@article{multimodalreferencelearningforfine,
  title = {Multi-modal Reference Learning for Fine-grained Text-to-Image Retrieval},
  author = {Zehong Ma and Hao Chen and Wei Zeng and Limin Su and Shiliang Zhang},
  year = {2025},
  eprint = {2504.07718},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2504.07718v1},
}