Multimodal Event Detection

Multimodal Event Detection is an event detection paradigm that integrates and analyzes complementary information from multiple modalities—such as text, image, audio, and video—to identify and classify events in a unified semantic space, distinguishing it from unimodal approaches by leveraging cross-modal correlations for improved detection accuracy and contextual understanding.

301

Publications

14.1K

Citations

1.1K

Authors

366

Institutions

Publications per year

2017–2026

132

Authors

1.1K

  1. CX
    Changsheng Xu

    Chinese Academy of Sciences, China

    17 publications · 1.1K citations

    15

    h-index

  2. QT
    Qi Tian

    Huawei Technologies (China), China

    8 publications · 400 citations

    8

    h-index

  3. AD
    Ajay Divakaran

    Mitsubishi Electric (United States), United States

    6 publications · 261 citations

    6

    h-index

  4. XZ
    Xiaodan Zhuang

    University of Illinois Urbana-Champaign, United States

    6 publications · 375 citations

    6

    h-index

  5. SC
    Shih‐Fu Chang

    Columbia University, United States

    6 publications · 349 citations

    6

    h-index

1–5 of 1.1K

Venues

  1. IEEE Transactions on Multimedia

    9 publications · 638 citations

    9

    h-index

  2. arXiv (Cornell University)

    Repository · 6 publications · 289 citations

    6

    h-index

  3. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 5 publications · 232 citations

    5

    h-index

  4. MediaEval

    6 publications · 92 citations

    5

    h-index

  5. 5

    h-index

1–5