Text-to-Image Person Re-identification on CUHK-PEDES
78.18Rank-1ICL
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| ICLImage Enc.=CLIP-ViT, Text Enc.=CLIP-X., Interp.=×2026.04 | 78.18 | — | — | 69.58 | |
| InterPartAbilityImage Enc.=CLIP-ViT, Text Enc.=CLIP-X., Interp.=✓2026.04 | 78.17 | — | — | 69.2 | |
| MARSImage Enc.=Swin-B, Text Enc.=BERT, Interp.=×2026.04 | 77.62 | — | — | 71.71 | |
| MARSCategory=T2I-only2026.06 | 77.6 | — | — | 71.7 | |
| NAMImage Enc.=CLIP-ViT, Text Enc.=CLIP-X., Interp.=×2026.04 | 77.47 | — | — | 69.43 | |
| DiCOImage Enc.=CLIP-ViT, Text Enc.=CLIP-X., Interp.=✓2026.04 | 77.21 | — | — | — | |
| APTMImage Enc.=Swin-B, Text Enc.=BERT, Interp.=×2026.04 | 76.53 | — | — | 66.91 | |
| RaSaImage Backbone=ViT-B, Text Backbone=BERT2023.05 | 76.51 | 90.29 | 94.25 | — | |
| RaSaCategory=T2I-only2026.06 | 76.5 | — | — | 69.4 | |
| HPLCategory=Unified2026.06 | 76.3 | — | — | 70.9 | |
| APTMImage Backbone=Swin-B, Text Backbone=BERT2023.05 | 76.17 | 89.47 | 93.57 | — | |
| RDECategory=T2I-only2026.06 | 75.9 | — | — | 67.6 | |
| CFAMCategory=T2I-only2026.06 | 75.6 | — | — | 67.3 | |
| PLIPImage Backbone=Swin-B, Text Backbone=BERT2023.05 | 75.36 | 90.86 | 94.87 | — | |
| PLOTImage Enc.=CLIP-ViT, Text Enc.=CLIP-X., Interp.=✓2026.04 | 75.28 | — | — | — | |
| OursCategory=Unified2026.06 | 75.2 | — | — | 68.6 | |
| IRMCategory=Unified2026.06 | 74.2 | — | — | 66.5 | |
| IRRAImage Enc.=CLIP-ViT, Text Enc.=CLIP-X., Interp.=×2026.04 | 74.05 | — | — | 66.57 | |
| PLIPImage Backbone=RN152, Text Backbone=BERT2023.05 | 73.68 | 90.35 | 94.22 | — | |
| IRRACategory=T2I-only2026.06 | 73.4 | — | — | 66.1 | |
| IRRAImage Backbone=ViT-B, Text Backbone=Xformer2023.05 | 73.38 | 89.93 | 93.71 | — | |
| PLIPImage Backbone=RN101, Text Backbone=BERT2023.05 | 72.34 | 89.15 | 93.46 | — | |
| PLIPImage Backbone=RN50, Text Backbone=BERT2023.05 | 71.13 | 87.57 | 92.81 | — | |
| CFineImage Backbone=ViT-B, Text Backbone=BERT2023.05 | 69.57 | 85.93 | 91.15 | — | |
| IVTImage Backbone=ViT-B, Text Backbone=BERT2023.05 | 65.59 | 83.11 | 89.21 | — | |
| LGURImage Backbone=RN50, Text Backbone=BERT2023.05 | 64.21 | 81.94 | 87.93 | — | |
| TIPCBImage Backbone=RN50, Text Backbone=BERT2023.05 | 63.63 | 82.82 | 89.01 | — | |
| LapsCoreImage Backbone=RN50, Text Backbone=BERT2023.05 | 63.4 | — | 87.8 | — | |
| SSANBackbone=ResNet-502021.07 | 61.37 | 80.15 | 86.73 | — | |
| SSANImage Backbone=RN50, Text Backbone=LSTM2023.05 | 61.37 | 80.15 | 86.73 | — | |
| NAFSImage Backbone=RN50, Text Backbone=BERT2023.05 | 59.94 | 79.86 | 86.7 | — | |
| ViTAABackbone=ResNet-502021.07 | 55.97 | 75.84 | 83.52 | — | |
| VITAAImage Backbone=RN50, Text Backbone=LSTM2023.05 | 55.97 | 75.84 | 83.52 | — | |
| SCANBackbone=ResNet-502021.07 | 55.86 | 75.97 | 83.69 | — | |
| SSANBackbone=VGG-162021.07 | 55.52 | 76.17 | 83.45 | — | |
| TDEBackbone=ResNet-502021.07 | 55.25 | 77.46 | 84.56 | — | |
| Baseline in SSANBackbone=ResNet-502021.07 | 54.68 | 75.42 | 82.73 | — | |
| PMABackbone=ResNet-502021.07 | 53.81 | 73.54 | 81.23 | — | |
| MIABackbone=ResNet-502021.07 | 53.1 | 75 | 82.9 | — | |
| TDEBackbone=VGG-162021.07 | 52.37 | 75.26 | 83.31 | — | |
| Baseline in ViTAABackbone=ResNet-502021.07 | 52.27 | 73.33 | 81.61 | — | |
| CMPM + CMPCBackbone=ResNet-502021.07 | 49.37 | — | 79.27 | — | |
| CMPM/CImage Backbone=RN50, Text Backbone=LSTM2023.05 | 49.37 | 79.27 | — | — | |
| MIABackbone=VGG-162021.07 | 48 | 70.7 | 79.3 | — | |
| PMABackbone=VGG-162021.07 | 47.02 | 68.54 | 78.06 | — | |
| Dual PathBackbone=ResNet-502021.07 | 44.4 | 66.26 | 75.07 | — | |
| ReTextCategory=Unified2026.06 | 34.7 | — | — | 37.6 | |
| PWM-ATHBackbone=VGG-162021.07 | 27.14 | 49.45 | 61.02 | — | |
| IATVMBackbone=VGG-162021.07 | 25.94 | — | 60.48 | — | |
| GNA-RNNBackbone=VGG-162021.07 | 19.05 | — | 53.64 | — | |
| GNA-RNNImage Backbone=VGG, Text Backbone=LSTM2023.05 | 19.05 | 53.64 | — | — |