@inproceedings{ijcai2018p214,
  title     = {Deep Learning Based Multi-modal Addressee Recognition in Visual Scenes with Utterances},
  author    = {Le Minh, Thao and Shimizu, Nobuyuki and Miyazaki, Takashi and Shinoda, Koichi},
  booktitle = {Proceedings of the Twenty-Seventh International Joint Conference on
               Artificial Intelligence, {IJCAI-18}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Jérôme Lang},
  pages     = {1546--1553},
  year      = {2018},
  month     = {7},
  note      = {Main track},
  doi       = {10.24963/ijcai.2018/214},
  url       = {https://doi.org/10.24963/ijcai.2018/214},
}