Self-supervised Object Recognition

Self-Supervised Object Recognition is a machine learning paradigm within object recognition that leverages unlabeled data to generate supervisory signals from the input itself, enabling the model to learn discriminative features without explicit human-annotated labels.

49

Publications

4.2K

Citations

208

Authors

70

Institutions

Publications per year

2017–2026

40

Authors

208

  1. AG
    Abhinav Gupta

    Carnegie Mellon University, United States

    4 publications · 353 citations

    4

    h-index

  2. HX
    Hang Xu

    Huawei Technologies (Sweden), Sweden

    3 publications · 199 citations

    3

    h-index

  3. AZ
    Andrew Zisserman

    University of Oxford, United Kingdom

    3 publications · 821 citations

    3

    h-index

  4. CY
    Chaoqiang Ye

    Huawei Technologies (Sweden), Sweden

    2 publications · 166 citations

    2

    h-index

  5. CX
    Chunjing Xu

    The University of Sydney, Australia

    2 publications · 166 citations

    2

    h-index

1–5 of 208

Venues

  1. arXiv (Cornell University)

    Repository · 15 publications · 718 citations

    13

    h-index

  2. 4

    h-index

  3. 2021 IEEE/CVF International Conference on Computer Vision (ICCV)

    Conference · 2 publications · 334 citations

    2

    h-index

  4. Neural Information Processing Systems

    Conference · 2 publications · 36 citations

    2

    h-index

  5. 1

    h-index

1–5