@inproceedings{zhu2020describing,
  title = {Describing unseen videos via multi-modal cooperative dialog agents},
  author = {Zhu, Ye and Wu, Yu and Yang, Yi and Yan, Yan},
  booktitle = {European Conference on Computer Vision (ECCV)},
  pages = {153--169},
  year = {2020},
  organization = {Springer},
}