@article{modelingparagraphlevelvisionlanguage,
  title = {Modeling Paragraph-Level Vision-Language Semantic Alignment for Multi-Modal Summarization},
  author = {Chenhao Cui and Xinnian Liang and Shuangzhi Wu and Zhoujun Li},
  year = {2022},
  eprint = {2208.11303},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2208.11303v3},
}