AI RESEARCH
RMPL: Relation-aware Multi-task Progressive Learning with Stage-wise Training for Multimedia Event Extraction
arXiv CS.CL
•
ArXi:2602.13748v2 Announce Type: replace Multimedia Event Extraction (MEE) aims to identify events and their arguments from documents that contain both text and images. It requires grounding event semantics across different modalities. Progress in MEE is limited by the lack of annotated