@article{multimodalperceptionattentionnetworkwith,
  title = {Multi-Modal Perception Attention Network with Self-Supervised Learning for Audio-Visual Speaker Tracking},
  author = {Yidi Li and Hong Liu and Hao Tang},
  year = {2021},
  eprint = {2112.07423},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2112.07423v1},
}