Beyond General Alignment: Fine-Grained Entity-Centric Image-Text Matching with Multimodal Attentive Experts.

@inproceedings{wang-2025-beyond, author = {Yaxiong Wang and Lianwei Wu and Lechao Cheng and Zhun Zhong and Yujiao Wu and Meng Wang}, editor = {Nicola Ferro and Maria Maistro and Gabriella Pasi and Omar Alonso and Andrew Trotman and Suzan Verberne}, title = {{Beyond General Alignment: Fine-Grained Entity-Centric Image-Text Matching with Multimodal Attentive Experts}}, booktitle = {{Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2025, Padua, Italy, July 13-18, 2025}}, pages = {792--802}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3726302.3729902}, doi = {https://doi.org/10.1145/3726302.3729902} }