In real-world scenarios, multimodal information continuously evolves, with new entity and relation types emerging, necessitating timely updates to multimodal knowledge graphs for supporting downstream tasks. However, existing methods struggle to balance real-time adaptability and computational efficiency in continual learning scenarios. To this end, this paper proposes the Continual Multimodal Entity and Relation Joint Extraction (CMERJE) task and a Multimodal Prompt-based Boundary-enhanced Continual (MPBoCo) framework. Specifically, MPBoCo incrementally stores task-specific knowledge via learnable multimodal prompts, dynamically matches relevant prompts for each instance, and fuses them into a frozen backbone model for task-specific reasoning. Subsequently, the boundary-enhanced dual-branch module leverages the auxiliary branch to preserve local syntactic continuity and provide boundary guidance. Experimental results demonstrate that MPBoCo achieves superior performance in real-world scenarios, significantly outperforming baseline methods by 5.5% and 7.2% in 10-task and 5-task settings, respectively.

Multimodal Named Entity Recognition (MNER) uses visual information to improve the performance of text-only Named Entity Recognition (NER). However, existing methods for acquiring local visual information suffer from certain limitations: (1) using an attention-based method to extract visual regions related to the text from visual regions obtained through convolutional architectures (e.g., ResNet), attention is distracted by the entire image, rather than being fully focused on the visual regions most relevant to the text; (2) using an object detection-based (e.g., Mask R-CNN) method to detect visual object regions related to the text, object detection has a limited range of recognition categories. Moreover, the visual regions obtained by object detection may not correspond to the entities in the text. In summary, the goal of these methods is not to extract the most relevant visual regions for the entities in the text. The visual regions obtained by these methods may be redundant or insufficient for the entities in the text. In this paper, we propose an Entity Spans Position Visual Regions (ESPVR) module to obtain the most relevant visual regions corresponding to the entities in the text. Experiments show that our proposed approach can achieve the SOTA on Twitter-2017 and competitive results on Twitter-2015.