Metric: B4 (higher is better)
| # | Model↕ | B4▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | GIT2 | 37.65 | No | GIT: A Generative Image-to-text Transformer for ... | 2022-05-27 | Code |
| 2 | GIT | 37.35 | No | GIT: A Generative Image-to-text Transformer for ... | 2022-05-27 | Code |
| 3 | Microsoft Cognitive Services team | 34.65 | Yes | Scaling Up Vision-Language Pre-training for Imag... | 2021-11-24 | - |
| 4 | VLAF2 | 29.69 | No | - | - | - |
| 5 | Microsoft Cognitive Services team | 28.95 | No | VIVO: Visual Vocabulary Pre-Training for Novel O... | 2020-09-28 | - |
| 6 | icp2ssi1_coco_si_0.02_5_test | 23.77 | No | - | - | - |
| 7 | test_cbs2 | 20.81 | No | - | - | - |
| 8 | Human | 19.48 | No | - | - | - |
| 9 | UpDown | 19.16 | No | - | - | - |
| 10 | UpDown + ELMo + CBS | 18.41 | No | - | - | - |
| 11 | Neural Baby Talk | 14.73 | No | - | - | - |
| 12 | Neural Baby Talk + CBS | 12.88 | No | - | - | - |