@article{selfsupervisedaudiovisualrepresentation,
  title = {Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity},
  author = {Pritam Sarkar and Ali Etemad},
  year = {2021},
  eprint = {2111.05329},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2111.05329v5},
}