Text-to-image Person Retrieval on RSTPReid
73.75Rank-1 AccuracyHAM(RDE) + MVR
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| HAM(RDE) + MVRVenue=-2026.04 | 73.75 | 87.9 | 92.55 | 55.74 | — | |
| AULVenue=AAAI '242026.04 | 71.65 | 87.55 | 92.05 | — | — | |
| HAM(RDE)Venue=CVPR '252026.04 | 71.5 | 86.5 | 91.15 | 55.34 | — | |
| HAM(IRRA) + MVRVenue=-2026.04 | 71.05 | 87.85 | 92.7 | 55.15 | — | |
| InterPartAbilityImage Enc.=CLIP-ViT, Text Enc.=CLIP-X., Interp.=Yes2026.04 | 70.9 | 85.5 | 90.8 | 52.76 | 28 | |
| HAM(IRRA)Venue=CVPR '252026.04 | 70.8 | 87.5 | 92.4 | 54.52 | — | |
| ICLImage Enc.=CLIP-ViT, Text Enc.=CLIP-X., Interp.=No2026.04 | 70 | 86.6 | 91.7 | 54.16 | 30.93 | |
| CONQUERImage Enc.=CLIP-ViT, Text Enc.=CLIP-Xformer2026.01 | 68.4 | 84.95 | — | 51.73 | — | |
| DiCOImage Enc.=CLIP-ViT, Text Enc.=CLIP-X., Interp.=Yes2026.04 | 67.84 | 85.72 | 91.98 | — | — | |
| CADAVenue=TMM '242026.04 | 67.7 | 84.6 | 89.75 | 49.95 | — | |
| RDE + MVRVenue=-2026.04 | 67.6 | 85.15 | 90.1 | 52.07 | — | |
| MARSImage Enc.=Swin-B, Text Enc.=BERT, Interp.=No2026.04 | 67.6 | 81.47 | 85.79 | 44.93 | — | |
| APTMPretraining=MALS2023.06 | 67.5 | 85.7 | 91.45 | 52.56 | — | |
| APTMVenue=ACM MM '232026.04 | 67.5 | 85.7 | 91.45 | 52.56 | — | |
| APTMImage Enc.=Swin-B, Text Enc.=BERT, Interp.=No2026.04 | 67.5 | 85.7 | 91.45 | 52.56 | — | |
| NAM♮Image Enc.=CLIP-ViT, Text Enc.=CLIP-X., Interp.=No2026.04 | 67.15 | 86.55 | 91.9 | 52 | 28.46 | |
| RaSaVenue=IJCAI '232026.04 | 66.9 | 86.5 | 91.35 | 52.31 | — | |
| F-WoRAVenue=WWW '252026.04 | 66.85 | 86.45 | 91.1 | 52.49 | — | |
| CTGIImage Enc.=CLIP-ViT, Text Enc.=CLIP-Xformer2026.01 | 66.35 | 85.5 | — | 51.51 | — | |
| RDEImage Enc.=CLIP-ViT, Text Enc.=CLIP-Xformer2026.01 | 65.35 | 83.95 | — | 50.88 | — | |
| RDEVenue=CVPR '242026.04 | 65.35 | 83.95 | 89.9 | 50.88 | — | |
| RDEsetting=Standard HR setting2026.06 | 63.85 | — | — | 47.67 | — | |
| UMSAVenue=AAAI '242026.04 | 63.4 | 83.3 | 90.3 | 49.28 | — | |
| IRRA + MVRVenue=-2026.04 | 63.1 | 82.4 | 89.4 | 49.21 | — | |
| DPImage Enc.=CLIP-ViT, Text Enc.=CLIP-Xformer2026.01 | 62.48 | 83.77 | — | 48.86 | — | |
| CFAMImage Enc.=CLIP-ViT, Text Enc.=CLIP-Xformer2026.01 | 62.45 | 83.55 | — | 49.5 | — | |
| TBPSImage Enc.=CLIP-ViT, Text Enc.=CLIP-Xformer2026.01 | 61.95 | 83.55 | — | 48.26 | — | |
| TBPS-CLIPVenue=AAAI '242026.04 | 61.95 | 83.55 | 88.75 | 48.26 | — | |
| TBPS-CLIPsetting=Standard HR setting2026.06 | 61.95 | — | — | 48.26 | — | |
| IRRA♭Image Enc.=CLIP-ViT, Text Enc.=CLIP-X., Interp.=No2026.04 | 61.9 | 80.6 | 89.3 | 48.08 | — | |
| PropotVenue=ACM MM '242026.04 | 61.87 | 83.63 | 89.7 | 47.82 | — | |
| PLOTVenue=ECCV '242026.04 | 61.8 | 82.85 | 89.45 | — | — | |
| PLOTImage Enc.=CLIP-ViT, Text Enc.=CLIP-X., Interp.=Yes2026.04 | 61.8 | 82.85 | 89.45 | — | — | |
| OCDLImage Enc.=CLIP-ViT, Text Enc.=CLIP-Xformer2026.01 | 61.6 | 82.35 | — | 49.77 | — | |
| IRLTVenue=AAAI '242026.04 | 61.49 | 82.26 | 89.23 | — | — | |
| DCELImage Enc.=CLIP-ViT, Text Enc.=CLIP-Xformer2026.01 | 61.35 | 83.95 | — | — | — | |
