1. Deep Reinforcement Learning for Active Human Pose Estimation
2. Learning Texture Transformer Network for Image Super-Resolution
3. An image is worth 16x16 words: Transformers for image recognition at scale;dosovitskiy;arXiv preprint arXiv 2010 11419,2020
4. Wide-Context Semantic Image Extrapolation
5. Masked autoencoders are scalable vision learners;he;arXiv preprint arXiv 2111 02269,2021