@inproceedings{learningspatialfeaturesfromaudiovisual,
  title = {Learning Spatial Features from Audio-Visual Correspondence in Egocentric Videos},
  author = {Sagnik Majumder and Ziad Al-Halah and Kristen Grauman},
  year = {2023},
  booktitle = {CVPR 2024 1},
  eprint = {2307.04760},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2307.04760v4},
}