Research map / Vision-language and multimodal / Cross-modal learning
Multi-modal Multi-platform Person Re-Identification: Benchmark and Method
Ruiyang Ha, Songyi Jiang, Bin Li, Bikang Pan, Yihang Zhu, Junjie Zhang, Xiatian Zhu, Shaogang Gong, Jingya Wang
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 PM prompt (ablation) | Base ReID model · MP-ReID UR→GR | mAP (%): 71.04 -> 73.34 | Improved |
| add MS prompt (ablation) | Base ReID model · MP-ReID UR→GR | mAP (%): 71.04 -> 71.36 | No clear effect |
| add IE (ablation) | Base ReID model · MP-ReID UR→GR | mAP (%): 71.04 -> 71.22 | No clear effect |
| add IE to PM prompt (ablation) | Base ReID model · MP-ReID UR→GR | mAP (%): 73.34 -> 74.16 | Improved |
| add MS prompt (ablation) | Base ReID model · MP-ReID UT→GR | mAP (%): 17.81 -> 22.51 | Improved |
| add PM prompt (ablation) | Base ReID model · MP-ReID UT→GR | mAP (%): 17.81 -> 30.87 | Improved |
| add IE (ablation) | Base ReID model · MP-ReID UT→GR | mAP (%): 17.81 -> 20.23 | Improved |
| add IE to PM prompt (ablation) | Base ReID model · MP-ReID UT→GR | mAP (%): 30.87 -> 34.14 | Improved |
| add MS prompt (ablation) | Base ReID model · MP-ReID UR→UT | mAP (%): 31.11 -> 43.07 | Improved |
| add PM prompt (ablation) | Base ReID model · MP-ReID UR→UT | mAP (%): 31.11 -> 47.98 | Improved |
| add IE (ablation) | Base ReID model · MP-ReID UR→UT | mAP (%): 31.11 -> 42.73 | Improved |
| add IE to PM prompt (ablation) | Base ReID model · MP-ReID UR→UT | mAP (%): 47.98 -> 50.26 | Improved |
Closest papers by meaning
- Exert Diversity and Mitigate Bias: Domain Generalizable Person Re-identification with a Comprehensive Benchmark (IJCV 2024 · similarity 0.88)
- MARS: A Video Benchmark for Large-Scale Person Re-Identification (ECCV 2016 · similarity 0.88)
- Attribute-Image Person Re-identification via Modal-Consistent Metric Learning (IJCV 2023 · similarity 0.87)
- Joint Bilateral-Resolution Identity Modeling for Cross-Resolution Person Re-Identification (IJCV 2021 · similarity 0.86)
- FlexiReID: Adaptive Mixture of Expert for Multi-Modal Person Re-Identification (ICML 2025 · similarity 0.85)
- LiDAR-based Person Re-identification (CVPR 2024 · similarity 0.83)
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.
