@article{framesubtitleselfsupervisionformulti,
  title = {Frame-Subtitle Self-Supervision for Multi-Modal Video Question Answering},
  author = {Jiong Wang and Zhou Zhao and Weike Jin},
  year = {2022},
  eprint = {2209.03609},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2209.03609v1},
}