@article{deeplearningbasedmultimodaladdressee,
  title = {Deep Learning Based Multi-modal Addressee Recognition in Visual Scenes with Utterances},
  author = {Thao Minh Le and Nobuyuki Shimizu and Takashi Miyazaki and Koichi Shinoda},
  year = {2018},
  eprint = {1809.04288},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1809.04288v1},
}