| referring-expression-segmentation-on-refcoco | VLT | #20 | Overall IoU: 72.96 |
| referring-expression-segmentation-on-refcoco-3 | VLT | #19 | Overall IoU: 63.53 |
| referring-expression-segmentation-on-refcoco-4 | VLT | #16 | Overall IoU: 68.43 |
| referring-expression-segmentation-on-refcoco-5 | VLT | #15 | Overall IoU: 56.92 |
| referring-expression-segmentation-on-refcocog | VLT (Swin-B) | #16 | Overall IoU: 63.49 |
| referring-expression-segmentation-on-refer-1 | VLT | #15 | J&F: 63.8J: 61.9F: 65.6 |
| referring-video-object-segmentation-on-mevis | VLT+TC | #10 | J&F: 35.5J: 33.6F: 37.3 |
| referring-video-object-segmentation-on-refer | VLT | #9 | J&F: 63.8J: 61.9F: 65.6 |