MeGraS: An Open-Source Store for Multimodal Knowledge Graphs

摘要

Multimodal knowledge graphs often separate easily represented information (text) from that which is not (multimedia documents like images, videos, or audio). This severely limits query expressiveness, as the engines lack access to the node contents stored externally. We present MeGraS, the MediaGraph Store, a novel storage and query engine for multimodal knowledge graphs. By storing multimedia documents directly in the graph, MeGraS allows the query engine to leverage their content for enhanced capabilities, making it natively capable of performing operations such as k-NN, segmentation, or deriving non-materialized relations based on visual features. To demonstrate this, we incorporate and extend the pattern-matching query language SPARQL, resulting in a unified framework for storing and managing multimodal knowledge graphs with advanced expressiveness. MeGraS is available as open-source software: http://megras.org