Research map / Label-efficient and robust learning / Recognition and long-tail
Uncertainty Modeling for Group Re-Identification
Quan Zhang, Jianhuang Lai, Zhanxiang Feng, Xiaohua Xie
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 |
|---|---|---|---|
| add Group Layout Adaptation (GLA) (ablation) | Base · CSG | Rank-1: 68.7 -> 76.9 | Improved |
| add GLA (ablation) | Base · RoadGroup | Rank-1: 75.4 -> 81.5 | Improved |
| add GLA (ablation) | Base · iLIDS-MCTS | Rank-1: 53.6 -> 61.2 | Improved |
| add Member Variant Simulation (MVS) (ablation) | Base · CSG | Rank-1: 68.7 -> 74.3 | Improved |
| add MVS (ablation) | Base · RoadGroup | Rank-1: 75.4 -> 79.7 | Improved |
| add Group Relationship Construction Encoder (GRCE) (ablation) | Base · CSG | Rank-1: 68.7 -> 74.2 | Improved |
| add GRCE (ablation) | Base · iLIDS-MCTS | Rank-1: 53.6 -> 58.4 | Improved |
| add MVS to GLA (ablation) | Base + GLA · CSG | Rank-1: 76.9 -> 87.7 | Improved |
| add GRCE to GLA + MVS (ablation) | Base + GLA + MVS · CSG | Rank-1: 87.7 -> 94.4 | Improved |
| add GRCE to GLA + MVS (ablation) | Base + GLA + MVS · RoadGroup | Rank-1: 88.2 -> 90.1 | Improved |
| add GRCE to GLA + MVS (ablation) | Base + GLA + MVS · iLIDS-MCTS | Rank-1: 64.2 -> 67.8 | Improved |
| use GCUM instead of UMSOT | UMSOT · CSG | Rank-1: 93.6 -> 94.4 | Improved |
Closest papers by meaning
- Uncertainty Modeling with Second-Order Transformer for Group Re-identification (AAAI 2022 · similarity 0.92)
- Unsupervised Group Re-identification via Adaptive Clustering-Driven Progressive Learning (AAAI 2024 · similarity 0.90)
- Learning Multi-Attention Context Graph for Group-Based Re-Identification (TPAMI 2020 · similarity 0.89)
- Similarity Metric Learning for RGB-Infrared Group Re-Identification (CVPR 2023 · similarity 0.88)
- Calibrating Multi-modal Representations: A Pursuit of Group Robustness without Annotations (CVPR 2024 · similarity 0.84)
- Project-Probe-Aggregate: Efficient Fine-Tuning for Group Robustness (CVPR 2025 · similarity 0.84)
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.
