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

VQGCOCO

VQGCOCO is a dataset consisting of 2500 training images, 1250 validation images, and 1250 test images from MS COCO, each with 5 corresponding questions and 5 ground-truth captions.

Data and Resources

This dataset has no data

Cite this as

Mostafazadeh et al. (2024). Dataset: VQGCOCO. https://doi.org/10.57702/1we323um

DOI retrieved: November 25, 2024

Additional Info

Field Value
Created November 25, 2024
Last update November 25, 2024
Defined In https://doi.org/10.48550/arXiv.2002.10832
Author Mostafazadeh et al.
Homepage https://www.microsoft.com/en-us/download/details.aspx?id=53670