Multimodal Input Fusion

Multimodal Input Fusion is a computational framework that integrates heterogeneous input data from multiple modalities into a unified representation by aligning and combining modality-specific features through learned or engineered fusion mechanisms.

79

Publications

4.4K

Citations

335

Authors

149

Institutions

Publications per year

2017–2026

55

Authors

335

  1. YG
    Yuanxu Gao

    Macau University of Science and Technology, Macao SAR China

    2 publications · 310 citations

    2

    h-index

  2. FC
    Fang Chen

    Data61, Australia

    2 publications · 32 citations

    2

    h-index

  3. JP
    Jia Pan

    University of Hong Kong, Hong Kong SAR China

    2 publications · 310 citations

    2

    h-index

  4. WL
    Weimin Li

    Sichuan University, China

    2 publications · 310 citations

    2

    h-index

  5. KZ
    Kang Zhang

    University of California San Diego, United States

    2 publications · 310 citations

    2

    h-index

1–5 of 335

Venues

  1. arXiv (Cornell University)

    Repository · 3 publications · 148 citations

    3

    h-index

  2. 2

    h-index

  3. IEEE Transactions on Multimedia

    2 publications · 44 citations

    2

    h-index

  4. Sensors

    2 publications · 34 citations

    2

    h-index

  5. 2

    h-index

1–5