@article{unifiedmultimodalpretrainingandprompt,
  title = {Unified Multimodal Pre-training and Prompt-based Tuning for Vision-Language Understanding and Generation},
  author = {Tianyi Liu and Zuxuan Wu and Wenhan Xiong and Jingjing Chen and Yu-Gang Jiang},
  year = {2021},
  eprint = {2112.05587},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2112.05587v2},
}