@article{vlcdocvisionlanguagecontrastivepre,
  title = {VLCDoC: Vision-Language Contrastive Pre-Training Model for Cross-Modal Document Classification},
  author = {Souhail Bakkali and Zuheng Ming and Mickael Coustaty and Marçal Rusiñol and Oriol Ramos Terrades},
  year = {2022},
  eprint = {2205.12029},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2205.12029v3},
}