Text-based Person Search on ICFG-PEDES (test)
71.18R@1DAPL
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| DAPL2024.05 | 71.18 | 84.68 | 91.22 | 42.96 | — | |
| APTM2024.05 | 70.42 | 84.35 | 89.59 | 42.37 | — | |
| RaSa2024.05 | 69.27 | 84.42 | 89.44 | 42.91 | — | |
| OursVenue=WACV’26, Image enc.=CLIP-ViT, Text enc.=CLIP-Xformer, Setup=with CLIP backbone2026.01 | 69.23 | 82.84 | 87.62 | 43.8 | — | |
| AULVenue=AAAI’24, Image enc.=Swin-B, Text enc.=BERT, Setup=with using external tools or ReID-Domain Pre-training2026.01 | 69.16 | 83.32 | 88.37 | — | — | |
| DECL2024.05 | 68.73 | 83.33 | 88.58 | 39.42 | — | |
| CAMeLVenue=TIFS’25, Image enc.=SG-Former, Text enc.=BERT, Setup=with using external tools or ReID-Domain Pre-training2026.01 | 68.7 | 83.11 | 88.32 | 41.58 | — | |
| APTM#Parameter=214M2024.04 | 68.51 | 82.99 | 87.56 | 41.22 | — | |
| APTMVenue=MM, Method Type=Non-CLIP based, NNN=false2026.01 | 68.51 | 82.99 | 87.56 | 41.22 | — | |
| APTMVenue=MM’23, Image enc.=Swin-B, Text enc.=BERT, Setup=with using external tools or ReID-Domain Pre-training2026.01 | 68.51 | 82.99 | 87.56 | 41.22 | — | |
| Filtering-WoRA#Parameter=127M2024.04 | 68.35 | 83.1 | 87.53 | 42.6 | — | |
| WoRA-TBPSVenue=MM, Method Type=Non-CLIP based, NNN=false2026.01 | 68.35 | 83.1 | 87.53 | 42.6 | — | |
| Scale-TBPSVenue=Ours, Method Type=Non-CLIP based, NNN=true2026.01 | 68.24 | 83 | 87.63 | 45.68 | — | |
| Scale-TBPSVenue=Ours, Method Type=Non-CLIP based, NNN=false2026.01 | 68.22 | 82.09 | 86.8 | 45.16 | — | |
| ICLVenue=CVPR, Method Type=CLIP based, NNN=false2026.01 | 68.11 | 82.59 | 87.52 | 40.81 | — | |
| APTM#Parameter=214M, implementation=re-implemented baseline2024.04 | 67.81 | 82.7 | 87.32 | 41.22 | — | |
| RDEVenue=CVPR, Method Type=Non-CLIP based, NNN=false2026.01 | 67.68 | 82.47 | 87.36 | 40.06 | — | |
| RDEVenue=CVPR’24, Image enc.=CLIP-ViT, Text enc.=CLIP-Xformer, Setup=with CLIP backbone2026.01 | 67.68 | 82.47 | 87.36 | 40.06 | — | |
| MARS2024.07 | 67.6 | 81.47 | 85.79 | 44.93 | — | |
| MARSVenue=TOMM’25, Image enc.=Swin-B, Text enc.=BERT, Setup=with ALBEF backbone2026.01 | 67.6 | 81.47 | 85.79 | 44.93 | — | |
| CADAretrained=true2024.07 | 67.38 | 81.34 | 85.64 | 37.81 | — | |
| IRRA2024.05 | 67.04 | 82.28 | 87.66 | 39.83 | — | |
| RDEVenue=-, Method Type=Non-CLIP based, NNN=true2026.01 | 66.73 | 82.87 | 87.63 | 39.42 | — | |
| PLOTVenue=ECCV’24, Image enc.=CLIP-ViT, Text enc.=CLIP-Xformer, Setup=with CLIP backbone2026.01 | 65.76 | 81.39 | 86.73 | — | — | |
| MUMVenue=AAAI’24, Image enc.=CLIP-ViT, Text enc.=CLIP-Xformer, Setup=with CLIP backbone2026.01 | 65.62 | 80.54 | 85.83 | 38.78 | — | |
| DPVenue=AAAI’24, Image enc.=CLIP-ViT, Text enc.=CLIP-Xformer, Setup=with using external tools or ReID-Domain Pre-training2026.01 | 65.61 | 81.73 | 86.95 | 39.14 | — | |
| CFAMVenue=CVPR, Method Type=CLIP based, NNN=false2026.01 | 65.38 | 81.17 | 86.35 | 39.42 | — | |
| CFAM(L/14)Venue=CVPR’24, Image enc.=CLIP-ViT, Text enc.=CLIP-Xformer, Setup=with using external tools or ReID-Domain Pre-training2026.01 | 65.38 | 81.17 | 86.35 | 39.42 | — | |
