@article{learningmultimodalrepresentationsby,
  title = {Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures},
  author = {Kun Yuan and Vinkle Srivastav and Tong Yu and Joel L. Lavanchy and Jacques Marescaux and Pietro Mascagni and Nassir Navab and Nicolas Padoy},
  year = {2023},
  eprint = {2307.15220},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2307.15220v4},
}