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

EPIC: Leveraging Per Image-Token Consistency for Vision-Language Pre-training

The proposed EPIC method is a pre-training approach that leverages more text tokens for learning vision-language associations.

Data and Resources

Cite this as

Yunhao Gou, Tom Ko, Hansi Yang, Mingxuan Wang, James Kwok, Yu Zhang (2024). Dataset: EPIC: Leveraging Per Image-Token Consistency for Vision-Language Pre-training. https://doi.org/10.57702/4s3ecd7l

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.2211.15398
Author Yunhao Gou
More Authors
Tom Ko
Hansi Yang
Mingxuan Wang
James Kwok
Yu Zhang
Homepage https://github.com/gyhdog99/epic