@article{scalableaudiovisualmaskedautoencodersfor,
  title = {Scalable Audio-Visual Masked Autoencoders for Efficient Affective Video Facial Analysis},
  author = {Xuecheng Wu and Junxiao Xue and Xinyi Yin and Yunyun Shi and Liangyu Fu and Danlei Huang and Yifan Wang and Jia Zhang and Jiayu Nie and Jun Wang},
  year = {2025},
  eprint = {2509.24214},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.24214},
}