@misc{arxiv_2610_19559v1,
  title = {Learning Visual Speech Representations via Cross-Modal Distillation and Joint Face-Lip Modeling},
  author = {{Jing-Xuan Zhang} and {Genshun Wan} and {Jianqing Gao} and {Jia Pan} and {Yumei Zhang} and {Lichen Zhang}},
  eprint = {2610.19559v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.19559v1}
}