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
Parents
156
Multi-modal Knowledge Graphs for Recommender Systems
Rui Sun, Xuezhi Cao, Yan Zhao et al. · 2020 · 261 citations
Graph Convolution for Multimodal Information Extraction from Visually Rich Documents
Xiaojing Liu, Feiyu Gao, Qiong Zhang et al. · 2019 · 204 citations · Full text
1–5 of 156
572
8
h-index
5
h-index
5
h-index
4
h-index
4
h-index
1–5 of 572
192

Chinese Academy of Sciences
Beijing, China
13 h-index
33 publications
2.3K citations
University of Chinese Academy of Sciences
Beijing, China
9 h-index
23 publications
1.6K citations
University of Science and Technology of China
Hefei, China
9 h-index
22 publications
1.1K citations

Zhejiang University
Hangzhou, China
8 h-index
24 publications
1.8K citations
Peng Cheng Laboratory
Shenzhen, China
7 h-index
12 publications
635 citations
Tsinghua University
Beijing, China
6 h-index
15 publications
838 citations

Beijing University of Posts and Telecommunications
Beijing, China
6 h-index
8 publications
253 citations

Alibaba Group (China)
Hangzhou, China
5 h-index
25 publications
1.3K citations
1–8 of 192
Repository · 9 publications · 233 citations
10
h-index
Conference · 5 publications · 189 citations
7
h-index
7 publications · 426 citations
7
h-index
4 publications · 212 citations
5
h-index
3 publications · 72 citations
4
h-index
1–5