@article{multimodalvideorepresentationalignmentfo,
  title = {Multi-modal Video Representation Alignment for Robust Self-supervised Driver Distraction Detection},
  author = {David J. Lerch and Livien Majer and Zeyun Zhong and Manuel Martin and Frederik Diederichs and Rainer Stiefelhagen},
  year = {2026},
  eprint = {2606.02352},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.02352},
}