@article{anaudiovisualdatasetanddeeplearning,
  title = {An Audio-Visual Dataset and Deep Learning Frameworks for Crowded Scene Classification},
  author = {Lam Pham and Dat Ngo and Phu X. Nguyen and Truong Hoang and Alexander Schindler},
  year = {2021},
  eprint = {2112.09172},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2112.09172v1},
}