@inproceedings{victrvisualinformationcapturedtext1,
  title = {VICTR: Visual Information Captured Text Representation for Text-to-Vision Multimodal Tasks},
  author = {Caren Han and Siqu Long and Siwen Luo and Kunze Wang and Josiah Poon},
  year = {2020},
  booktitle = {COLING 2020 8},
  url = {https://aclanthology.org/2020.coling-main.277},
}