Research map / Label-efficient and robust learning / Recognition and long-tail
Learning Longterm Representations for Person Re-Identification Using Radio Signals
Lijie Fan, Tianhong Li, Rongyao Fang, Rumen Hristov, Yuan Yuan, Dina Katabi
Check 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 RF-ReID instead of the strongest RGB video baseline | Person ReID · RRD-Campus | mAP: 48.1 -> 59.5 | Improved |
| Use RF-ReID instead of the strongest RGB video baseline | Person ReID · RRD-Campus | CMC-1: 69.2 -> 82.1 | Improved |
| Use RF-ReID instead of the strongest RGB video baseline | Person ReID · RRD-Campus | CMC-5: 89.1 -> 95.5 | Improved |
| Train a single model on combined RRD datasets rather than separately | RF-ReID · RRD-Campus | mAP: 59.5 -> 60.7 | Improved |
| Train a single model on combined RRD datasets rather than separately | RF-ReID · RRD-Home | mAP: 46.4 -> 49.4 | Improved |
| Add skeleton loss to the ReID training objective (ablation) | RF-ReID · RRD-Campus | mAP: 57.3 -> 59.5 | Improved |
| Add skeleton loss to the ReID training objective (ablation) | RF-ReID · RRD-Campus | CMC-1: 78.2 -> 82.1 | Improved |
| Add skeleton loss to the ReID training objective (ablation) | RF-ReID · RRD-Campus | CMC-5: 94.4 -> 95.5 | Improved |
| Replace average pooling in the first block with first-block attention (ablation) | RF-ReID hierarchical attention · RRD-Campus | mAP: 55.4 -> 58.6 | Improved |
| Replace average pooling in the second block with second-block attention (ablation) | RF-ReID hierarchical attention · RRD-Campus | mAP: 55.4 -> 58.3 | Improved |
| Use both hierarchical attention blocks rather than average pooling (ablation) | RF-ReID · RRD-Campus | mAP: 55.4 -> 59.5 | Improved |
| Use both hierarchical attention blocks rather than average pooling (ablation) | RF-ReID · RRD-Campus | CMC-1: 74.5 -> 82.1 | Improved |
Closest papers by meaning
- Learning Clothing and Pose Invariant 3D Shape Representation for Long-Term Person Re-Identification (ICCV 2023 · similarity 0.90)
- Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions (CVPR 2024 · similarity 0.87)
- Learning Continual Compatible Representation for Re-indexing Free Lifelong Person Re-identification (CVPR 2024 · similarity 0.86)
- Person De-reidentification: A Variation-guided Identity Shift Modeling (CVPR 2025 · similarity 0.86)
- From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization (CVPR 2025 · similarity 0.86)
- From Laboratory to Real World: A New Benchmark Towards Privacy-Preserved Visible-Infrared Person Re-Identification (CVPR 2025 · similarity 0.85)
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.
