VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

Citation

(Tong et al., 2022)

Tong, Z., Song, Y., Wang, J., & Wang, L. (2022). VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training. https://arxiv.org/pdf/2203.12602