@misc{hong2022cogvideo,
  title={CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers},
  author={Wenyi Hong and Ming Ding and Wendi Zheng and Xinghan Liu and Jie Tang},
  year={2022},
  eprint={2205.15868},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2205.15868}
}