Text-to-Image Retrieval on ICFG-PEDES
69.92R@1InterPartAbility
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| InterPartAbilityImage Enc.=CLIP-ViT, Text Enc.=CLIP-X., Interp.=Yes2026.04 | 69.92 | 83.83 | 88.13 | 42.03 | 8.79 | |
| ICLImage Enc.=CLIP-ViT, Text Enc.=CLIP-X., Interp.=No2026.04 | 69.22 | 83.49 | 88.06 | 42.34 | 9.01 | |
| APTMImage Enc.=Swin-B, Text Enc.=BERT, Interp.=No2026.04 | 68.51 | 82.99 | 87.56 | 41.22 | — | |
| DiCOImage Enc.=CLIP-ViT, Text Enc.=CLIP-X., Interp.=Yes2026.04 | 67.81 | 83.29 | 87.62 | — | — | |
| MARSImage Enc.=Swin-B, Text Enc.=BERT, Interp.=No2026.04 | 67.6 | 81.47 | 85.79 | 44.93 | — | |
| NAM♮Image Enc.=CLIP-ViT, Text Enc.=CLIP-X., Interp.=No2026.04 | 66.76 | 82.02 | 87.17 | 41.45 | 9.53 | |
| PLOTImage Enc.=CLIP-ViT, Text Enc.=CLIP-X., Interp.=Yes2026.04 | 65.76 | 81.39 | 86.73 | — | — | |
| IRRA♭Image Enc.=CLIP-ViT, Text Enc.=CLIP-X., Interp.=No2026.04 | 64.37 | 80.75 | 86.12 | 38.85 | — |