1. Masked Autoencoders Are Scalable Vision Learners
2. Region attention networks for pose and occlusion robust facial expression recognition;wang;IEEE Transactions on Image Processing,2020
3. Understanding the difficulty of training deep feedforward neural networks;glorot;Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics,2010
4. Vision transformer for action units detection;vu,2023
5. Deep networks with stochastic depth;huang;European Conference on Computer Vision,2016