Research map / Label-efficient and robust learning / Domain adaptation and generalization
Dynamic-Static Collaboration for Unsupervised Domain Adaptive Video-Based Visible-Infrared Person Re-Identification
Jiaxu Leng, Zhengjie Wang, Shuang Li, Xinbo Gao
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 DSLU (dynamic-static label unification) (ablation) | DSC (B+Clu.) · BUPTCampus RGB->IR | mAP (%): 27.5 -> 39.3 | Improved |
| add DSJL on top of clustering + DSLU (ablation) | DSC (B+Clu.) · BUPTCampus RGB->IR | mAP (%): 39.3 -> 40.0 | Improved |
| add DSJL without DSLU (ablation) | DSC (B+Clu.) · BUPTCampus RGB->IR | mAP (%): 27.5 -> 27.7 | No clear effect |
| add inter-modal unification in DSLU (ablation) | DSC (B+Clu.) · BUPTCampus RGB->IR | mAP (%): 27.7 -> 35.5 | Improved |
| add intra-modal correction alone in DSLU (ablation) | DSC (B+Clu.) · BUPTCampus RGB->IR | mAP (%): 27.7 -> 29.4 | No clear effect |
| combine intra- and inter-modal correction in DSLU (ablation) | DSC (B+Clu.) · BUPTCampus RGB->IR | mAP (%): 35.5 -> 40.0 | Improved |
| add intra-modal neighbor learning in DSJL (with inter) (ablation) | DSC (B+Clu.) · BUPTCampus RGB->IR | mAP (%): 38.0 -> 40.0 | Improved |
| add inter-modal neighbor learning alone in DSJL (ablation) | DSC (B+Clu.) · BUPTCampus RGB->IR | mAP (%): 39.3 -> 38.0 | Hurt |
| use balanced similarity weights lambda_dy = lambda_st = 1.0 (ablation) | DSC (B+Clu.) · BUPTCampus RGB->IR | mAP (%): 35.9 -> 40.0 | Improved |
| use alpha = 0.9 neighbor threshold and top-k = 20 (ablation) | DSC (B+Clu.) · BUPTCampus | mAP | Improved |
| apply DSC vs cross-domain baseline | DSC (B+Clu.) · HITSZ-VCM RGB->IR | Rank-1 (%): 40.1 -> 63.8 | Improved |
| apply DSC vs strongest unsupervised baseline PGM | DSC (B+Clu.) · BUPTCampus RGB->IR | Rank-1 (%): 32.2 -> 41.8 | Improved |
Closest papers by meaning
- Towards Grand Unified Representation Learning for Unsupervised Visible-Infrared Person Re-Identification (ICCV 2023 · similarity 0.90)
- Relieving Universal Label Noise for Unsupervised Visible-Infrared Person Re-Identification by Inferring from Neighbors (AAAI 2025 · similarity 0.90)
- Learning Commonality, Divergence and Variety for Unsupervised Visible-Infrared Person Re-identification (NeurIPS 2024 · similarity 0.90)
- Shallow-Deep Collaborative Learning for Unsupervised Visible-Infrared Person Re-Identification (CVPR 2024 · similarity 0.88)
- TokenMatcher: Diverse Tokens Matching for Unsupervised Visible-Infrared Person Re-Identification (AAAI 2025 · similarity 0.88)
- From Laboratory to Real World: A New Benchmark Towards Privacy-Preserved Visible-Infrared Person Re-Identification (CVPR 2025 · 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.
