Research map / Label-efficient and robust learning / Recognition and long-tail
Learning Multi-Attention Context Graph for Group-Based Re-Identification
Yichao Yan, Jie Qin, Bingbing Ni, Jiaxin Chen, Li Liu, Fan Zhu, Wei‐Shi Zheng, Xiaokang Yang, Ling Shao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| model each group with a GNN over person features (ablation) | Local CNN · CSG | Rank-1 accuracy: 52.7 -> 58.7 | Improved |
| use part-level node features (ablation) | GNN · CSG | Rank-1 accuracy: 58.7 -> 60.1 | Improved |
| add intra-graph attention (ablation) | Part GNN · CSG | Rank-1 accuracy: 60.1 -> 62.2 | Improved |
| add inter-graph attention (ablation) | Part GNN · CSG | Rank-1 accuracy: 60.1 -> 62.8 | Improved |
| add readout self-attention instead of mean pooling (ablation) | Part GNN · CSG | Rank-1 accuracy: 60.1 -> 61.2 | Improved |
| combine all multi-level attention (ablation) | Part GNN · CSG | Rank-1 accuracy: 60.1 -> 63.2 | Improved |
| add person correspondence loss (ablation) | MACG · CSG (group-aware person re-id) | mAP: 64.2 -> 66.5 | Improved |
| fully connected context graph versus top-K neighbors (ablation) | MACG · CSG | Rank-1 accuracy | Improved |
| build graph from attribute similarity or add re-ranking (ablation) | MACG · CSG | Rank-1 accuracy | No clear effect |
| use two-layer GNN instead of other depths (ablation) | MACG · CSG | Rank-1 accuracy | Improved |
| use ResNet101 instead of ResNet50 (ablation) | MACG · CSG | Rank-1 accuracy | No clear effect |
| use detected boxes (Faster R-CNN) instead of ground truth | MACG · CSG | Rank-1 accuracy: 63.2 -> 59.9 | Hurt |
Closest papers by meaning
- Group Re-Identification via Unsupervised Transfer of Sparse Features Encoding (ICCV 2017 · similarity 0.90)
- Separable Spatial-Temporal Residual Graph for Cloth-Changing Group Re-Identification (TPAMI 2024 · similarity 0.90)
- A Systematic Evaluation and Benchmark for Person Re-Identification: Features, Metrics, and Datasets (TPAMI 2018 · similarity 0.89)
- Keypoint Message Passing for Video-Based Person Re-identification (AAAI 2022 · similarity 0.89)
- Unsupervised Group Re-identification via Adaptive Clustering-Driven Progressive Learning (AAAI 2024 · similarity 0.88)
- Cheb-GR: Rethinking K-nearest Neighbor Search in Re-ranking for Person Re-identification (CVPR 2025 · 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.
