| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Video Question Answering | NextQA | Accuracy85.4 | 78 | |
| Video Question Answering | NextQA | WUPS33.86 | 26 | |
| Video Question Answering | NextQA MC | Score86.3 | 24 | |
| Video Understanding | NextQA | Accuracy86.24 | 19 | |
| Video Question Answering | NextQA (val) | Accuracy85.5 | 11 | |
| Video Question Answering | NextQA (test) | Score84.1 | 7 | |
| Video-Language Understanding | NextQA | EM56.61 | 7 | |
| Multiple Choice Question Answering | NextQA (1,000 QA pairs sample) | Accuracy (%)76.8 | 2 | |
| Video Question Answering | NextQA 2021 (test) | Accuracy80.7 | 2 |