| RaSaVLP=true2023.05 | 65.28 | 80.4 | 85.12 | 41.29 | — | |
| RaSaReference=IJCAI232023.08 | 65.28 | 80.4 | 85.12 | 41.29 | — | |
| RaSa#Parameter=210M2024.04 | 65.28 | 80.04 | 85.12 | 41.29 | — | |
| RaSa2024.07 | 65.28 | 80.4 | 85.12 | 41.29 | — | |
| RaSaVenue=IJCAI, Method Type=Non-CLIP based, NNN=false2026.01 | 65.28 | 80.4 | 85.12 | 41.29 | — | |
| RaSaVenue=IJCAI’23, Image enc.=Swin-B, Text enc.=BERT, Setup=with ALBEF backbone2026.01 | 65.28 | 80.4 | 85.12 | 41.29 | — | |
| TBPS-CLIPBackbone=ViT-B/16, Reference=Ours2023.08 | 65.05 | 80.34 | 85.47 | 39.83 | — | |
| TBPS-CLIP#Parameter=149M2024.04 | 65.05 | 80.34 | 85.47 | 39.83 | — | |
| TBPS-CLIP2024.07 | 65.05 | 80.34 | 85.47 | 39.83 | — | |
| TBPS-CLIPVenue=AAAI, Method Type=CLIP based, NNN=false2026.01 | 65.05 | 80.34 | 85.47 | 39.83 | — | |
| TBPSCLIPVenue=AAAI’24, Image enc.=CLIP-ViT, Text enc.=CLIP-Xformer, Setup=with CLIP backbone2026.01 | 65.05 | 80.34 | 85.47 | 39.83 | — | |
| CRUEVenue=TOMM’25, Image enc.=CLIP-ViT, Text enc.=CLIP-Xformer, Setup=with CLIP backbone2026.01 | 64.88 | 80.9 | 86.36 | 41.82 | — | |
| Simplified TBPS-CLIPBackbone=ViT-B/16, Reference=Ours2023.08 | 64.52 | 80.03 | 85.39 | 39.54 | — | |
| SAP-SAMVenue=MM’24, Image enc.=CLIP-ViT, Text enc.=CLIP-Xformer, Setup=with using external tools or ReID-Domain Pre-training2026.01 | 63.97 | 80.84 | 86.17 | — | — | |
| BiLMaVenue=ICCV’23, Image enc.=CLIP-ViT, Text enc.=CLIP-Xformer, Setup=with CLIP backbone2026.01 | 63.83 | 80.15 | 85.74 | 38.26 | — | |
| IRRABackbone=ViT-B/16, Reference=CVPR232023.08 | 63.46 | 80.25 | 85.82 | 38.06 | — | |
| IRRA#Parameter=194M2024.04 | 63.46 | 80.25 | 85.82 | 38.06 | — | |
| IRRA2024.07 | 63.46 | 80.25 | 85.82 | 38.06 | — | |
| IRRAVenue=CVPR, Method Type=CLIP based, NNN=false2026.01 | 63.46 | 80.25 | 85.82 | 38.06 | — | |
| IRRAVenue=CVPR’23, Image enc.=CLIP-ViT, Text enc.=CLIP-Xformer, Setup=with CLIP backbone2026.01 | 63.46 | 80.25 | 85.82 | 38.06 | — | |
| VGSGArch.=ViT-Base2023.11 | 63.05 | 78.43 | 84.36 | — | — | |
| DM-AdapterVenue=AAAI’25, Image enc.=CLIP-ViT, Text enc.=CLIP-Xformer, Setup=with CLIP backbone2026.01 | 62.64 | 79.53 | 85.32 | 36.5 | — | |
| CFAM (B/16)Venue=CVPR’24, Image enc.=CLIP-ViT, Text enc.=CLIP-Xformer, Setup=with using external tools or ReID-Domain Pre-training2026.01 | 62.17 | 79.57 | 85.32 | 36.34 | — | |
| CFineArch.=ViT-Base2023.11 | 60.83 | 76.55 | 82.42 | — | — | |
| CFineVLP=true2023.05 | 60.83 | 76.55 | 82.42 | — | — | |
| CFineReference=arXiv222023.08 | 60.83 | 76.55 | 82.42 | — | — | |
| CFine#Parameter=not specified2024.04 | 60.83 | 76.55 | 82.42 | — | — | |
| CFine2024.07 | 60.83 | 76.55 | 82.42 | — | — | |
| CFineVenue=TIP, Method Type=CLIP based, NNN=false2026.01 | 60.83 | 76.55 | 82.42 | — | — | |
| CFineVenue=TIP’23, Image enc.=CLIP-ViT, Text enc.=BERT, Setup=with CLIP backbone2026.01 | 60.83 | 76.55 | 82.42 | — | — | |
| TP-TPSReference=arXiv232023.08 | 60.64 | 75.97 | 81.76 | 42.78 | — | |
| VGSGArch.=ResNet502023.11 | 60.34 | 76.01 | 82.01 | — | — | |
