@inproceedings{ijcai2017p492,
  title     = {Video Question Answering via Hierarchical Spatio-Temporal Attention Networks},
  author    = {Zhao, Zhou and Yang, Qifan and Cai, Deng and He, Xiaofei and Zhuang, Yueting},
  booktitle = {Proceedings of the Twenty-Sixth International Joint Conference on
               Artificial Intelligence, {IJCAI-17}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Carles Sierra},
  pages     = {3518--3524},
  year      = {2017},
  month     = {8},
  note      = {Main track},
  doi       = {10.24963/ijcai.2017/492},
  url       = {https://doi.org/10.24963/ijcai.2017/492},
}