MSCOCO dataset

The MSCOCO dataset is a large-scale image captioning dataset, containing 113,287 images with 5,000 validation images and 5,000 test images. The dataset is used for training and evaluating image captioning models.

Data and Resources

Cite this as

Zheng Ma Shi Zong Mianzhi Pan Jianbing Zhang, Shujian Huang, Xinyu Dai, Jiajun Chen (2024). Dataset: MSCOCO dataset. https://doi.org/10.57702/uatmnerr

DOI retrieved: November 25, 2024

Additional Info

Field Value
Created November 25, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.1908.06288
Citation
  • https://doi.org/10.48550/arXiv.2307.02773
  • https://doi.org/10.48550/arXiv.1811.10787
Author Zheng Ma Shi Zong Mianzhi Pan Jianbing Zhang
More Authors
Shujian Huang
Xinyu Dai
Jiajun Chen
Homepage https://github.com/aaronma2020/probing_vlp