#artificial intelligence
Jun 2024
Long Story Short: Story-level Video Understanding from 20K Short Films
This work proposes Short-Films 20K (SF20K), the largest publicly available movie dataset, and accompanies this dataset with SF20K-Test, a manual, open-ended question answering benchmark, showing that instruction tuning on the large-scale dataset substantially improves model performance.
Ridouane Ghermi, Xi Wang, Vicky Kalogeiton et al.
· International Journal of Com... · 11 citations
· ⚡1