@misc{mo2023segment,
  title={AV-SAM: Segment Anything Model Meets Audio-Visual Localization and Segmentation},
  author={Shentong Mo and Yapeng Tian},
  year={2023},
  eprint={2305.01836},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2305.01836}
}