Text Based Person Retrieval With Noisy 2
評価指標
Rank 1
Rank 10
Rank 5
mAP
mINP
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | Rank 1 | Rank 10 | Rank 5 | mAP | mINP | Paper Title | Repository |
|---|---|---|---|---|---|---|---|
| CLIP-C | 54.45 | 86.70 | 77.80 | 42.58 | 21.38 | Learning Transferable Visual Models From Natural Language Supervision | |
| SSAN | 35.10 | 71.45 | 60.00 | 28.90 | 12.08 | Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification | |
| IVT | 43.65 | 75.70 | 66.50 | 37.22 | 20.47 | See Finer, See More: Implicit Modality Alignment for Text-based Person Retrieval | |
| IRRA | 58.75 | 88.25 | 81.90 | 46.38 | 24.78 | Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval | - |
| RDE | 64.45 | 90.00 | 83.50 | 49.78 | 27.43 | Noisy-Correspondence Learning for Text-to-Image Person Re-identification | |
| DECL | 61.75 | 86.90 | 80.70 | 47.70 | 26.07 | Deep Evidential Learning with Noisy Correspondence for Cross-Modal Retrieval |
0 of 6 row(s) selected.