@article{audiovisualsceneawaredialogandreasoning,
  title = {Audio-Visual Scene-Aware Dialog and Reasoning using Audio-Visual Transformers with Joint Student-Teacher Learning},
  author = {Ankit P. Shah and Shijie Geng and Peng Gao and Anoop Cherian and Takaaki Hori and Tim K. Marks and Jonathan Le Roux and Chiori Hori},
  year = {2021},
  eprint = {2110.06894},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2110.06894v1},
}