BLIP2

A vision-language pre-training dataset, BLIP2, which consists of 100 million image-text pairs.

Data and Resources

Cite this as

Yun Liu, Yun Liu (2024). Dataset: BLIP2. https://doi.org/10.57702/2f5q6lwh

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2312.06738
Citation
  • https://doi.org/10.48550/arXiv.2401.07519
  • https://doi.org/10.48550/arXiv.2306.06870
Author Yun Liu
More Authors
Yun Liu
Homepage https://ai.stanford.edu/~jgao/BLIP2/