You're currently viewing an old version of this dataset. To see the current version, click here.

VQAv2

Visual Question Answering (VQA) has achieved great success thanks to the fast development of deep neural networks (DNN). On the other hand, the data augmentation, as one of the major tricks for DNN, has been widely used in many computer vision tasks.

Data and Resources

Cite this as

Yen-Chun Chen, Linjie Li, Licheng Yu, Ahmed El Kholy, Faisal Ahmed, Zhe Gan, Yu Cheng, Jingjing Liu (2024). Dataset: VQAv2. https://doi.org/10.57702/kob379ex

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.2305.10722
Citation
  • https://doi.org/10.48550/arXiv.2007.09592
  • https://doi.org/10.48550/arXiv.2402.08756
  • https://doi.org/10.48550/arXiv.2402.08360
Author Yen-Chun Chen
More Authors
Linjie Li
Licheng Yu
Ahmed El Kholy
Faisal Ahmed
Zhe Gan
Yu Cheng
Jingjing Liu
Homepage https://huggingface.co/datasets/vqa2