Fact-based Visual Question Answering (FVQA)
Question AnsweringVisualEnglish
Created by Wang et al. at 2017, the Fact-based Visual Question Answering (FVQA) is a question answering dataset in English containing 5,826 questions; 2,190 images records in JSON format.
Details
- Task
- Question Answering, Visual
- Language
- English
- Format
- JSON
- Rows / instances
- 5,826 questions; 2,190 images
- Creator
- Wang et al.
- Year
- 2017