About SBU Caption dataset

dandelin / ViLT

Code for the ICML 2021 (long talk) paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"

Apache License 2.0

1.36k stars 209 forks source link

Open 4fee8fea opened 2 years ago

4fee8fea commented 2 years ago

Hi @dandelin, Thanks for your great work and make it public!

we wanna follow your work, but the SBU Caption dataset becomes an obstacle. The URL has been inaccessible.

Could you please offer me a copy file including the [url - caption] pairs?

Thanks in advance!

bfshi commented 1 year ago

This link works: