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

Visual Genome

Visual Genome is a large-scale dataset that provides dense image annotations with object, attribute, and relationship annotations. It contains 108k images and is utilized to pre-train the object detectors in the study.

Data and Resources

Cite this as

Zhou Yu, Qingming Huang (2024). Dataset: Visual Genome. https://doi.org/10.57702/p2euk5d9

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.2002.07417
Citation
  • https://doi.org/10.48550/arXiv.1912.12394
  • https://doi.org/10.48550/arXiv.1905.07841
Author Zhou Yu
More Authors
Qingming Huang
Homepage http://visualgenome.org/