Concepedia

Multi-view Self-supervision

Multi-View Self-Supervision is a self-supervised learning framework that leverages multiple observational perspectives of the same physical scene or event as the genus of correlated data modalities, differentiating itself by exploiting cross-view consistency and invariance as supervisory signals to learn rich, generalizable representations without manual annotation.

20

Publications

1.4K

Citations

100

Authors

32

Institutions

Publications per year

2017–2026

19

Parents

Publications

20

Multi-view self-supervised deep learning for 6D pose estimation in the Amazon Picking Challenge

Andy Zeng, Kuan‐Ting Yu, Shuran Song et al. · 2017 · 487 citations

, , +17

3D Semi-Supervised Learning with Uncertainty-Aware Multi-View Co-Training

Yingda Xia, Fengze Liu, Dong Yang et al. · 2020 · 171 citations

, , +16

Rotate-and-Render: Unsupervised Photorealistic Face Rotation From Single-View Images

Hang Zhou, Jihao Liu, Ziwei Liu et al. · 2020 · 141 citations

, , +12

Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm

Yangguang Li, Feng Liang, Li-Chen Zhao et al. · arXiv (Cornell University) · 2021 · 127 citations · Full text

, , +11

Multi-view graph embedding clustering network: Joint self-supervision and block diagonal representation

Wei Xia, Sen Wang, Ming Yang et al. · Neural Networks · 2021 · 93 citations

, , +13

1–5 of 20

Authors

100

  1. KY
    Kuan‐Ting Yu

    Massachusetts Institute of Technology, United States

    2 publications · 523 citations

    2

    h-index

  2. ZL
    Ziwei Liu

    Nanyang Technological University, Singapore

    2 publications · 163 citations

    2

    h-index

  3. AZ
    Andy Zeng

    Google (United States), United States

    2 publications · 523 citations

    2

    h-index

  4. JL
    Jihao Liu

    Chinese University of Hong Kong, Hong Kong SAR China

    2 publications · 163 citations

    2

    h-index

  5. AY
    Alan Yuille

    Johns Hopkins University, United States

    2 publications · 195 citations

    2

    h-index

1–5 of 100

Institutions

32

  1. Chinese University of Hong Kong

    Hong Kong, Hong Kong

    3 h-index

    9 publications

    823 citations

  2. Carnegie Mellon University

    Pittsburgh, United States

    2 h-index

    6 publications

    116 citations

  3. Princeton University

    Princeton, United States

    2 h-index

    8 publications

    2.5K citations

  4. Google (United States)

    Mountain View, United States

    2 h-index

    2 publications

    523 citations

  5. Switch

    Zurich, Switzerland

    2 h-index

    9 publications

    210 citations

  6. Beijing University of Posts and Telecommunications

    Beijing, China

    2 h-index

    9 publications

    210 citations

  7. Griffith University

    Brisbane, Australia

    1 h-index

    1 publications

    16 citations

  8. University of Minnesota

    Minneapolis, United States

    1 h-index

    1 publications

    13 citations

1–8 of 32

Venues

  1. arXiv (Cornell University)

    Repository · 6 publications · 237 citations

    6

    h-index

  2. 1

    h-index

  3. 1

    h-index

  4. 2021 IEEE/CVF International Conference on Computer Vision (ICCV)

    Conference · 1 publications · 63 citations

    1

    h-index

  5. Neural Networks

    1 publications · 93 citations

    1

    h-index

1–5