Text-based person search on RSTPReid (test)
71.7R@1Scale-TBPS
Evaluation results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Scale-TBPSVenue=Ours, Method Type=Non-CLIP based, NNN=true2026.01 | 71.7 | 87.4 | 91.95 | 58.38 | — | — | — | — | — | — | |
| AULVenue=AAAI’24, Image enc.=Swin-B, Text enc.=BERT, Setup=with using external tools or ReID-Domain Pre-training2026.01 | 71.65 | 87.55 | 92.05 | — | — | — | — | — | — | — | |
| AUL2026.04 | 71.65 | 87.55 | 92.05 | — | — | — | — | — | — | — | |
| DAPL2024.05 | 70.84 | 86.96 | 95.32 | 55.98 | — | — | — | — | — | — | |
| BAMGAdditional information (human parsing)=true2026.04 | 69.73 | 87.65 | 93.33 | 55.21 | — | — | — | — | — | — | |
| GITMBackbone=Swinv2-B2026.04 | 69.45 | 85.5 | 91.65 | 56.11 | — | — | — | — | — | — | |
| APTM2024.05 | 69.07 | 86.47 | 94.73 | 55.2 | — | — | — | — | — | — | |
| Scale-TBPSVenue=Ours, Method Type=Non-CLIP based, NNN=false2026.01 | 68.9 | 87 | 91.65 | 56 | — | — | — | — | — | — | |
| CAMeLVenue=TIFS’25, Image enc.=SG-Former, Text enc.=BERT, Setup=with using external tools or ReID-Domain Pre-training2026.01 | 68.5 | 87.4 | 92.7 | 53.61 | — | — | — | — | — | — | |
| MRA2025.07 | 68.15 | 86.3 | 91.1 | 53.77 | — | — | — | — | — | — | |
| DiCo2026.04 | 67.84 | 85.72 | 91.98 | — | — | — | — | — | — | — | |
| CADAretrained=true2024.07 | 67.7 | 84.6 | 89.75 | 49.95 | — | — | — | — | — | — | |
| ICLVenue=CVPR, Method Type=CLIP based, NNN=false2026.01 | 67.7 | 86.05 | 91.75 | 52.62 | — | — | — | — | — | — | |
| MARS2024.07 | 67.55 | 86.65 | 91.35 | 52.92 | — | — | — | — | — | — | |
| MARSVenue=TOMM’25, Image enc.=Swin-B, Text enc.=BERT, Setup=with ALBEF backbone2026.01 | 67.55 | 86.65 | 91.35 | 52.92 | — | — | — | — | — | — | |
| APTM#Parameter=214M2024.04 | 67.5 | 85.7 | 91.45 | 52.56 | — | — | — | — | — | — | |
| APTMVenue=MM, Method Type=Non-CLIP based, NNN=false2026.01 | 67.5 | 85.7 | 91.45 | 52.56 | — | — | — | — | — | — | |
| APTMVenue=MM’23, Image enc.=Swin-B, Text enc.=BERT, Setup=with using external tools or ReID-Domain Pre-training2026.01 | 67.5 | 85.7 | 91.45 | 52.56 | — | — | — | — | — | — | |
| APTM2025.07 | 67.5 | 85.7 | 91.45 | 52.56 | — | — | — | — | — | — | |
| APTM2026.04 | 67.5 | 85.7 | 91.45 | 52.56 | — | — | — | — | — | — | |
| OursVenue=WACV’26, Image enc.=CLIP-ViT, Text enc.=CLIP-Xformer, Setup=with CLIP backbone2026.01 | 67.3 | 85.6 | 90.5 | 53.05 | — | — | — | — | — | — | |
| ITSELF2026.04 | 67.3 | 85.6 | 90.5 | 53.05 | — | — | — | — | — | — | |
| RaSa2024.05 | 67.17 | 86.45 | 91.19 | 54.97 | — | — | — | — | — | — | |
| RaSaVision-Language Pre-training (VLP)=true2023.05 | 66.9 | 86.5 | 91.35 | 52.31 | — | — | — | — | — | — | |
