Implementation of the proposed LVMAE, from the paper, Extending Video Masked Autoencoders to 128 frames, in Pytorch
@inproceedings{Gundavarapu2024ExtendingVM,
title = {Extending Video Masked Autoencoders to 128 frames},
author = {Nitesh Bharadwaj Gundavarapu and Luke Friedman and Raghav Goyal and Chaitra Hegde and Eirikur Agustsson and Sagar M. Waghmare and Mikhail Sirotenko and Ming Yang and Tobias Weyand and Boqing Gong and Leonid Sigal},
year = {2024},
url = {https://api.semanticscholar.org/CorpusID:274166018}
}