@article{looklistenandattendcoattentionnetwork,
  title = {Look, Listen, and Attend: Co-Attention Network for Self-Supervised Audio-Visual Representation Learning},
  author = {Ying Cheng and Ruize Wang and Zhihao Pan and Rui Feng and Yuejie Zhang},
  year = {2020},
  eprint = {2008.05789},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2008.05789v1},
}