GIT: A Generative Image-to-text Transformer for Vision and Language

Jianfeng Wang, Zhengyuan Yang, Xiaowei Hu 0006, Linjie Li, Kevin Lin, Zhe Gan, Zicheng Liu 0001, Ce Liu 0001, Lijuan Wang. GIT: A Generative Image-to-text Transformer for Vision and Language. Trans. Mach. Learn. Res., 2022, 2022. [doi]

@article{WangYHLLGLLW22,
  title = {GIT: A Generative Image-to-text Transformer for Vision and Language},
  author = {Jianfeng Wang and Zhengyuan Yang and Xiaowei Hu 0006 and Linjie Li and Kevin Lin and Zhe Gan and Zicheng Liu 0001 and Ce Liu 0001 and Lijuan Wang},
  year = {2022},
  url = {https://openreview.net/forum?id=b4tMhpN0JC},
  researchr = {https://researchr.org/publication/WangYHLLGLLW22},
  cites = {0},
  citedby = {0},
  journal = {Trans. Mach. Learn. Res.},
  volume = {2022},
}