@article{learningtomaskandpermutevisualtokens,
  title = {Learning to Mask and Permute Visual Tokens for Vision Transformer Pre-Training},
  author = {Roberto Amoroso and Marcella Cornia and Lorenzo Baraldi and Andrea Pilzer and Rita Cucchiara},
  year = {2023},
  eprint = {2306.07346},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2306.07346v2},
}