Metric: B2 (higher is better)
| # | Model↕ | B2▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | GIT | 76.1 | No | GIT: A Generative Image-to-text Transformer for ... | 2022-05-27 | Code |
| 2 | GIT2 | 75.86 | No | GIT: A Generative Image-to-text Transformer for ... | 2022-05-27 | Code |
| 3 | VLAF2 | 70.44 | No | - | - | - |
| 4 | Microsoft Cognitive Services team | 67.56 | No | VIVO: Visual Vocabulary Pre-Training for Novel O... | 2020-09-28 | - |
| 5 | test_cbs2 | 64.09 | No | - | - | - |
| 6 | icp2ssi1_coco_si_0.02_5_test | 62.18 | No | - | - | - |
| 7 | UpDown | 60.34 | No | - | - | - |
| 8 | UpDown + ELMo + CBS | 59.58 | No | - | - | - |
| 9 | Human | 57.3 | No | - | - | - |
| 10 | Neural Baby Talk | 56.78 | No | - | - | - |
| 11 | Neural Baby Talk + CBS | 56.2 | No | - | - | - |