| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Referring Expression Comprehension | ReferItGame (test) | Top-1 Acc79.3 | 47 | |
| Visual Grounding | ReferitGame (test) | Pr@0.50.7142 | 26 | |
| Phrase localization | ReferItGame | Accuracy59.38 | 22 | |
| Visual Grounding | ReferItGame (test) | Accuracy0.63 | 14 | |
| Referring Expression Generation | ReferItGame (test B) | Meteor13.1 | 7 | |
| Referring Expression Generation | ReferItGame (test A) | Meteor11.6 | 7 |