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

CLEVR-CoGenT

The CLEVR-CoGenT dataset is a dataset for visual question answering, where the questions consist on comparing the position of two objects.

Data and Resources

Cite this as

Johnson, Hariharan, Van Der Maaten, Fei-Fei, Girshick (2024). Dataset: CLEVR-CoGenT. https://doi.org/10.57702/v42pwykk

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.1007/s11633-022-1360-1
Citation
  • https://doi.org/10.48550/arXiv.2106.08170
Author Johnson
More Authors
Hariharan
Van Der Maaten
Fei-Fei
Girshick
Homepage https://cs.stanford.edu/people/jcjohns/clevr