AI Paper Atlas

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

ICCV 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 855 citations (OpenAlex)

Read the paper

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 changedWhereMeasuredEffect
add part features to the global feature (ablation)Global Only · CUHK03 labeledrank-1 accuracy: 79.83 -> 85.07Improved
add part features to the global feature (ablation)Global Only · CUHK03 detectedrank-1 accuracy: 71.89 -> 76.33Improved
add part features to the global feature (ablation)Global Only · Market-1501mAP: 52.84 -> 62.20Improved
add part features to the global feature (ablation)Global Only · VIPeRrank-1 accuracy: 37.97 -> 48.42Improved
add global feature to part-only model (ablation)Part Only · CUHK03 labeledrank-1 accuracy: 53.73 -> 85.07Improved
add Feature Embedding sub-Net (pose transformation) (ablation)Global+Part · CUHK03 labeledrank-1 accuracy: 85.07 -> 87.15Improved
add Feature Embedding sub-Net (pose transformation) (ablation)Global+Part · Market-1501rank-1 accuracy: 81.74 -> 83.05Improved
add Feature Embedding sub-Net (pose transformation) (ablation)Global+Part · VIPeRrank-1 accuracy: 48.42 -> 50.32Improved
add Feature Weighting sub-Net (ablation)Global+Part · CUHK03 labeledrank-1 accuracy: 85.07 -> 86.41Improved
add Feature Weighting sub-Net (ablation)Global+Part · VIPeRrank-1 accuracy: 48.42 -> 50.00Improved
add both FEN and FWN (full PDC) (ablation)Global+Part · Market-1501rank-1 accuracy: 81.74 -> 84.14Improved
use one nonlinear weight layer instead of one linear weight layer in FWN (ablation)FWN · CUHK03 labeledrank-1 accuracy: 88.18 -> 88.70Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy