@inproceedings{vitcomervisiontransformerwith1,
  title = {ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions},
  author = {Chunlong Xia and Xinliang Wang and Feng Lv and Xin Hao and Yifeng Shi},
  year = {2024},
  booktitle = {CVPR 2024 1},
  eprint = {2403.07392},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.07392v3},
}