@article{vitocvisiontransformerandobjectaware,
  title = {ViTOC: Vision Transformer and Object-aware Captioner},
  author = {Feiyang Huang},
  year = {2024},
  eprint = {2411.07265},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2411.07265v4},
}