Zero Shot Video Question Answer On Tvqa
Metrics
Accuracy
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Accuracy |
|---|---|
| mvbench-a-comprehensive-multi-modal-video | 40.6 |
| zero-shot-video-question-answering-via-frozen | 59.7 |
| zero-shot-video-question-answering-via-frozen | 29.7 |
| internvideo-general-video-foundation-models | 35.9 |
| an-image-grid-can-be-worth-a-video-zero-shot | 57.8 |
| mvbench-a-comprehensive-multi-modal-video | 50.6 |
| mvbench-a-comprehensive-multi-modal-video | 46.4 |
| self-chained-image-language-model-for-video-1 | 38.2 |
| minigpt4-video-advancing-multimodal-llms-for | 54.21 |