Video Commonsense Reasoning (VCR)
Question AnsweringVisualCommonsenseEnglish
Video Commonsense Reasoning (VCR) is a question answering-focused dataset in English that provides 290 labeled examples distributed in JSON, JPG format.
Details
- Task
- Question Answering, Visual, Commonsense
- Language
- English
- Format
- JSON, JPG
- Rows / instances
- 290
- Creator
- Zellers et al.
- Year
- 2018