Research map / Label-efficient and robust learning / Recognition and long-tail
Stepwise Metric Promotion for Unsupervised Video Person Re-Identification
Zimo Liu, Dong Wang, Huchuan Lu
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 |
|---|---|---|---|
| extend nearest neighbor number K from 1 to 5 (ablation) | Ours (LOMO) · PRID 2011 | rank-1 (%): 70.8 -> 80.9 | Improved |
| extend K from 1 to 20 (ablation) | Ours (LOMO) · PRID 2011 | rank-1 (%): 70.8 -> 84.27 | Improved |
| extend K from 20 to 50 (ablation) | Ours (LOMO) · PRID 2011 | rank-1 (%): 84.27 -> 78.65 | Hurt |
| extend K from 1 to 10 on label recall (ablation) | Ours (LOMO) · PRID 2011 | Recall: 0.5168 -> 0.8314 | Improved |
| iterative negative label propagation training (ablation) | Ours (LOMO) · PRID 2011 | rank-1 matching rate: improves by around 30% | Improved |
| use set-to-set distance instead of max-pooling at test time (ablation) | Ours (LOMO) · PRID 2011 | CMC: no numbers given | Improved |
| use supervised XQDA instead of unsupervised method on MARS | Ours · MARS (LOMO) | rank-1 (%): 26.92 vs 23.59 | Hurt |
| use unsupervised method versus supervised XQDA on iLIDS-VID | Ours (LOMO) · iLIDS-VID | rank-1 (%): 58.7 vs 41.7 | Hurt |
Closest papers by meaning
- Unsupervised Tracklet Person Re-Identification (TPAMI 2019 · similarity 0.93)
- Tracklet Self-Supervised Learning for Unsupervised Person Re-Identification (AAAI 2020 · similarity 0.93)
- Unsupervised Person Re-identification by Deep Learning Tracklet Association (ECCV 2018 · similarity 0.92)
- Exploit the Unknown Gradually: One-Shot Video-Based Person Re-Identification by Stepwise Learning (CVPR 2018 · similarity 0.92)
- Cross-View Asymmetric Metric Learning for Unsupervised Person Re-Identification (ICCV 2017 · similarity 0.92)
- Weakly Supervised Tracklet Association Learning With Video Labels for Person Re-Identification (TPAMI 2023 · similarity 0.91)
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.
