@inproceedings{vilsumenhancingvisionandlanguage,
  title = {ViL-Sum: Enhancing Vision and Language Representations via Multi-task Learning for Multi-modal Summarization},
  author = {Anonymous},
  year = {2022},
  booktitle = {ACL ARR January 2022 1},
  url = {https://openreview.net/forum?id=2J8zoGnOTn},
}