Deep Early Fusion

Deep Early Fusion is an academic methodological framework within multimodal machine learning that integrates raw input data from multiple modalities at the earliest possible stage of processing through deep neural architectures to enable end-to-end learning of joint representations.

16

Publications

1.3K

Citations

49

Authors

29

Institutions

Publications per year

2017–2026

14

Authors

49

  1. QS
    Quansen Sun

    Nanjing University of Science and Technology, China

    1 publications · 17 citations

    1

    h-index

  2. RP
    Rae‐Hong Park

    Sogang University, South Korea

    1 publications · 16 citations

    1

    h-index

  3. HP
    Hyung‐Min Park

    Sogang University, South Korea

    1 publications · 16 citations

    1

    h-index

  4. MX
    M. X. Ortega

    Pontifícia Universidade Católica do Rio de Janeiro, Brazil

    1 publications · 23 citations

    1

    h-index

  5. JH
    Jung-Wook Hwang

    Sogang University, South Korea

    1 publications · 16 citations

    1

    h-index

1–5 of 49

Venues

  1. 1

    h-index

  2. 1

    h-index

  3. Sensors

    1 publications · 14 citations

    1

    h-index

  4. IEEE Transactions on Human-Machine Systems

    1 publications · 44 citations

    1

    h-index

  5. Artificial Intelligence Review

    1 publications · 46 citations

    1

    h-index

1–5