Text Based Person Retrieval With Noisy
평가 지표
Rank 10
Rank-1
Rank-5
mAP
mINP
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | Rank 10 | Rank-1 | Rank-5 | mAP | mINP | Paper Title | Repository |
|---|---|---|---|---|---|---|---|
| IVT | 85.61 | 58.59 | 78.51 | 57.19 | 45.78 | See Finer, See More: Implicit Modality Alignment for Text-based Person Retrieval | |
| SSAN | 77.42 | 46.52 | 68.36 | 42.49 | 28.13 | Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification | |
| RDE | 93.63 | 74.46 | 89.42 | 66.13 | 49.66 | Noisy-Correspondence Learning for Text-to-Image Person Re-identification | |
| IRRA | 92.20 | 69.74 | 87.09 | 62.28 | 45.84 | Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval | - |
| DECL | 91.93 | 70.29 | 87.04 | 62.84 | 46.54 | Deep Evidential Learning with Noisy Correspondence for Cross-Modal Retrieval | |
| CLIP-C | 90.89 | 66.41 | 85.15 | 59.36 | 43.02 | Learning Transferable Visual Models From Natural Language Supervision |
0 of 6 row(s) selected.