Video Question Answering On Agqa 2 0 Balanced
평가 지표
Average Accuracy
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | Average Accuracy |
|---|---|
| mist-multi-modal-iterative-spatial-temporal | 50.96 |
| glance-and-focus-memory-prompting-for-multi-1 | 53.33 |
| mist-multi-modal-iterative-spatial-temporal | 54.39 |
| learning-situation-hyper-graphs-for-video | 49.2 |
| glance-and-focus-memory-prompting-for-multi-1 | 48.59 |
| mmtf-multi-modal-temporal-fusion-for | 44.36 |
| svitt-temporal-learning-of-sparse-video-text | 52.7 |
| glance-and-focus-memory-prompting-for-multi-1 | 55.08 |