| visual-question-answering-on-clevr-humans | MDETR | #1 | Accuracy: 81.7 |
| referring-expression-segmentation-on-phrasecut | MDETR ENB3 | #2 | Mean IoU: 53.7Pr@0.5: 57.5Pr@0.7: 39.9Pr@0.9: 11.9 |
| visual-question-answering-on-clevr | MDETR | #2 | Accuracy: 99.7 |
| referring-image-matting-refmatte-rw100-on-refmatte | MDETR (ResNet-101) | #3 | SAD: 131.58MSE: 0.0675MAD: 0.0751SAD(E): 136.59MSE(E): 0.0700… |
| visual-question-answering-on-gqa-test-std | MDETR-ENB5 | #3 | Accuracy: 62.45 |
| generalized-referring-expression-comprehension-on-grefcoco | MDETR | #4 | Precision@(F1=1, IoU≥0.5): 41.5N-acc.: 36.1 |
| referring-image-matting-expression-based-on-refmatte | MDETR (ResNet-101) | #4 | SAD: 84.70MSE: 0.0434MAD: 0.0482SAD(E): 90.45MSE(E): 0.0463… |
| referring-image-matting-keyword-based-on-refmatte | MDETR (ResNet-101) | #4 | SAD: 32.27MSE: 0.0137MAD: 0.0183SAD(E): 33.52MSE(E): 0.0141… |
| phrase-grounding-on-flickr30k-entities-test | MDETR-ENB5 | #5 | R@1: 84.3R@5: 93.9R@10: 95.8 |