EgoSchema is very long-form video question-answering dataset, and benchmark to evaluate long video understanding capabilities of modern vision and language systems. Derived from Ego4D, EgoSchema consists of over 5000 human curated multiple choice question answer pairs, spanning over 250 hours of real video data, covering a very broad range of natural human activity and behavior.
Variants: EgoSchema, EgoSchema (subset), EgoSchema (fullset)
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Visual Question Answering (VQA) | Lyra-Pro | Lyra: An Efficient and Speech-Centric … | 2024-12-12 |
Recent papers with results on this dataset: