stoneMo

icon company Carnegie Mellon University

Results 2 comments of stoneMo

output of FastconvMAE

Thanks for your interest in our FastConvMAE. Motivated by the information density in MAE, we fixed the group size to 4. Each group covers 25% of tokens and reconstructs the...

which frame of the video is extracted?

Hi, thanks for your interest in our work. We extracted the middle frame as a single image from the video.