Skip to main content

Search AIMS

Find pages, publications, events, course projects, and software. Results update as you type; press Enter to open the first result.

Reasoning

EgoSchema

Tests understanding of everyday activities in long videos through caption-based question answering.

4,500items
11subjects
No explicit license was found for the captured LLoVi output/data archives or EgoSchema annotations. Do not infer MIT permission from the previous builder.license
reasoningdomain
textmodality
item-level responses released
Saturation status: No
About this data

Dataset name: EgoSchema (released LLoVi configurations)

Published LLoVi question-answering results on the 500-question public EgoSchema subset, retaining the available caption-based inputs and eleven model/prompt configurations.

4,500 items · 5,500 recorded attempts. Browse item pages to see all observations. Filters and means apply to the current page.

Loading observation records…