Xiaode Chen

2026

doi dblp

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

Jiakang Yu|Shizhou Huang|Xiaode Chen|Hongtao Deng|Wang Gao|Xun Zhu

Proceedings of the 2026 International Conference on Multimedia Retrieval, ICMR 2026, Amsterdam, The Netherlands, June 16-19, 2026