@article{optimizinglatencyforonlinevideo,
  title = {Optimizing Latency for Online Video CaptioningUsing Audio-Visual Transformers},
  author = {Chiori Hori and Takaaki Hori and Jonathan Le Roux},
  year = {2021},
  eprint = {2108.02147},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2108.02147v1},
}