@article{leveraginglargevisionlanguagemodelas, title = {Leveraging Large Vision-Language Model as User Intent-aware Encoder for Composed Image Retrieval}, author = {Zelong Sun and Dong Jing and Guoxing Yang and Nanyi Fei and Zhiwu Lu}, year = {2024}, eprint = {2412.11087}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.11087v1}, }