@inproceedings{zeroshotreferringexpressioncomprehension, 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}, booktitle = {CVPR 2024 1}, eprint = {2311.17048}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2311.17048v3}, }