@inproceedings{multimodaltransformernetworksforendto,
  title = {Multimodal Transformer Networks for End-to-End Video-Grounded Dialogue Systems},
  author = {Hung Le and Doyen Sahoo and Nancy F. Chen and Steven C. H. Hoi},
  year = {2019},
  booktitle = {ACL 2019 7},
  eprint = {1907.01166},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1907.01166v1},
}