Metric: B3 (higher is better)
| # | Model↕ | B3▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | GIT | 60.53 | No | GIT: A Generative Image-to-text Transformer for ... | 2022-05-27 | Code |
| 2 | GIT2 | 59.94 | No | GIT: A Generative Image-to-text Transformer for ... | 2022-05-27 | Code |
| 3 | VLAF2 | 52.99 | No | - | - | - |
| 4 | Microsoft Cognitive Services team | 49.66 | No | VIVO: Visual Vocabulary Pre-Training for Novel O... | 2020-09-28 | - |
| 5 | test_cbs2 | 44.03 | No | - | - | - |
| 6 | icp2ssi1_coco_si_0.02_5_test | 43.04 | No | - | - | - |
| 7 | UpDown | 41.5 | No | - | - | - |
| 8 | UpDown + ELMo + CBS | 39.86 | No | - | - | - |
| 9 | Human | 37.78 | No | - | - | - |
| 10 | Neural Baby Talk | 35.58 | No | - | - | - |
| 11 | Neural Baby Talk + CBS | 33.73 | No | - | - | - |