VQA-CP v2 and VQA 2.0

The dataset used in the paper is VQA-CP v2 and VQA 2.0, which are two standard datasets for visual question answering.

Data and Resources

Cite this as

Yusuke Hirota, Chenhui Chu, Noa Garcia, Mayu Otani, Ittetsu Taniguchi, Yuta Nakashima, Takao Onoye (2024). Dataset: VQA-CP v2 and VQA 2.0. https://doi.org/10.57702/k4gebcsa

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Author Yusuke Hirota
More Authors
Chenhui Chu
Noa Garcia
Mayu Otani
Ittetsu Taniguchi
Yuta Nakashima
Takao Onoye
Homepage https://arxiv.org/abs/2006.10084