Concepedia

Video Self-supervised Learning

Video Self-Supervised Learning is a machine learning paradigm that enables models to learn spatiotemporal representations from unlabeled video data by leveraging the inherent temporal coherence and structure of video sequences as supervisory signals.

142

Publications

10.8K

Citations

572

Authors

206

Institutions

Publications per year

2017–2026

135

Parents

Publications

142

VideoBERT: A Joint Model for Video and Language Representation Learning

Chen Sun, Austin Myers, Carl Vondrick et al. · 2019 · 1.1K citations

, , +16

Masked Feature Prediction for Self-Supervised Visual Pre-Training

Chen Wei, Haoqi Fan, Saining Xie et al. · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 2022 · 528 citations

, , +16

Self-Supervised Video Representation Learning with Odd-One-Out Networks

Basura Fernando, Hakan Bilen, Efstratios Gavves et al. · 2017 · 455 citations · Full text

, , +16

VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

Tong Zhan, Yibing Song, Jue Wang et al. · arXiv (Cornell University) · 2022 · 436 citations · Full text

, , +12

VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking

Limin Wang, Bingkun Huang, Zhiyu Zhao et al. · 2023 · 415 citations

, , +15

1–5 of 142

Authors

572

  1. AZ
    Andrew Zisserman

    University of Oxford, United Kingdom

    6 publications · 747 citations

    6

    h-index

  2. CS
    Cordelia Schmid

    Institut national de recherche en sciences et technologies du numérique, France

    5 publications · 1.3K citations

    5

    h-index

  3. DL
    Dezhao Luo

    University of Chinese Academy of Sciences, China

    5 publications · 394 citations

    5

    h-index

  4. YZ
    Yu Zhou

    Harbin Institute of Technology, China

    5 publications · 394 citations

    5

    h-index

  5. LW
    Limin Wang

    Nanjing University, China

    5 publications · 920 citations

    5

    h-index

1–5 of 572

Institutions

206

  1. University of Oxford

    Oxford, United Kingdom

    11 h-index

    24 publications

    2.5K citations

  2. Google (United States)

    Mountain View, United States

    8 h-index

    35 publications

    9K citations

  3. University of Chinese Academy of Sciences

    Beijing, China

    8 h-index

    23 publications

    1.7K citations

  4. Tencent (China)

    Shenzhen, China

    7 h-index

    23 publications

    1.3K citations

  5. Chinese Academy of Sciences

    Beijing, China

    5 h-index

    18 publications

    1.5K citations

  6. Meta (Israel)

    Tel Aviv, Israel

    5 h-index

    20 publications

    3.6K citations

  7. University of Toronto

    Toronto, Canada

    4 h-index

    11 publications

    368 citations

  8. Zhejiang University

    Hangzhou, China

    4 h-index

    12 publications

    346 citations

1–8 of 206

Venues

  1. arXiv (Cornell University)

    Repository · 25 publications · 1.5K citations

    16

    h-index

  2. 13

    h-index

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

    Conference · 10 publications · 354 citations

    10

    h-index

  4. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 7 publications · 623 citations

    7

    h-index

  5. IEEE Transactions on Image Processing

    5 publications · 478 citations

    5

    h-index

1–5