@article{synchronizedaudiovisualframeswith,
  title = {Synchronized Audio-Visual Frames with Fractional Positional Encoding for Transformers in Video-to-Text Translation},
  author = {Philipp Harzig and Moritz Einfalt and Rainer Lienhart},
  year = {2021},
  eprint = {2112.14088},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2112.14088v1},
}