@article{spatiotemporalscenegraphsforvideodialog,
  title = {Dynamic Graph Representation Learning for Video Dialog via Multi-Modal Shuffled Transformers},
  author = {Shijie Geng and Peng Gao and Moitreya Chatterjee and Chiori Hori and Jonathan Le Roux and Yongfeng Zhang and Hongsheng Li and Anoop Cherian},
  year = {2020},
  eprint = {2007.03848},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2007.03848v2},
}