Research map / Label-efficient and robust learning / Recognition and long-tail
Towards Cross-Modal Preservation, Consistency and Alignment for Privacy-Preserving Visible-Infrared Person Re-Identification
Yudi Xie, Zhongao Zhou, Bin Yang, Zhenghan Chen, Mang Ye
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 |
|---|---|---|---|
| use PPA instead of SecureReID for raw-to-raw retrieval with mosaic-initialized targets | SecureReID adapted with AGW · SYSU-MM01 all search (Raw to Raw) | Rank-1 (%): 35.6 -> 60.7 | Improved |
| use PPA instead of SecureReID for raw-to-raw retrieval on RegDB | SecureReID adapted with AGW · RegDB infrared to visible (Raw to Raw) | Rank-1 (%): 45.9 -> 80.5 | Improved |
| use PPA instead of SecureReID in Anon to Anon | SecureReID adapted with AGW · SYSU-MM01 all search (Anon to Anon) | Rank-1 (%): 32.2 -> 46.2 | Improved |
| use PPA for anonymization quality, blur init | SecureReID · SYSU-MM01 all search, visible | SSIM / PSNR: SSIM 0.16 -> 0.11, PSNR 9.5 -> 8.2 | Improved |
| PPA anonymization on RegDB RGB with mosaic init | SecureReID · RegDB visible | SSIM: 0.14 -> 0.33 | Hurt |
| add Keypoint-Preserving Regularization (ablation) | baseline · SYSU-MM01 all search, Anon to Raw | Rank-1 (%): 47.9 -> 51.6 | Improved |
| add DCMA (ablation) | baseline · SYSU-MM01 all search, Anon to Raw | Rank-1 (%): 47.9 -> 49.9 | Improved |
| combine KPR and DCMA (ablation) | baseline · SYSU-MM01 all search, Anon to Raw | Rank-1 (%): 47.9 -> 53.3 | Improved |
| add KPR and DCMA (ablation) | baseline · SYSU-MM01 indoor search, Anon to Raw | Rank-1 (%): 59.1 -> 62.9 | Improved |
| set KPR weight delta to 1.0 (ablation) | PPA · SYSU-MM01 | Rank-1 (%) | Improved |
Closest papers by meaning
- Learning by Aligning: Visible-Infrared Person Re-Identification Using Cross-Modal Correspondences (ICCV 2021 · similarity 0.91)
- Blurring Modal Boundaries: A Unified Survey from Single- to Multi-modal Person Re-ldentification (IJCV 2026 · similarity 0.91)
- From Laboratory to Real World: A New Benchmark Towards Privacy-Preserved Visible-Infrared Person Re-Identification (CVPR 2025 · similarity 0.90)
- TokenMatcher: Diverse Tokens Matching for Unsupervised Visible-Infrared Person Re-Identification (AAAI 2025 · similarity 0.88)
- Person De-reidentification: A Variation-guided Identity Shift Modeling (CVPR 2025 · similarity 0.88)
- Cross-Modality Perturbation Synergy Attack for Person Re-identification (NeurIPS 2024 · 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.
