Metric: SPICE (higher is better)
| # | Model↕ | SPICE▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | GIT2, Single Model | 16.36 | No | GIT: A Generative Image-to-text Transformer for ... | 2022-05-27 | Code |
| 2 | GIT, Single Model | 16.18 | No | GIT: A Generative Image-to-text Transformer for ... | 2022-05-27 | Code |
| 3 | PaLI | 15.69 | No | PaLI: A Jointly-Scaled Multilingual Language-Ima... | 2022-09-14 | Code |
| 4 | CoCa - Google Brain | 15.49 | No | - | - | - |
| 5 | Microsoft Cognitive Services team | 15.22 | No | VIVO: Visual Vocabulary Pre-Training for Novel O... | 2020-09-28 | - |
| 6 | firethehole | 15.17 | No | - | - | - |
| 7 | FudanFVL | 15.04 | No | - | - | - |
| 8 | vll@mk514 | 14.99 | No | - | - | - |
| 9 | Human | 14.99 | No | - | - | - |
| 10 | FudanWYZ | 14.85 | No | - | - | - |
| 11 | Single Model | 14.6 | No | SimVLM: Simple Visual Language Model Pretraining... | 2021-08-24 | Code |
| 12 | IEDA-LAB | 14.47 | No | - | - | - |
| 13 | MD | 14.08 | No | - | - | - |
| 14 | VinVL (Microsoft Cognitive Services + MSR) | 13.63 | No | VinVL: Revisiting Visual Representations in Visi... | 2021-01-02 | Code |
| 15 | ViTCAP-CIDEr-136.7-ENC-DEC-ViTbfocal10-test-CBS | 13.61 | No | - | - | - |
| 16 | GRIT (zero-shot, no VL pretraining, no CBS) | 13.6 | No | GRIT: Faster and Better Image captioning Transfo... | 2022-07-20 | Code |
| 17 | camel XE | 13.04 | No | - | - | - |
| 18 | RCAL | 12.79 | No | - | - | - |
| 19 | evertyhing | 12.6 | No | - | - | - |
| 20 | MQ-UpDown-C | 12.38 | No | - | - | - |
| 21 | cxy_nocaps_training | 12.35 | No | - | - | - |
| 22 | 作者给的test文件 | 12.35 | No | - | - | - |
| 23 | Xinyi | 12.3 | No | - | - | - |
| 24 | icgp2ssi1_coco_si_0.02_5_test | 12.28 | No | - | - | - |
| 25 | ClipCap (MLP + GPT2 tuning) | 12.2 | No | ClipCap: CLIP Prefix for Image Captioning | 2021-11-18 | Code |
| 26 | ClipCap (Transformer) | 12.14 | No | ClipCap: CLIP Prefix for Image Captioning | 2021-11-18 | Code |
| 27 | Oscar | 12.06 | No | - | - | - |
| 28 | 7_10-7_40000_predict_test.json | 12.04 | No | - | - | - |
| 29 | UpDown + ELMo + CBS | 11.8 | No | - | - | - |
| 30 | UpDown | 11.47 | No | - | - | - |
| 31 | nocaps_training | 11.46 | No | - | - | - |
| 32 | None | 11.07 | No | - | - | - |
| 33 | YX | 10.94 | No | - | - | - |
| 34 | area_attention | 10.87 | No | - | - | - |
| 35 | B2 | 10.55 | No | - | - | - |
| 36 | Neural Baby Talk + CBS | 10.13 | No | - | - | - |
| 37 | coco_all_19 | 10.11 | No | - | - | - |
| 38 | Neural Baby Talk | 9.81 | No | - | - | - |
| 39 | Yu-Wu | 9.16 | No | - | - | - |
| 40 | CS395T | 8.91 | No | - | - | - |