| Paper | Code | overall | ModelName | ReleaseDate |
|---|---|---|---|---|
| PaLI: A Jointly-Scaled Multilingual Language-Image Model | ✓ Link | 73.1 | PaLI | 2022-09-14 |
| 53.97 | TAP | |||
| TAG: Boosting Text-VQA via Text-aware Visual Question-answer Generation | ✓ Link | 53.69 | TAG | 2022-08-03 |
| 45.66 | ssbaseline | |||
| 45.51 | SMA single model | |||
| 44.8 | SAM (Single Model) | |||
| 44.73 | colab_buaa | |||
| 40.96 | CRN (Single Model) | |||
| 40.77 | CIG | |||
| 40.46 | M4C | |||
| 39.95 | Shuai | |||
| 32.46 | mmgnn |