Multiple-choice Video Question Answering on TVQA (val)
57.9AccuracyFrozenBiLM
Evaluation results
| Method | Links | |
|---|---|---|
| FrozenBiLMTraining Data=WebVid10M, Zero-shot evaluation=true2022.06 | 57.9 | |
| CLIP ViT-L/14Training Data=400M image-texts, Zero-shot evaluation=true2022.06 | 26.3 | |
| RandomTraining Data=—, Zero-shot evaluation=true2022.06 | 20 |