@inproceedings{visiontransformersareparameterefficient,
  title = {Vision Transformers are Parameter-Efficient Audio-Visual Learners},
  author = {Yan-Bo Lin and Yi-Lin Sung and Jie Lei and Mohit Bansal and Gedas Bertasius},
  year = {2022},
  booktitle = {CVPR 2023 1},
  eprint = {2212.07983},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2212.07983v2},
}