MCIRP: A multi-granularity cross-modal interaction model based on relational propagation for Multimodal Named Entity Recognition with multiple images.

@article{mu-2026-mcirp, author = {Yongheng Mu and Ziyu Guo and Xuewei Li and Lixu Shao and Shijun Liu and Feng Li and Guangxu Mei}, title = {{MCIRP: A multi-granularity cross-modal interaction model based on relational propagation for Multimodal Named Entity Recognition with multiple images}}, journal = {Information Processing and Management}, volume = {63}, number = {2}, pages = {104384}, year = {2026}, url = {https://doi.org/10.1016/J.IPM.2025.104384}, doi = {https://doi.org/10.1016/J.IPM.2025.104384} }