Research map / Label-efficient and robust learning / Domain adaptation and generalization
Unsupervised Cross-Dataset Person Re-Identification by Transfer Learning of Spatial-Temporal Patterns
Read the paperCheck 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 spatial-temporal pattern fusion to the transferred visual classifier (ablation) | TFusion · Market1501→GRID | rank-1: 17.80 -> 49.60 | Helped |
| add spatial-temporal pattern fusion to the transferred visual classifier (ablation) | TFusion · CUHK01→GRID | rank-1: 10.70 -> 30.90 | Helped |
| add spatial-temporal pattern fusion to the transferred visual classifier (ablation) | TFusion · VIPeR→GRID | rank-1: 9.70 -> 28.40 | Helped |
| add spatial-temporal pattern fusion to the transferred visual classifier (ablation) | TFusion · GRID→Market1501 | rank-1: 20.72 -> 51.16 | Helped |
| add spatial-temporal pattern fusion to the transferred visual classifier (ablation) | TFusion · VIPeR→Market1501 | rank-1: 24.70 -> 56.18 | Helped |
| add spatial-temporal pattern fusion to the transferred visual classifier (ablation) | TFusion · CUHK01→Market1501 | rank-1: 29.39 -> 56.53 | Helped |
| add learning-to-rank optimization and mutual updates of the visual and fusion classifiers (ablation) | TFusion · Market1501→GRID | rank-1: 49.60 -> 60.40 | Helped |
| add learning-to-rank optimization and mutual updates of the visual and fusion classifiers (ablation) | TFusion · CUHK01→GRID | rank-1: 30.90 -> 50.90 | Helped |
| add learning-to-rank optimization and mutual updates of the visual and fusion classifiers (ablation) | TFusion · VIPeR→GRID | rank-1: 28.40 -> 52.70 | Helped |
| add learning-to-rank optimization and mutual updates of the visual and fusion classifiers (ablation) | TFusion · GRID→Market1501 | rank-1: 51.16 -> 58.22 | Helped |
| add learning-to-rank optimization and mutual updates of the visual and fusion classifiers (ablation) | TFusion · VIPeR→Market1501 | rank-1: 56.18 -> 59.17 | Helped |
| add learning-to-rank optimization and mutual updates of the visual and fusion classifiers (ablation) | TFusion · CUHK01→Market1501 | rank-1: 56.53 -> 60.75 | Helped |
Closest papers by meaning
- Unsupervised Cross-Dataset Transfer Learning for Person Re-Identification (CVPR 2016 · similarity 0.91)
- Tracklet Self-Supervised Learning for Unsupervised Person Re-Identification (AAAI 2020 · similarity 0.88)
- Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification (CVPR 2021 · similarity 0.88)
- Unsupervised Adaptive Re-Identification in Open World Dynamic Camera Networks (CVPR 2017 · similarity 0.88)
- Camera-Aware Proxies for Unsupervised Person Re-Identification (AAAI 2021 · similarity 0.88)
- Unsupervised Pre-Training for Person Re-Identification (CVPR 2021 · 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.