| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Referring Image Segmentation | G-Ref (val) | mIoU75.54 | 95 | |
| Referring Image Segmentation | G-Ref Google split (val) | IoU65.79 | 58 | |
| Referring Image Segmentation | G-Ref (test) | IoU80.54 | 33 | |
| Referring Image Segmentation | G-Ref u (val) | IoU74.6 | 19 | |
| Referring Image Segmentation | G-Ref UMD (test) | IoU66.22 | 19 | |
| Referring Image Segmentation | G-Ref UMD split (val) | mIoU63.49 | 19 | |
| Referring Expression Segmentation | G-Ref UMD (test) | cIoU66.22 | 17 | |
| Referring Image Segmentation | G-Ref u (test) | mIoU75.3 | 16 | |
| Referring Image Segmentation | G-Ref hard UMD (val) | oIoU67.79 | 14 | |
| Referring Image Segmentation | G-Ref hard UMD partition (test) | oIoU69.29 | 12 | |
| Referring Image Segmentation | G-Ref UMD partition U (val) | oIoU64.68 | 12 | |
| Referring Image Segmentation | G-Ref g (val) | IoU0.679 | 11 | |
| Referring Expression Segmentation | G-Ref (test-U) | cIoU66.64 | 11 | |
| Referring Expression Segmentation | G-Ref (val-U) | cIoU65.38 | 11 | |
| Referring Image Segmentation | G-Ref MS-COCO based (longer sentences) (val) | Overall IoU49.05 | 10 | |
| Referring Expression Segmentation | G-Ref Google (val) | mIoU66.89 | 9 | |
| Referring Expression Segmentation | G-Ref (val) | cIoU62.84 | 8 | |
| Referring Image Segmentation | G-Ref hard Google partition (val) | oIoU63.13 | 8 | |
| Referring Expression Segmentation | G-Ref UMD (val) | cIoU65 | 7 | |
| Referring Image Segmentation | G-Ref UMD partition (test) | oIoU62.09 | 7 | |
| Referring Image Segmentation | G-Ref UMD (val) | cIoU65 | 6 | |
| Referring Image Segmentation | G-Ref standard (test-U (UMD)) | mIoU67.83 | 5 | |
| Referring Image Segmentation | G-Ref Google partition unseen (val) | mIoU45.05 | 3 | |
| Referring Image Segmentation | G-Ref Google partition seen (val) | mIoU62.85 | 3 | |
| Referring Image Segmentation | G-Ref UMD partition unseen (test) | mIoU0.4231 | 3 |