Compositional Visual Understanding

Compositional Visual Understanding is a computational framework that enables the interpretation of complex visual scenes by decomposing them into semantically meaningful components and their relational structures, thereby facilitating inference through systematic integration of part-whole hierarchies and contextual dependencies.

154

Publications

16.9K

Citations

518

Authors

176

Institutions

Publications per year

2017–2026

109

Authors

518

  1. AY
    Alan Yuille

    Johns Hopkins University, United States

    8 publications · 321 citations

    8

    h-index

  2. JB
    Joshua B. Tenenbaum

    Massachusetts Institute of Technology, United States

    6 publications · 531 citations

    6

    h-index

  3. AT
    Antonio Torralba

    Massachusetts Institute of Technology, United States

    5 publications · 153 citations

    5

    h-index

  4. SV
    Sjoerd van Steenkiste

    Dalle Molle Institute for Artificial Intelligence Research, Switzerland

    4 publications · 226 citations

    4

    h-index

  5. JS
    Jürgen Schmidhuber

    Dalle Molle Institute for Artificial Intelligence Research, Switzerland

    4 publications · 226 citations

    4

    h-index

1–5 of 518

Venues

  1. arXiv (Cornell University)

    Repository · 48 publications · 2.4K citations

    24

    h-index

  2. 5

    h-index

  3. 5

    h-index

  4. Neural Information Processing Systems

    Conference · 4 publications · 159 citations

    4

    h-index

  5. Cognitive Science

    3 publications · 110 citations

    3

    h-index

1–5