Yuanze Lin, Chen Wei 0005, Huiyu Wang, Alan L. Yuille, Cihang Xie. SMAUG: Sparse Masked Autoencoder for Efficient Video-Language Pre-training. In IEEE/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1-6, 2023. pages 2459-2469, IEEE, 2023. [doi]
Abstract is missing.