| RaSaSource=IJCAI23, Use CLIP=false2023.08 | 66.9 | 86.5 | 91.35 | 52.31 | — | — | — | — | — | — | |
| RaSa#Parameter=210M2024.04 | 66.9 | 86.5 | 91.35 | 52.31 | — | — | — | — | — | — | |
| RaSa2024.07 | 66.9 | 86.5 | 91.35 | 52.31 | — | — | — | — | — | — | |
| RaSaVenue=IJCAI, Method Type=Non-CLIP based, NNN=false2026.01 | 66.9 | 86.5 | 91.35 | 52.31 | — | — | — | — | — | — | |
| RaSa2025.07 | 66.9 | 86.5 | 91.35 | 52.31 | — | — | — | — | — | — | |
| RaSa2026.04 | 66.9 | 86.5 | 91.35 | 52.31 | — | — | — | — | — | — | |
| RaSa2026.06 | 66.9 | 86.5 | 91.35 | 52.31 | — | — | — | — | — | — | |
| Filtering-WoRA#Parameter=127M2024.04 | 66.85 | 86.45 | 91.1 | 52.49 | — | — | — | — | — | — | |
| WoRA-TBPSVenue=MM, Method Type=Non-CLIP based, NNN=false2026.01 | 66.85 | 86.45 | 91.1 | 52.49 | — | — | — | — | — | — | |
| Baseline (APTM re-implementation)Backbone=Swinv2-B2026.04 | 66.75 | 85.7 | 91.65 | 53.22 | — | — | — | — | — | — | |
| APTM (Baseline)#Parameter=214M, implementation=re-implemented2024.04 | 66.4 | 85.55 | 91.1 | 52.21 | — | — | — | — | — | — | |
| IRRA2024.05 | 65.88 | 82.29 | 93.88 | 50.28 | — | — | — | — | — | — | |
| RDEVenue=CVPR, Method Type=Non-CLIP based, NNN=false2026.01 | 65.35 | 83.95 | 89.9 | 50.88 | — | — | — | — | — | — | |
| RDEVenue=CVPR’24, Image enc.=CLIP-ViT, Text enc.=CLIP-Xformer, Setup=with CLIP backbone2026.01 | 65.35 | 83.95 | 89.9 | 50.88 | — | — | — | — | — | — | |
| RDE2026.04 | 65.35 | 83.95 | 89.9 | 50.88 | — | — | — | — | — | — | |
| RDEVenue=-, Method Type=Non-CLIP based, NNN=true2026.01 | 65.3 | 85.9 | 90.9 | 51.63 | — | — | — | — | — | — | |
| RaSaVenue=IJCAI’23, Image enc.=Swin-B, Text enc.=BERT, Setup=with ALBEF backbone2026.01 | 65.2 | 84.05 | 89.85 | 50.14 | — | — | — | — | — | — | |
| ROGLE2026.06 | 65.2 | 83.75 | 89.45 | 50.93 | — | — | — | — | — | 27.83 | |
| DECL2024.05 | 64.16 | 85.45 | 92.01 | 53.81 | — | — | — | — | — | — | |
| MUMVenue=AAAI’24, Image enc.=CLIP-ViT, Text enc.=CLIP-Xformer, Setup=with CLIP backbone2026.01 | 63.4 | 83.3 | 90.3 | 49.28 | — | — | — | — | — | — | |
| CRUEVenue=TOMM’25, Image enc.=CLIP-ViT, Text enc.=CLIP-Xformer, Setup=with CLIP backbone2026.01 | 63.15 | 82.8 | 90.2 | 50.2 | — | — | — | — | — | — | |
| SAP-SAMVenue=MM’24, Image enc.=CLIP-ViT, Text enc.=CLIP-Xformer, Setup=with using external tools or ReID-Domain Pre-training2026.01 | 62.85 | 82.65 | 89.85 | — | — | — | — | — | — | — | |
| DPVenue=AAAI’24, Image enc.=CLIP-ViT, Text enc.=CLIP-Xformer, Setup=with using external tools or ReID-Domain Pre-training2026.01 | 62.48 | 83.77 | 89.93 | 48.86 | — | — | — | — | — | — | |
