@article{wang2022git, title={GIT: A Generative Image-to-text Transformer for Vision and Language}, author={Wang, Jianfeng and Yang, Zhengyuan and Hu, Xiaowei and Li, Linjie and Lin, Kevin and Gan, Zhe and Liu, Zicheng and Liu, Ce and Wang, Lijuan}, journal={arXiv preprint arXiv:2205.14100}, year={2022} }