ViTextVQA contains over 16,000 images and over 50,000 questions with answers. The dataset is designed to evaluate the ability of AI models to comprehend text within images and answer questions based on that understanding.
The purpose of ViTextVQA is to provide a benchmark for evaluating the reading comprehension ability of Visual Question Answering (VQA) models in the Vietnamese language. As a developing country, Vietnam is still in need of resources and benchmarks to advance research in AI and machine learning.

please contact 21521333@gm.uit.edu.vn or haryquan.minh@gmail.com for providing dataset