i-CLEVR

i-CLEVR is a synthetic dataset generated using the CLEVR engine. Each scene contains five image-instruction pairs. Starting from a background image, new objects are added sequentially in a scene.

Data and Resources

Cite this as

J. Johnson, B. Hariharan, L. van der Maaten, L. Fei-Fei, C. Lawrence Zitnick, R. Girshick (2024). Dataset: i-CLEVR. https://doi.org/10.57702/j2sr20dv

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Author J. Johnson
More Authors
B. Hariharan
L. van der Maaten
L. Fei-Fei
C. Lawrence Zitnick
R. Girshick
Homepage https://figureqadataset.blob.core.windows.net/live-dataset/GeNeVA-models/iclevr_inception_best_checkpoint.pth?st=2019-08-16T20%3A34%3A22Z&se=3019-08-17T20%3A34%3A00Z&sp=rl&sv=2018-03-28&sr=b&sig=U9eRRPZHoZDOLOFWYnNAZ9attfFJKlGo28ZX7D%2BTIDk%3D