Multimodal Topic Modeling

Multimodal Topic Modeling is a computational framework within topic modeling that integrates and analyzes multiple modalities of data—such as text, image, audio, or video—to jointly discover latent thematic structures that are coherent across different forms of representation.

120

Publications

5.4K

Citations

422

Authors

202

Institutions

Publications per year

2017–2026

69

Authors

422

  1. CX
    Changsheng Xu

    Chinese Academy of Sciences, China

    7 publications · 428 citations

    7

    h-index

  2. SQ
    Shengsheng Qian

    Institute of Automation, China

    6 publications · 364 citations

    6

    h-index

  3. TZ
    Tianzhu Zhang

    University of Science and Technology of China, China

    4 publications · 300 citations

    4

    h-index

  4. QH
    Qingming Huang

    University of Chinese Academy of Sciences, China

    4 publications · 77 citations

    4

    h-index

  5. BB
    Bing‐Kun Bao

    Nanjing University of Posts and Telecommunications, China

    3 publications · 229 citations

    3

    h-index

1–5 of 422

Venues

  1. IEEE Transactions on Multimedia

    8 publications · 525 citations

    8

    h-index

  2. IEEE Access

    5 publications · 113 citations

    5

    h-index

  3. Neurocomputing

    4 publications · 121 citations

    4

    h-index

  4. arXiv (Cornell University)

    Repository · 4 publications · 87 citations

    4

    h-index

  5. 3

    h-index

1–5