| DCELVenue=ACM MM '232026.04 | 61.35 | 83.95 | 93.46 | — | — | |
| CRSTsetting=Standard HR setting2026.06 | 61.05 | — | — | 47.94 | — | |
| CFAMVenue=CVPR '242026.04 | 60.51 | 82.85 | 89.71 | 47.64 | — | |
| IRRAType=Global2023.03 | 60.2 | 81.3 | 88.2 | 47.17 | 25.28 | |
| IRRAImage Enc.=CLIP-ViT, Text Enc.=CLIP-Xformer2026.01 | 60.2 | 81.3 | — | 47.17 | — | |
| FSRLVenue=ICMR '242026.04 | 60.2 | 81.4 | 88.6 | 47.38 | — | |
| IRRAVenue=CVPR '232026.04 | 60.2 | 81.3 | 88.2 | 47.17 | — | |
| IRRAsetting=Standard HR setting2026.06 | 60.2 | — | — | 47.17 | — | |
| DM-AdapterImage Enc.=CLIP-ViT, Text Enc.=CLIP-Xformer2026.01 | 60 | 82.1 | — | 47.37 | — | |
| DM-Adaptersetting=Standard HR setting2026.06 | 60 | — | — | 47.37 | — | |
| MMRefsetting=Standard HR setting2026.06 | 56.2 | — | — | — | — | |
| LCR2SImage Enc.=RN50, Text Enc.=TextCNN2026.01 | 54.95 | 76.65 | — | 40.92 | — | |
| LCR2SVenue=ACM MM '232026.04 | 54.95 | 76.65 | 84.7 | 40.92 | — | |
| LCR2Ssetting=Standard HR setting2026.06 | 54.95 | — | — | 40.92 | — | |
| BaselineType=Global, Backbone=CLIP-ViT-B/162023.03 | 54.05 | 80.7 | 88 | 43.41 | 22.31 | |
| UniPTImage Enc.=CLIP-ViT, Text Enc.=CLIP-Xformer2026.01 | 51.85 | 74.85 | — | — | — | |
| UniPTVenue=ICCV '232026.04 | 51.85 | 74.85 | 82.85 | — | — | |
| UniPTsetting=Standard HR setting2026.06 | 51.85 | — | — | — | — | |
| TP-TPSsetting=Standard HR setting2026.06 | 50.65 | — | — | 43.11 | — | |
| CFineType=Local2023.03 | 50.55 | 72.5 | 81.6 | — | — | |
| CFine2023.06 | 50.55 | 72.5 | 81.6 | — | — | |
| CFineImage Enc.=CLIP-ViT, Text Enc.=BERT2026.01 | 50.55 | 72.5 | — | — | — | |
| CFineVenue=TIP '232026.04 | 50.55 | 72.5 | 81.6 | — | — | |
| CFinesetting=Standard HR setting2026.06 | 50.55 | — | — | — | — | |
| BEATImage Enc.=RN101, Text Enc.=BERT2026.01 | 48.1 | 73.1 | — | — | — | |
| LGURVenue=ACM MM '222026.04 | 47.95 | 71.85 | 80.25 | — | — | |
| PBSLsetting=Standard HR setting2026.06 | 47.8 | — | — | — | — | |
| CAIBC2023.06 | 47.35 | 69.55 | 79 | — | — | |
| CAIBCVenue=ACM MM '222026.04 | 47.35 | 69.55 | 79 | — | — | |
| BaselinePretraining=None / without pretraining on MALS2023.06 | 47.2 | 70.85 | 80 | 36.36 | — | |
| IVTType=Global2023.03 | 46.7 | 70 | 78.8 | — | — | |
| IVT2023.06 | 46.7 | 70 | 78.8 | — | — | |
| IVTImage Enc.=ViT-Base, Text Enc.=BERT2026.01 | 46.7 | 70 | — | — | — | |
| IVTsetting=Standard HR setting2026.06 | 46.7 | — | — | — | — | |
| LBULType=Local2023.03 | 45.55 | 68.2 | 77.85 | — | — | |
| LBUL2023.06 | 45.55 | 68.2 | 77.85 | — | — | |
| LBULsetting=Standard HR setting2026.06 | 45.55 | — | — | — | — | |
| SSANType=Local2023.03 | 43.5 | 67.8 | 77.15 | — | — | |
| SSANImage Enc.=RN50, Text Enc.=LSTM2026.01 | 43.5 | 67.8 | — | — | — | |
| SSANsetting=Standard HR setting2026.06 | 43.5 | — | — | — | — | |
| BaselineType=Global, Backbone=CLIP-RN1012023.03 | 43.45 | 67.75 | 78.4 | 29.91 | 11.18 | |
| BaselineType=Global, Backbone=CLIP-RN502023.03 | 41.4 | 68.55 | 77.95 | 31.51 | 12.71 | |
| DSSLType=Global2023.03 | 39.05 | 62.6 | 73.95 | — | — | |
| DSSL2023.06 | 32.43 | 55.08 | 63.19 | — | — |