DocVQA

Introduced by Mathew et al. in DocVQA: A Dataset for VQA on Document Images

DocVQA consists of 50,000 questions defined on 12,000+ document images.

Source: DocVQA: A Dataset for VQA on Document Images

Homepage

Trend	Task	Dataset Variant	Best Model	Paper	Code
	Visual Question Answering (VQA)	DocVQA test	Human
	Visual Question Answering (VQA)	DocVQA val	BERT LARGE Baseline

Paper	Code	Results	Date	Stars

18,398

TextVQA