@article{visualrepresentationlearningwith,
  title = {Vision Transformers: From Semantic Segmentation to Dense Prediction},
  author = {Li Zhang and Jiachen Lu and Sixiao Zheng and Xinxuan Zhao and Xiatian Zhu and Yanwei Fu and Tao Xiang and Jianfeng Feng and Philip H. S. Torr},
  year = {2022},
  eprint = {2207.09339},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2207.09339v4},
}