@inproceedings{multimodalpretrainingfordensevideo,
  title = {Multimodal Pretraining for Dense Video Captioning},
  author = {Gabriel Huang and Bo Pang and Zhenhai Zhu and Clara Rivera and Radu Soricut},
  year = {2020},
  booktitle = {Asian Chapter of the Association for Computational Linguistics 2020},
  eprint = {2011.11760},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2011.11760v1},
}