[CVPR 2022] Part-based Pseudo Label Refinement for Unsupervised Person Re-identification
active 2023-08-15 → 2025-07-09 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 695 days from 2023-08-15 to 2025-07-09. Pushes: 3 total, peak 1 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 5 total, peak 2 in a day. Comments: 3 total, peak 1 in a day. Stars: 20 total, peak 1 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| yoonkicho | 5 | 3 | 0 | 0 |
| koamd | 3 | 0 | 0 | 1 |
| qingsonghu08 | 1 | 0 | 0 | 1 |
| LYL-hub-source | 1 | 0 | 0 | 0 |
| newbie521 | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue#15yoonkicho2024-07-31 20:59A few questions about the code implementation
- Issue#17yoonkicho2024-07-31 20:59Hello Professor. When using the DukeMTMC dataset, labeled training can be run through, but the data for unlabeled training is very low. What is the reason?
- Issue comment#18koamd2024-03-21 15:15Clarification on training process
- Issue#18koamd2024-03-21 15:15Clarification on training process
- Issue#18koamd2024-03-18 17:48Clarification on training process
- Issue comment#10qingsonghu082023-11-24 08:36about Accuracy
- Issue comment#10newbie5212023-10-19 14:59about Accuracy
- Issue#17LYL-hub-source2023-08-30 08:55Hello Professor. When using the DukeMTMC dataset, labeled training can be run through, but the data for unlabeled training is very low. What is the reason?
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 20 stars here means stars gained during the window, not the repo's star count.