RMPL: Relation-aware Multi-task Progressive Learning with Stage-wise Training for Multimedia Event Extraction 文章

ArXiv CS.CV2026-05-28NEWSen作者: Yongkang Jin, Jianwen Luo, Jingjing Wang, Jianmin Yao, Yu Hong
大语言模型
查看原文 →
关系图谱

RMPL: Relation-aware Multi-task Progressive Learning with Stage-wise Training for Multimedia Event Extraction · 相关技术

相关技术

Vision-Language ModelsVision--Language ModelsMultimedia Event ExtractionVLMRMPLLVLMsMEE