CodeMNER: Vision-Language Models are Better Multimodal Named Entity Recognizers via Progressive Vision-Code Alignment.

@inproceedings{yu-2026-codemner, author = {Jiakang Yu and Shizhou Huang and Xiaode Chen and Hongtao Deng and Wang Gao and Xun Zhu}, editor = {Stevan Rudinac and Zi Huang and Marcel Worring and Lucia Vadicamo and Xirong Li and Pascal Mettes and Lizi Liao}, title = {{CodeMNER: Vision-Language Models are Better Multimodal Named Entity Recognizers via Progressive Vision-Code Alignment}}, booktitle = {{Proceedings of the 2026 International Conference on Multimedia Retrieval, ICMR 2026, Amsterdam, The Netherlands, June 16-19, 2026}}, pages = {497--505}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805622.3810770}, doi = {https://doi.org/10.1145/3805622.3810770} }