@article{beyondimagetextmatchingverbunderstanding,
  title = {Beyond Image-Text Matching: Verb Understanding in Multimodal Transformers Using Guided Masking},
  author = {Ivana Beňová and Jana Košecká and Michal Gregor and Martin Tamajka and Marcel Veselý and Marián Šimko},
  year = {2024},
  eprint = {2401.16575},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2401.16575v1},
}