Visual Commonsense Graphs
Visual Question AnsweringCommonsenseEnglish
Visual Commonsense Graphs is a visual question answering-focused dataset in English that provides 59 labeled examples distributed in JSON, JPG format.
About Visual Commonsense Graphs
Dataset consists of over 1.4 million textual descriptions of visual commonsense inferences carefully annotated over a diverse set of 59,000 images, each paired with short video summaries of before and after.
Details
- Task
- Visual Question Answering, Commonsense
- Language
- English
- Format
- JSON, JPG
- Rows / instances
- 59
- Creator
- Park et al.
- Year
- 2020