TextVQA
Question AnsweringVisualCommonsenseEnglish
Created by Singh et al. at 2019, the TextVQA is a question answering dataset in English containing 36,602 records in JSON, PNG format.
About TextVQA
TextVQA requires models to read and reason about text in images to answer questions about them. Specifically, models need to incorporate a new modality of text present in the images and reason over it to answer TextVQA questions.
Details
- Task
- Question Answering, Visual, Commonsense
- Language
- English
- Format
- JSON, PNG
- Rows / instances
- 36,602
- Creator
- Singh et al.
- Year
- 2019