Visual Text Question Answering (VTQA)

A new challenge named Visual Text Question Answering (VTQA) along with a corresponding dataset, which includes 23,781 questions based on 10,124 image-text pairs.

Data and Resources

Cite this as

Kang Chen, Xiangqian Wu (2024). Dataset: Visual Text Question Answering (VTQA). https://doi.org/10.57702/3i9nvd4e

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2303.02635
Author Kang Chen
More Authors
Xiangqian Wu
Homepage https://visual-text-QA.github.io/