Joint Embedding Learning

Joint Embedding Learning is a computational framework that, within the context of multi-omics integration, belongs to the class of feature-level fusion methods and is distinguished by its capacity to simultaneously map heterogeneous omics data modalities—such as single-cell and spatial multi-omics—into a shared latent representation space where biological relationships are preserved and integrative analysis can be performed.

212

Publications

20.1K

Citations

817

Authors

280

Institutions

Publications per year

2017–2026

180

Authors

817

  1. AZ
    Andrew Zisserman

    University of Oxford, United Kingdom

    6 publications · 479 citations

    6

    h-index

  2. BS
    Bernt Schiele

    Max Planck Institute for Informatics, Germany

    5 publications · 1.1K citations

    5

    h-index

  3. AK
    Amit K. Roy–Chowdhury

    University of California, Riverside, United States

    5 publications · 469 citations

    5

    h-index

  4. ZA
    Zeynep Akata

    Max Planck Institute for Informatics, Germany

    5 publications · 1.1K citations

    5

    h-index

  5. TX
    Tao Xiang

    Queen Mary University of London, United Kingdom

    5 publications · 1K citations

    5

    h-index

1–5 of 817

Venues

  1. arXiv (Cornell University)

    Repository · 30 publications · 2.6K citations

    21

    h-index

  2. IEEE Transactions on Multimedia

    8 publications · 476 citations

    8

    h-index

  3. Neurocomputing

    7 publications · 160 citations

    7

    h-index

  4. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 7 publications · 820 citations

    7

    h-index

  5. IEEE Transactions on Image Processing

    7 publications · 553 citations

    7

    h-index

1–5