@inproceedings{speech2actioncrossmodalsupervisionfor,
  title = {Speech2Action: Cross-modal Supervision for Action Recognition},
  author = {Arsha Nagrani and Chen Sun and David Ross and Rahul Sukthankar and Cordelia Schmid and Andrew Zisserman},
  year = {2020},
  booktitle = {CVPR 2020 6},
  eprint = {2003.13594},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2003.13594v1},
}