1 result found Sort:

bcmi
Causal-VidQA bcmi
4
52
mit
10
[CVPR 2022] A large-scale public benchmark dataset for video question-answering, especially about evidence and commonsense reasoning. The code used in our paper "From Representation to Reasoning: Towa...
evidence-reason visual-understanding commonsense-reasoning video-question-answering video-question-answering-dataset
Created 2022-05-31
6 commits to master branch, last one 5 months ago