@inproceedings{zhang2021rstnet,
  title={RSTNet: Captioning with adaptive attention on visual and non-visual words},
  author={Zhang, Xuying and Sun, Xiaoshuai and Luo, Yunpeng and Ji, Jiayi and Zhou, Yiyi and Wu, Yongjian and Huang, Feiyue and Ji, Rongrong},
  booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
  pages={15465--15474},
  year={2021}
}