FVQA

FVQA is a fact-based visual question answering dataset, containing 2190 images and 5826 (question, answer) pairs, with supporting facts selected from knowledge bases.

Data and Resources

Cite this as

Wang et al. (2024). Dataset: FVQA. https://doi.org/10.57702/ovvtiz08

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2402.12846
Citation
  • https://doi.org/10.48550/arXiv.2402.12728
  • https://doi.org/10.48550/arXiv.1811.11903
Author Wang et al.
Homepage https://fvaq.org/