Feature-level Fusion

Feature-Level Fusion is a data integration paradigm within sensor fusion wherein extracted features from multiple sensor modalities are combined into a unified representation prior to final decision-making, distinguished from other fusion levels by operating on abstracted signal characteristics rather than raw data or independent decisions.

10.4K

Publications

505.7K

Citations

33.1K

Authors

4K

Institutions

Publications per year

2017–2026

8.2K

Authors

33.1K

  1. JM
    Jiayi Ma

    Wuhan University, China

    37 publications · 10.2K citations

    29

    h-index

  2. WZ
    Wujie Zhou

    Zhejiang University of Science and Technology, China

    33 publications · 2.7K citations

    25

    h-index

  3. QD
    Qian Du

    Mississippi State University, United States

    34 publications · 4.1K citations

    24

    h-index

  4. LJ
    Licheng Jiao

    Xidian University, China

    39 publications · 1.8K citations

    24

    h-index

  5. YL
    Yü Liu

    Hefei University of Technology, China

    30 publications · 7.5K citations

    22

    h-index

1–5 of 33.1K

Venues

  1. Information Fusion

    291 publications · 39.6K citations

    94

    h-index

  2. IEEE Transactions on Geoscience and Remote Sensing

    350 publications · 19.3K citations

    69

    h-index

  3. IEEE Access

    330 publications · 13.5K citations

    59

    h-index

  4. 54

    h-index

  5. IEEE Transactions on Image Processing

    103 publications · 11.1K citations

    53

    h-index

1–5