Metric: SPICE (higher is better)
| # | Model↕ | SPICE▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | GIT | 15.7 | No | GIT: A Generative Image-to-text Transformer for ... | 2022-05-27 | Code |
| 2 | GIT2 | 15.62 | No | GIT: A Generative Image-to-text Transformer for ... | 2022-05-27 | Code |
| 3 | Human | 14.21 | No | - | - | - |
| 4 | VLAF2 | 13.11 | No | - | - | - |
| 5 | Microsoft Cognitive Services team | 12.66 | No | VIVO: Visual Vocabulary Pre-Training for Novel O... | 2020-09-28 | - |
| 6 | icp2ssi1_coco_si_0.02_5_test | 11.28 | No | - | - | - |
| 7 | test_cbs2 | 11.07 | No | - | - | - |
| 8 | UpDown + ELMo + CBS | 9.74 | No | - | - | - |
| 9 | Neural Baby Talk + CBS | 8.77 | No | - | - | - |
| 10 | Neural Baby Talk | 8.2 | No | - | - | - |
| 11 | UpDown | 8.08 | No | - | - | - |