| CFAMBackbone=CLIP-ViT-L/142023.12 | 62.45 | 83.55 | 91.1 | 49.5 | 36.92 | — | — | — | — | — | |
| CFAMVenue=CVPR, Method Type=CLIP based, NNN=false2026.01 | 62.45 | 83.55 | 91.1 | 49.5 | — | — | — | — | — | — | |
| 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 | 62.45 | 83.55 | 91.1 | 49.5 | — | — | — | — | — | — | |
| CFAM2026.06 | 62.45 | 83.55 | — | 49.5 | — | — | — | — | — | — | |
| Simplified TBPS-CLIPBackbone=ViT-B/162023.08 | 62.1 | 81.9 | 87.75 | 48 | — | — | — | — | — | — | |
| TBPS-CLIPVenue=AAAI, Method Type=CLIP based, NNN=false2026.01 | 62.1 | 81.9 | 87.75 | 48 | — | — | — | — | — | — | |
| TBPS-CLIPBackbone=ViT-B/162023.08 | 61.95 | 83.55 | 88.75 | 48.26 | — | — | — | — | — | — | |
| TBPS-CLIP#Parameter=149M2024.04 | 61.95 | 83.55 | 88.75 | 48.26 | — | — | — | — | — | — | |
| TBPS-CLIP2024.07 | 61.95 | 83.55 | 88.75 | 48.26 | — | — | — | — | — | — | |
| TBPSCLIPVenue=AAAI’24, Image enc.=CLIP-ViT, Text enc.=CLIP-Xformer, Setup=with CLIP backbone2026.01 | 61.95 | 83.55 | 88.75 | 48.26 | — | — | — | — | — | — | |
| TBPS-CLIP2026.04 | 61.95 | 83.55 | 88.75 | 48.26 | — | — | — | — | — | — | |
| TBPS2026.06 | 61.95 | 83.55 | 88.75 | 48.26 | — | — | — | — | — | — | |
| PLOTVenue=ECCV’24, Image enc.=CLIP-ViT, Text enc.=CLIP-Xformer, Setup=with CLIP backbone2026.01 | 61.8 | 82.85 | 89.45 | — | — | — | — | — | — | — | |
| PLOT2026.06 | 61.8 | 82.85 | 89.45 | — | — | — | — | — | — | — | |
| OCDL2026.06 | 61.6 | 82.35 | — | 49.77 | — | — | — | — | — | — | |
| DCEL2026.06 | 61.35 | 83.95 | 90.45 | — | — | — | — | — | — | — | |
| BiLMaVenue=ICCV’23, Image enc.=CLIP-ViT, Text enc.=CLIP-Xformer, Setup=with CLIP backbone2026.01 | 61.2 | 81.5 | 88.8 | 48.51 | — | — | — | — | — | — | |
| BiLMa2026.06 | 61.2 | 81.5 | 88.8 | 48.51 | — | — | — | — | — | — | |
| SAMC2025.07 | 60.8 | 82.35 | 89 | 49.67 | — | — | — | — | — | — | |
| SAMC2026.04 | 60.8 | 82.35 | 89 | 49.67 | — | — | — | — | — | — | |
| IRRASource=CVPR23, Backbone=ViT-B/16, Use CLIP=true2023.08 | 60.2 | 81.3 | 88.2 | 47.17 | — | — | — | — | — | — | |
| IRRA2023.12 | 60.2 | 81.3 | 88.2 | 47.17 | 35.22 | — | — | — | — | — | |
| IRRA#Parameter=194M2024.04 | 60.2 | 81.3 | 88.2 | 47.17 | — | — | — | — | — | — | |
| IRRA2024.07 | 60.2 | 81.3 | 88.2 | 47.17 | — | — | — | — | — | — | |
| IRRAVenue=CVPR, Method Type=CLIP based, NNN=false2026.01 | 60.2 | 81.3 | 88.2 | 47.17 | — | — | — | — | — | — | |
| IRRAVenue=CVPR’23, Image enc.=CLIP-ViT, Text enc.=CLIP-Xformer, Setup=with CLIP backbone2026.01 | 60.2 | 81.3 | 88.2 | 47.17 | — | — | — | — | — | — | |
| IRRA2025.07 | 60.2 | 81.3 | 88.2 | 47.17 | — | — | — | — | — | — | |
| IRRA2026.04 | 60.2 | 81.3 | 88.2 | 47.17 | — | — | — | — | — | — | |
