@article{transformerswithjointtokensandlocal,
  title = {Transformers with Joint Tokens and Local-Global Attention for Efficient Human Pose Estimation},
  author = {Kaleab A. Kinfu and René Vidal},
  year = {2025},
  eprint = {2503.00232},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.00232v1},
}