Metric: B4 (higher is better)
| # | Model↕ | B4▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | GIT | 41.65 | No | GIT: A Generative Image-to-text Transformer for ... | 2022-05-27 | Code |
| 2 | GIT2 | 41.1 | No | GIT: A Generative Image-to-text Transformer for ... | 2022-05-27 | Code |
| 3 | VLAF2 | 34.02 | No | - | - | - |
| 4 | Microsoft Cognitive Services team | 32.07 | No | VIVO: Visual Vocabulary Pre-Training for Novel O... | 2020-09-28 | - |
| 5 | icp2ssi1_coco_si_0.02_5_test | 25.67 | No | - | - | - |
| 6 | test_cbs2 | 25.66 | No | - | - | - |
| 7 | UpDown | 24.57 | No | - | - | - |
| 8 | UpDown + ELMo + CBS | 22.83 | No | - | - | - |
| 9 | Human | 21.49 | No | - | - | - |
| 10 | Neural Baby Talk | 17.39 | No | - | - | - |
| 11 | Neural Baby Talk + CBS | 15.14 | No | - | - | - |