Unsupervised Object Recognition

Unsupervised Object Recognition is a methodological framework within computer vision that enables the identification and localization of objects in visual data without reliance on labeled training examples, distinguishing itself from supervised approaches by leveraging inherent data structures, statistical regularities, or clustering mechanisms to discover object categories autonomously.

105

Publications

17.6K

Citations

289

Authors

117

Institutions

Publications per year

2017–2026

30

Authors

289

  1. AV
    Andrea Vedaldi

    University of Oxford, United Kingdom

    6 publications · 550 citations

    6

    h-index

  2. SW
    Shangzhe Wu

    University of Oxford, United Kingdom

    3 publications · 330 citations

    3

    h-index

  3. PP
    Pietro Perona

    California Institute of Technology, United States

    3 publications · 2.9K citations

    3

    h-index

  4. CR
    Christian Rupprecht

    University of Oxford, United Kingdom

    3 publications · 330 citations

    3

    h-index

  5. HB
    Hakan Bilen

    University of Edinburgh, United Kingdom

    3 publications · 220 citations

    3

    h-index

1–5 of 289

Venues

  1. arXiv (Cornell University)

    Repository · 15 publications · 1.2K citations

    13

    h-index

  2. 7

    h-index

  3. Neural Computation

    3 publications · 111 citations

    3

    h-index

  4. Pattern Recognition Letters

    1 publications · 18 citations

    1

    h-index

  5. International Journal of Computer Vision

    1 publications · 190 citations

    1

    h-index

1–5