Multi-modal Knowledge Graph

The Multi-modal Knowledge Graph (MMKG) is a research direction that combines knowledge graphs with multi-modal learning, aiming to construct a richer and more comprehensive knowledge representation system by integrating data from multiple modalities such as text, images, and audio. The goal of MMKG is to enhance the expressive and reasoning capabilities of knowledge graphs in complex scenarios, thereby better supporting cross-modal tasks. Its application value lies in effectively addressing the issue of information silos, promoting interoperability between different modalities of data, and enhancing the understanding and generation abilities of intelligent systems.