TextVQA

TextVQA dataset consists of 28,418 images with 45,336 questions.

Data and Resources

Cite this as

Soumya Jahagirdar, Shankar Gangisetty, Anand Mishra (2025). Dataset: TextVQA. https://doi.org/10.57702/ay9djnkq

DOI retrieved: January 3, 2025

Additional Info

Field Value
Created January 3, 2025
Last update January 3, 2025
Defined In https://doi.org/10.48550/arXiv.2211.12950
Author Soumya Jahagirdar
More Authors
Shankar Gangisetty
Anand Mishra
Homepage https://arxiv.org/abs/1904.09633