MRMKG (Lee et al., 2024) uses Relational Graph Attention Networks (RGAT) to encode multimodal knowledge graphs and includes a cross-modal module for image-text alignment.

Authors

• Person: Not available Organization: Frontiers
  Practices, opportunities and challenges in the fusion of knowledge ...

Sources

• Practices, opportunities and challenges in the fusion of knowledge ... www.frontiersin.org Frontiers via serper

Referenced by nodes (1)

• multimodal knowledge graphs concept