@article{vis2musexploringmultimodalrepresentation,
  title = {Vis2Mus: Exploring Multimodal Representation Mapping for Controllable Music Generation},
  author = {Runbang Zhang and Yixiao Zhang and Kai Shao and Ying Shan and Gus Xia},
  year = {2022},
  eprint = {2211.05543},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2211.05543v1},
}