@article{duoformerleveraginghierarchicalvisual,
  title = {DuoFormer: Leveraging Hierarchical Visual Representations by Local and Global Attention},
  author = {Xiaoya Tang and Bodong Zhang and Beatrice S. Knudsen and Tolga Tasdizen},
  year = {2024},
  eprint = {2407.13920},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.13920v1},
}