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

MS-COCO

MS-COCO is a large-scale dataset containing 123,287 images with 5 human-annotated descriptions per image, used for image-text matching and retrieval tasks.

Data and Resources

Cite this as

Tsung-Yi Lin, Michael Maire, Serge Belongie, Deva Ramanan (2024). Dataset: MS-COCO. https://doi.org/10.57702/d0h8si72

DOI retrieved: November 25, 2024

Additional Info

Field Value
Created November 25, 2024
Last update November 25, 2024
Author Tsung-Yi Lin
More Authors
Michael Maire
Serge Belongie
Deva Ramanan