@article{astudyonjointmodelinganddata,
  title = {A study on joint modeling and data augmentation of multi-modalities for audio-visual scene classification},
  author = {Qing Wang and Jun Du and Siyuan Zheng and Yunqing Li and Yajian Wang and Yuzhong Wu and Hu Hu and Chao-Han Huck Yang and Sabato Marco Siniscalchi and Yannan Wang and Chin-Hui Lee},
  year = {2022},
  eprint = {2203.04114},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2203.04114v3},
}