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

COCO Caption dataset

The COCO Caption dataset, containing 330,000 images with five independent human-generated captions each.

Data and Resources

This dataset has no data

Cite this as

Xinlei Chen, Hao Fang, Tsung-Yi Lin, Ramakrishna Vedantam, Saurabh Gupta, Piotr Dollár, C Lawrence Zitnick (2025). Dataset: COCO Caption dataset. https://doi.org/10.57702/n2kaqges

Private DOI This DOI is not yet resolvable.
It is available for use in manuscripts, and will be published when the Dataset is made public.

Additional Info

Field Value
Created January 3, 2025
Last update January 3, 2025
Defined In https://doi.org/10.48550/arXiv.2305.02297
Author Xinlei Chen
More Authors
Hao Fang
Tsung-Yi Lin
Ramakrishna Vedantam
Saurabh Gupta
Piotr Dollár
C Lawrence Zitnick
Homepage https://cocodataset.org/