Metric: SPICE (higher is better)
| # | Model↕ | SPICE▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | GIT2 | 16.11 | No | GIT: A Generative Image-to-text Transformer for ... | 2022-05-27 | Code |
| 2 | GIT | 15.96 | No | GIT: A Generative Image-to-text Transformer for ... | 2022-05-27 | Code |
| 3 | VLAF2 | 14.97 | No | - | - | - |
| 4 | Human | 14.72 | No | - | - | - |
| 5 | Microsoft Cognitive Services team | 14.27 | No | VIVO: Visual Vocabulary Pre-Training for Novel O... | 2020-09-28 | - |
| 6 | test_cbs2 | 13.01 | No | - | - | - |
| 7 | icp2ssi1_coco_si_0.02_5_test | 11.96 | No | - | - | - |
| 8 | UpDown + ELMo + CBS | 11.45 | No | - | - | - |
| 9 | UpDown | 10.33 | No | - | - | - |
| 10 | Neural Baby Talk + CBS | 9.83 | No | - | - | - |
| 11 | Neural Baby Talk | 9.26 | No | - | - | - |