Research map / Label-efficient and robust learning / Recognition and long-tail
Pose-Driven Deep Convolutional Model for Person Re-Identification
Chi Su, Jianing Li, Shiliang Zhang, Junliang Xing, Wen Gao, Qi Tian
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 part features to the global feature (ablation) | Global Only · CUHK03 labeled | rank-1 accuracy: 79.83 -> 85.07 | Improved |
| add part features to the global feature (ablation) | Global Only · CUHK03 detected | rank-1 accuracy: 71.89 -> 76.33 | Improved |
| add part features to the global feature (ablation) | Global Only · Market-1501 | mAP: 52.84 -> 62.20 | Improved |
| add part features to the global feature (ablation) | Global Only · VIPeR | rank-1 accuracy: 37.97 -> 48.42 | Improved |
| add global feature to part-only model (ablation) | Part Only · CUHK03 labeled | rank-1 accuracy: 53.73 -> 85.07 | Improved |
| add Feature Embedding sub-Net (pose transformation) (ablation) | Global+Part · CUHK03 labeled | rank-1 accuracy: 85.07 -> 87.15 | Improved |
| add Feature Embedding sub-Net (pose transformation) (ablation) | Global+Part · Market-1501 | rank-1 accuracy: 81.74 -> 83.05 | Improved |
| add Feature Embedding sub-Net (pose transformation) (ablation) | Global+Part · VIPeR | rank-1 accuracy: 48.42 -> 50.32 | Improved |
| add Feature Weighting sub-Net (ablation) | Global+Part · CUHK03 labeled | rank-1 accuracy: 85.07 -> 86.41 | Improved |
| add Feature Weighting sub-Net (ablation) | Global+Part · VIPeR | rank-1 accuracy: 48.42 -> 50.00 | Improved |
| add both FEN and FWN (full PDC) (ablation) | Global+Part · Market-1501 | rank-1 accuracy: 81.74 -> 84.14 | Improved |
| use one nonlinear weight layer instead of one linear weight layer in FWN (ablation) | FWN · CUHK03 labeled | rank-1 accuracy: 88.18 -> 88.70 | Improved |
Closest papers by meaning
- Deeply-Learned Part-Aligned Representations for Person Re-Identification (ICCV 2017 · similarity 0.92)
- Deep Neural Networks with Inexact Matching for Person Re-Identification (NeurIPS 2016 · similarity 0.91)
- Interaction-And-Aggregation Network for Person Re-Identification (CVPR 2019 · similarity 0.91)
- Multi-Scale Deep Learning Architectures for Person Re-Identification (ICCV 2017 · similarity 0.90)
- Interpretable and Generalizable Person Re-Identification with Query-Adaptive Convolution and Temporal Lifting (ECCV 2020 · similarity 0.90)
- From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization (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.
