@article{apretrainedaudiovisualtransformerfor,
  title = {A Pre-trained Audio-Visual Transformer for Emotion Recognition},
  author = {Minh Tran and Mohammad Soleymani},
  year = {2022},
  eprint = {2201.09165},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2201.09165v1},
}