Feature Pooling Models

Feature Pooling Models is a class of computational models in visual perception theory that accounts for the loss of object recognition in cluttered environments by averaging or integrating similar features across nearby regions in the visual field, thereby distinguishing itself from other crowding models through its reliance on local feature summation or statistical regularities as the primary mechanism underlying perceptual degradation.

94

Publications

16.7K

Citations

333

Authors

140

Institutions

Publications per year

2017–2026

53

Authors

333

  1. MH
    Michael H. Herzog

    École Polytechnique Fédérale de Lausanne, Switzerland

    3 publications · 223 citations

    3

    h-index

  2. MM
    Mauro Manassi

    University of California, Berkeley, United States

    2 publications · 166 citations

    2

    h-index

  3. HL
    Hong Liu

    Peking University, China

    2 publications · 35 citations

    2

    h-index

  4. MP
    Marcello Pelillo

    Ca' Foscari University of Venice, Italy

    2 publications · 198 citations

    2

    h-index

  5. XL
    Xi Li

    Zhejiang University, China

    2 publications · 47 citations

    2

    h-index

1–5 of 333

Venues

  1. arXiv (Cornell University)

    Repository · 8 publications · 1.1K citations

    8

    h-index

  2. IEEE Transactions on Multimedia

    6 publications · 125 citations

    6

    h-index

  3. Journal of Vision

    6 publications · 640 citations

    6

    h-index

  4. 5

    h-index

  5. Pattern Recognition

    3 publications · 100 citations

    3

    h-index

1–5