@inproceedings{crossmodalpromptsadaptinglargepre,
  title = {Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks},
  author = {Haoyi Duan and Yan Xia and Mingze Zhou and Li Tang and Jieming Zhu and Zhou Zhao},
  year = {2023},
  booktitle = {NeurIPS 2023 11},
  eprint = {2311.05152},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2311.05152v2},
}