@article{audiovisualsceneawaredialoggeneration,
  title = {Audio Visual Scene-Aware Dialog Generation with Transformer-based Video Representations},
  author = {Yoshihiro Yamazaki and Shota Orihashi and Ryo Masumura and Mihiro Uchida and Akihiko Takashima},
  year = {2022},
  eprint = {2202.09979},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2202.09979v1},
}