@article{dovisionandlanguagetransformerslearn,
  title = {Do Vision-and-Language Transformers Learn Grounded Predicate-Noun Dependencies?},
  author = {Mitja Nikolaus and Emmanuelle Salin and Stephane Ayache and Abdellah Fourtassi and Benoit Favre},
  year = {2022},
  eprint = {2210.12079},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2210.12079v1},
}