Metric: ROUGE-L (higher is better)
| # | Model↕ | ROUGE-L▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | GIT2 | 63.66 | No | GIT: A Generative Image-to-text Transformer for ... | 2022-05-27 | Code |
| 2 | GIT | 63.5 | No | GIT: A Generative Image-to-text Transformer for ... | 2022-05-27 | Code |
| 3 | VLAF2 | 59.75 | No | - | - | - |
| 4 | Microsoft Cognitive Services team | 58.76 | No | VIVO: Visual Vocabulary Pre-Training for Novel O... | 2020-09-28 | - |
| 5 | icp2ssi1_coco_si_0.02_5_test | 55.13 | No | - | - | - |
| 6 | test_cbs2 | 53.98 | No | - | - | - |
| 7 | Human | 53.06 | No | - | - | - |
| 8 | UpDown + ELMo + CBS | 52.64 | No | - | - | - |
| 9 | UpDown | 51.84 | No | - | - | - |
| 10 | Neural Baby Talk | 49.63 | No | - | - | - |
| 11 | Neural Baby Talk + CBS | 49.45 | No | - | - | - |