Compositional Visual Genome

The Compositional Visual Genome (ComVG) dataset is a reconstructed dataset of the Visual Genome (Krishna et al., 2017) dataset, containing 108,007 images annotated with 2.3 million relationships.

Data and Resources

Cite this as

Xuehai He, Weixi Feng, Tsu-Jui Fu, Varun Jampani, Arjun Akula, Pradyumna Narayana, Sugato Basu, William Yang Wang (2024). Dataset: Compositional Visual Genome. https://doi.org/10.57702/kvdtdksq

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2305.10722
Author Xuehai He
More Authors
Weixi Feng
Tsu-Jui Fu
Varun Jampani
Arjun Akula
Pradyumna Narayana
Sugato Basu
William Yang Wang
Homepage https://github.com/eric-ai-lab/DSD