Visual Commonsense Reasoning 벤치마크
Visual Commonsense Reasoning on VCR (Q-A) dev
| Rank | Model | Accuracy | Paper | Code | Year |
|---|---|---|---|---|---|
| 1 | PEVL | 75.1 | PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models | thunlp/pevl | 2022 |
Visual Commonsense Reasoning 벤치마크
| Rank | Model | Accuracy | Paper | Code | Year |
|---|---|---|---|---|---|
| 1 | PEVL | 75.1 | PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models | thunlp/pevl | 2022 |