@misc{kim2023region,
  title={Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers},
  author={Dahun Kim and Anelia Angelova and Weicheng Kuo},
  year={2023},
  eprint={2305.07011},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2305.07011}
}