[NAACL 2022 Findings] Good Visual Guidance Makes A Better Extractor: Hierarchical Visual Prefix for Multimodal Entity and Relation Extraction

[IJCAI 2024] Continual Multimodal Knowledge Graph Construction

[CIKM'24] Reviving the Context: Camera Trap Species Classification as Link Prediction on Multimodal Knowledge Graphs

A multimodal architecture to build multimodal knowledge graphs with flexible multimodal feature extraction and dynamic multimodal concept generation

Knowledge Capturing from Multimodal Video-Textual Knowledge-Entity Linking

RConE algorithm for logical query answering over multimodal knowledge graphs

MMIE is a multimodal open information extraction library for constructing Mutimodal Knowledge Graphs (MMKGs).