@misc{han2023zero,
  title={Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions},
  author={Zeyu Han and Fangrui Zhu and Qianru Lao and Huaizu Jiang},
  year={2023},
  eprint={2311.17048},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2311.17048}
}