Metric: METEOR (higher is better)
| # | Model↕ | METEOR▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | PaLI | 33.47 | No | PaLI: A Jointly-Scaled Multilingual Language-Ima... | 2022-09-14 | Code |
| 2 | GIT2, Single Model | 32.95 | No | GIT: A Generative Image-to-text Transformer for ... | 2022-05-27 | Code |
| 3 | GIT, Single Model | 32.86 | No | GIT: A Generative Image-to-text Transformer for ... | 2022-05-27 | Code |
| 4 | CoCa - Google Brain | 32.71 | No | - | - | - |
| 5 | Microsoft Cognitive Services team | 31.8 | No | VIVO: Visual Vocabulary Pre-Training for Novel O... | 2020-09-28 | - |
| 6 | FudanFVL | 31.08 | No | - | - | - |
| 7 | Single Model | 30.97 | No | SimVLM: Simple Visual Language Model Pretraining... | 2021-08-24 | Code |
| 8 | FudanWYZ | 30.79 | No | - | - | - |
| 9 | firethehole | 30.48 | No | - | - | - |
| 10 | IEDA-LAB | 29.53 | No | - | - | - |
| 11 | vll@mk514 | 29.11 | No | - | - | - |
| 12 | MD | 28.84 | No | - | - | - |
| 13 | Human | 28.42 | No | - | - | - |
| 14 | VinVL (Microsoft Cognitive Services + MSR) | 28.24 | No | VinVL: Revisiting Visual Representations in Visi... | 2021-01-02 | Code |
| 15 | ViTCAP-CIDEr-136.7-ENC-DEC-ViTbfocal10-test-CBS | 27.89 | No | - | - | - |
| 16 | camel XE | 26.87 | No | - | - | - |
| 17 | evertyhing | 26.68 | No | - | - | - |
| 18 | icgp2ssi1_coco_si_0.02_5_test | 26.63 | No | - | - | - |
| 19 | RCAL | 26.3 | No | - | - | - |
| 20 | vinvl_yuan_cbs | 25.98 | No | - | - | - |
| 21 | Oscar | 25.91 | No | - | - | - |
| 22 | cxy_nocaps_training | 25.64 | No | - | - | - |
| 23 | Xinyi | 25.64 | No | - | - | - |
| 24 | MQ-UpDown-C | 25.59 | No | - | - | - |
| 25 | UpDown + ELMo + CBS | 24.97 | No | - | - | - |
| 26 | 7_10-7_40000_predict_test.json | 24.52 | No | - | - | - |
| 27 | nocaps_training | 23.6 | No | - | - | - |
| 28 | UpDown | 23.6 | No | - | - | - |
| 29 | None | 23.12 | No | - | - | - |
| 30 | Neural Baby Talk + CBS | 22.55 | No | - | - | - |
| 31 | area_attention | 22.43 | No | - | - | - |
| 32 | B2 | 22.41 | No | - | - | - |
| 33 | YX | 22.27 | No | - | - | - |
| 34 | Neural Baby Talk | 21.93 | No | - | - | - |
| 35 | coco_all_19 | 21.48 | No | - | - | - |
| 36 | Yu-Wu | 20.18 | No | - | - | - |
| 37 | CS395T | 20.05 | No | - | - | - |