Research map / Label-efficient and robust learning / Recognition and long-tail
Dynamic Label Graph Matching for Unsupervised Video Re-Identification
Mang Ye, Andy J. Ma, Liang Zheng, Jiawei Li, Pong C. Yuen
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 label re-weighting (ablation) | DGM + MLAPG · PRID-2011 | rank-1 accuracy: 72.6 -> 73.1 | Improved |
| add label re-weighting (ablation) | DGM + MLAPG · iLIDS-VID | rank-1 accuracy: 35.6 -> 37.1 | Improved |
| add label re-weighting (ablation) | DGM + MLAPG · MARS | rank-1 accuracy: 22.8 -> 24.6 | Improved |
| add 20% distractor persons to training | DGM + MLAPG · PRID-2011 | rank-1 accuracy: 73.1 -> 72.1 | Hurt |
| add 50% distractor persons to training | DGM + MLAPG · PRID-2011 | rank-1 accuracy: 73.1 -> 70.3 | Hurt |
| split 20% of sequences into trajectory segments | DGM + MLAPG · PRID-2011 | rank-1 accuracy: 73.1 -> 72.3 | Hurt |
| split 50% of sequences into trajectory segments | DGM + MLAPG · PRID-2011 | rank-1 accuracy: 73.1 -> 71.1 | Hurt |
| use deep IDE model instead of MLAPG on estimated labels | DGM · PRID-2011 | rank-1 accuracy: 73.1 -> 56.4 | Hurt |
| use deep IDE model instead of MLAPG on estimated labels | DGM · iLIDS-VID | rank-1 accuracy: 37.1 -> 36.2 | No clear effect |
| use deep IDE model instead of MLAPG on estimated labels | DGM · MARS | rank-1 accuracy: 24.6 -> 36.8 | Improved |
Closest papers by meaning
- Intra-Inter Camera Similarity for Unsupervised Person Re-Identification (CVPR 2021 · similarity 0.89)
- Intra-Inter Domain Similarity for Unsupervised Person Re-Identification (TPAMI 2022 · similarity 0.88)
- Deep Graph Metric Learning for Weakly Supervised Person Re-Identification (TPAMI 2021 · similarity 0.88)
- Unsupervised Person Re-Identification by Camera-Aware Similarity Consistency Learning (ICCV 2019 · similarity 0.88)
- Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification (CVPR 2021 · similarity 0.88)
- Unsupervised Domain Adaptation for Person Re-identification via Heterogeneous Graph Alignment (AAAI 2021 · 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.
