Multimodal Representation Learning

Multimodal Representation Learning is a subfield of representation learning that focuses on learning joint, interoperable representations from multiple distinct modalities—such as text, audio, image, and video—by modeling their semantic correspondences and complementary information to enable coherent understanding across heterogeneous data sources.

2K

Publications

164K

Citations

8K

Authors

1.1K

Institutions

Publications per year

2017–2026

1.7K

Authors

8K

  1. LN
    Liqiang Nie

    Shandong University, China

    30 publications · 2.6K citations

    26

    h-index

  2. LM
    Louis‐Philippe Morency

    Carnegie Mellon University, United States

    20 publications · 7K citations

    18

    h-index

  3. CX
    Changsheng Xu

    Chinese Academy of Sciences, China

    23 publications · 1.3K citations

    18

    h-index

  4. HH
    Haifeng Hu

    Sun Yat-sen University, China

    18 publications · 1.2K citations

    17

    h-index

  5. XX
    Xing Xu

    University of Electronic Science and Technology of China, China

    16 publications · 1.4K citations

    15

    h-index

1–5 of 8K

Venues

  1. arXiv (Cornell University)

    Repository · 343 publications · 24.6K citations

    72

    h-index

  2. IEEE Transactions on Multimedia

    80 publications · 5.3K citations

    43

    h-index

  3. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 75 publications · 7.2K citations

    43

    h-index

  4. IEEE Transactions on Pattern Analysis and Machine Intelligence

    TPAMI · 42 publications · 10.5K citations

    32

    h-index

  5. IEEE Transactions on Image Processing

    39 publications · 3.1K citations

    29

    h-index

1–5