| Paper | Code | Rank-1 | Rank 10 | Rank-5 | mAP | mINP | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|---|---|
| Noisy-Correspondence Learning for Text-to-Image Person Re-identification | ✓ Link | 74.46 | 93.63 | 89.42 | 66.13 | 49.66 | RDE | 2023-08-19 |
| Deep Evidential Learning with Noisy Correspondence for Cross-Modal Retrieval | ✓ Link | 70.29 | 91.93 | 87.04 | 62.84 | 46.54 | DECL | 2022-10-10 |
| Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval | ✓ Link | 69.74 | 92.20 | 87.09 | 62.28 | 45.84 | IRRA | 2023-03-22 |
| Learning Transferable Visual Models From Natural Language Supervision | ✓ Link | 66.41 | 90.89 | 85.15 | 59.36 | 43.02 | CLIP-C | 2021-02-26 |
| See Finer, See More: Implicit Modality Alignment for Text-based Person Retrieval | ✓ Link | 58.59 | 85.61 | 78.51 | 57.19 | 45.78 | IVT | 2022-08-18 |
| Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification | ✓ Link | 46.52 | 77.42 | 68.36 | 42.49 | 28.13 | SSAN | 2021-07-27 |