Multimodal Knowledge Graphs

A Multimodal Knowledge Graph is a knowledge graph that integrates and represents heterogeneous knowledge from multiple modalities—such as text, images, audio, and video—by structuring entities and relations in a unified graph formalism where modal-specific representations are semantically aligned and jointly reason over cross-modal interactions.

156

Publications

6.6K

Citations

572

Authors

192

Institutions

Publications per year

2017–2026

145

Authors

572

  1. HC
    Huajun Chen

    Zhejiang University, China

    4 publications · 315 citations

    8

    h-index

  2. NZ
    Ningyu Zhang

    Zhejiang University, China

    3 publications · 260 citations

    5

    h-index

  3. ZC
    Zhuo Chen

    Zhejiang University, China

    2 publications · 85 citations

    5

    h-index

  4. JC
    Jiaoyan Chen

    University of Oxford, United Kingdom

    3 publications · 104 citations

    4

    h-index

  5. JZ
    Jeff Z. Pan

    University of Aberdeen, United Kingdom

    3 publications · 104 citations

    4

    h-index

1–5 of 572

Venues

  1. arXiv (Cornell University)

    Repository · 9 publications · 233 citations

    10

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 5 publications · 189 citations

    7

    h-index

  3. IEEE Transactions on Multimedia

    7 publications · 426 citations

    7

    h-index

  4. Information Fusion

    4 publications · 212 citations

    5

    h-index

  5. Neurocomputing

    3 publications · 72 citations

    4

    h-index

1–5