@misc{xu2022vitpose, title={ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation}, author={Yufei Xu and Jing Zhang and Qiming Zhang and Dacheng Tao}, year={2022}, eprint={2204.12484}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2204.12484} }