@article{efficientvideorepresentationlearningvia, title = {EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens}, author = {Sunil Hwang and Jaehong Yoon and Youngwan Lee and Sung Ju Hwang}, year = {2022}, eprint = {2211.10636}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2211.10636v6}, }