | HLGAT · Market-1501 | mAP: 84.0 -> 93.4 | Helped |
| add corresponding-part inter-local neighbors (ablation) | HLGAT · CUHK03 | mAP: 59.6 -> 80.6 | Helped |
| add corresponding-part inter-local neighbors (ablation) | HLGAT · DukeMTMC-reID | mAP: 75.6 -> 87.3 | Helped |
| add corresponding-part inter-local neighbors (ablation) | HLGAT · MSMT17 | mAP: 54.6 -> 73.2 | Helped |
| add adjacent-part inter-local neighbors (ablation) | HLGAT · CUHK03 | mAP: 79.5 -> 80.6 | Helped |
| add adjacent-part inter-local neighbors (ablation) | HLGAT · Market-1501 | mAP: 92.7 -> 93.4 | Helped |
| add adjacent-part inter-local neighbors (ablation) | HLGAT · DukeMTMC-reID | mAP: 86.5 -> 87.3 | Helped |
| add adjacent-part inter-local neighbors (ablation) | HLGAT · MSMT17 | mAP: 71.2 -> 73.2 | Helped |
| add attention regularization loss (ablation) | HLGAT · Market-1501 | mAP: 91.4 -> 93.4 | Helped |
| add attention regularization loss (ablation) | HLGAT · CUHK03 | mAP: 78.3 -> 80.6 | Helped |
| add attention regularization loss (ablation) | HLGAT · DukeMTMC-reID | mAP: 85.3 -> 87.3 | Helped |
| add attention regularization loss (ablation) | HLGAT · MSMT17 | mAP: 71.0 -> 73.2 | Helped |
Closest papers by meaning
- Learning Hybrid Relationships for Person Re-identification (AAAI 2021 · similarity 0.90)
- Relation-Aware Global Attention for Person Re-Identification (CVPR 2020 · similarity 0.90)
- Spatial-Temporal Graph Convolutional Network for Video-Based Person Re-Identification (CVPR 2020 · similarity 0.89)
- Harmonious Attention Network for Person Re-Identification (CVPR 2018 · similarity 0.88)
- Spatial-Temporal Correlation and Topology Learning for Person Re-Identification in Videos (CVPR 2021 · similarity 0.88)
- Re-Identification With Consistent Attentive Siamese Networks (CVPR 2019 · 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.