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

MSCOCO caption challenge dataset

The MSCOCO caption challenge dataset is a subset of the MSCOCO caption dataset, containing 113,287 training images, 5,000 validation images, and 5,000 test images.

Data and Resources

Cite this as

Jiajun Du, Yu Qin, Hongtao Lu, Yonghua Zhang (2024). Dataset: MSCOCO caption challenge dataset. https://doi.org/10.57702/knz565vz

DOI retrieved: December 17, 2024

Additional Info

Field Value
Created December 17, 2024
Last update December 17, 2024
Defined In https://doi.org/10.48550/arXiv.1812.03283
Author Jiajun Du
More Authors
Yu Qin
Hongtao Lu
Yonghua Zhang
Homepage https://mscoco.org/