| IRRA2026.06 | 60.2 | 81.3 | 88.2 | 47.17 | — | — | — | — | — | 25.28 | |
| DM-AdapterVenue=AAAI’25, Image enc.=CLIP-ViT, Text enc.=CLIP-Xformer, Setup=with CLIP backbone2026.01 | 60 | 82.1 | 87.9 | 47.37 | — | — | — | — | — | — | |
| CFAMBackbone=CLIP-ViT-B/162023.12 | 59.4 | 81.35 | 88.5 | 46.04 | 34.27 | — | — | — | — | — | |
| 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 | 59.4 | 81.35 | 88.5 | 46.04 | — | — | — | — | — | — | |
| CSKTVenue=ICASSP’24, Image enc.=CLIP-ViT, Text enc.=CLIP-Xformer, Setup=with CLIP backbone2026.01 | 57.75 | 81.3 | 88.35 | 46.43 | — | — | — | — | — | — | |
| CLIP (ViT-B/16)Venue=ICML’21, Image enc.=CLIP-ViT, Text enc.=CLIP-Xformer, Setup=with CLIP backbone2026.01 | 56.67 | 78.09 | 86.62 | 42.85 | — | — | — | — | — | — | |
| TBPS-CLIPBackbone=ViT-B/322023.08 | 56.65 | 80.75 | 87.3 | 44 | — | — | — | — | — | — | |
| Baseline2025.07 | 56.3 | 77.55 | 85.2 | 45.88 | — | — | — | — | — | — | |
| CLIPBackbone=ViT-B/16, Type=Baseline2023.08 | 56.15 | 78.3 | 86.6 | 43.26 | — | — | — | — | — | — | |
| TransTPS2026.04 | 56.05 | 78.65 | 86.75 | — | — | — | — | — | — | — | |
| CLIPVenue=PMLR, Method Type=CLIP based, NNN=false2026.01 | 56 | 80.85 | 87.9 | 44.06 | — | — | — | — | — | — | |
| LCR2S2026.06 | 54.95 | 76.65 | 84.7 | 40.92 | — | — | — | — | — | — | |
| CLIPbackbone=ViT-B/16, mode=fine-tuned2024.07 | 54.05 | 80.7 | 88 | 43.41 | — | — | — | — | — | — | |
| UniPTVenue=ICCV’23, Image enc.=ViT-B/16, Text enc.=BERT, Setup=with using external tools or ReID-Domain Pre-training2026.01 | 51.85 | 74.85 | 82.85 | — | — | — | — | — | — | — | |
| C2A2Vision-Language Pre-training (VLP)=false2023.05 | 51.55 | 76.75 | 85.15 | — | — | — | — | — | — | — | |
| TP-TPSSource=arXiv23, Use CLIP=true2023.08 | 50.65 | 72.45 | 81.2 | 43.11 | — | — | — | — | — | — | |
| CFineVision-Language Pre-training (VLP)=true2023.05 | 50.55 | 72.5 | 81.6 | — | — | — | — | — | — | — | |
| CFineSource=arXiv22, Use CLIP=true2023.08 | 50.55 | 72.5 | 81.6 | — | — | — | — | — | — | — | |
| CFine2023.12 | 50.55 | 72.5 | 81.6 | — | — | — | — | — | — | — | |
| CFine2024.04 | 50.55 | 72.5 | 81.6 | — | — | — | — | — | — | — | |
| CFine2024.07 | 50.55 | 72.5 | 81.6 | — | — | — | — | — | — | — | |
| CFineVenue=TIP, Method Type=CLIP based, NNN=false2026.01 | 50.55 | 72.5 | 81.6 | — | — | — | — | — | — | — | |
| CFineVenue=TIP’23, Image enc.=CLIP-ViT, Text enc.=BERT, Setup=with CLIP backbone2026.01 | 50.55 | 72.5 | 81.6 | — | — | — | — | — | — | — | |
| CFine2025.07 | 50.55 | 72.5 | 81.6 | — | — | — | — | — | — | — | |
| CFine2026.04 | 50.55 | 72.5 | 81.6 | — | — | — | — | — | — | — |