@article{structuredvisionlanguagepretrainingfor,
  title = {Vision and Structured-Language Pretraining for Cross-Modal Food Retrieval},
  author = {Mustafa Shukor and Nicolas Thome and Matthieu Cord},
  year = {2022},
  eprint = {2212.04267},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2212.04267v2},
}