| UniPTVenue=ICCV’23, Image enc.=ViT-B/16, Text enc.=BERT, Setup=with using external tools or ReID-Domain Pre-training2026.01 | 60.09 | 76.19 | 82.46 | — | — | |
| TBPS-CLIPBackbone=ViT-B/32, Reference=Ours2023.08 | 59.88 | 77.4 | 83.33 | 34.96 | — | |
| LGURVLP=false2023.05 | 59.02 | 75.32 | 81.56 | — | — | |
| LGUR#Parameter=not specified2024.04 | 59.02 | 75.32 | 81.56 | — | — | |
| CSKTVenue=ICASSP’24, Image enc.=CLIP-ViT, Text enc.=CLIP-Xformer, Setup=with CLIP backbone2026.01 | 58.9 | 77.31 | 83.56 | 33.87 | — | |
| ISANetArch.=ResNet502023.11 | 57.73 | 75.42 | 81.72 | — | — | |
| LGURArch.=ResNet502023.11 | 57.42 | 74.97 | 81.45 | — | — | |
| LGURReference=MM222023.08 | 57.42 | 74.97 | 81.45 | — | — | |
| SRCFArch.=ResNet502023.11 | 57.18 | 75.01 | 81.49 | — | — | |
| SRCFVLP=false2023.05 | 57.18 | 75.01 | 81.49 | — | — | |
| CLIPVenue=PMLR, Method Type=CLIP based, NNN=false2026.01 | 56.8 | 75.99 | 82.31 | 31.93 | — | |
| CLIPbackbone=ViT-B/16, mode=fine-tuned2024.07 | 56.74 | 75.72 | 82.26 | 31.84 | — | |
| CLIP (ViT-B/16)Venue=ICML’21, Image enc.=CLIP-ViT, Text enc.=CLIP-Xformer, Setup=with CLIP backbone2026.01 | 56.23 | 74.29 | 81.62 | 30.85 | — | |
| BLIPmode=fine-tuned2024.07 | 56.16 | 73.77 | 80.17 | 31.59 | — | |
| IVTArch.=ViT-Base2023.11 | 56.04 | 73.6 | 80.22 | — | — | |
| IVTVLP=true2023.05 | 56.04 | 73.6 | 80.22 | — | — | |
| IVTReference=ECCVW222023.08 | 56.04 | 73.6 | 80.22 | — | — | |
| IVT#Parameter=not specified2024.04 | 56.04 | 73.6 | 80.22 | — | — | |
| CLIPBackbone=ViT-B/16, Reference=Baseline2023.08 | 55.97 | 74.62 | 81.35 | 30.63 | — | |
| TIPCBVLP=false2023.05 | 54.96 | 74.72 | 81.89 | — | — | |
| SAFVLP=false2023.05 | 54.86 | 72.13 | 79.13 | 32.76 | — | |
| SAFReference=ICASSP222023.08 | 54.86 | 72.13 | 79.13 | 32.76 | — | |
| SSANArch.=ResNet502023.11 | 54.23 | 72.63 | 79.53 | — | — | |
| SSANVLP=false2023.05 | 54.23 | 72.63 | 79.53 | — | — | |
| SSANReference=arXiv212023.08 | 54.23 | 72.63 | 79.53 | — | — | |
| SSAN#Parameter=not specified2024.04 | 54.23 | 72.63 | 79.53 | — | — | |
| CLIPBackbone=ViT-B/32, Reference=Baseline2023.08 | 53.96 | 73.69 | 80.43 | 32.37 | — | |
| ViTAAArch.=ResNet502023.11 | 50.98 | 68.79 | 75.78 | — | — | |
| VITAAVLP=false2023.05 | 50.98 | 68.79 | 75.78 | — | — | |
| VITAAReference=ECCV202023.08 | 50.98 | 68.79 | 75.78 | — | — | |
| VITAA#Parameter=177M2024.04 | 50.98 | 68.79 | 75.78 | — | — | |
| RaSaSource Domain=CUHK-PEDES, Target Domain=ICFG-PEDES2023.05 | 50.7 | 72.4 | 79.58 | — | — | |
| SCANArch.=ResNet502023.11 | 50.05 | 69.65 | 77.21 | — | — | |
| SCAN#Parameter=not specified2024.04 | 50.05 | 69.65 | 77.21 | — | — | |
| MIAArch.=ResNet502023.11 | 46.49 | 67.14 | 75.18 | — | — | |
| MIA#Parameter=not specified2024.04 | 46.49 | 67.14 | 75.18 | — | — | |
| CMPM/CArch.=MobileNet2023.11 | 43.51 | 65.44 | 74.26 | — | — | |
| CMPM/CVLP=false2023.05 | 43.51 | 65.44 | 74.26 | — | — | |
| CMPM+CMPC#Parameter=not specified2024.04 | 43.51 | 65.44 | 74.26 | — | — | |
| Dual PathArch.=ResNet502023.11 | 38.99 | 59.44 | 68.41 | — | — |