Learned Feature Embeddings

Learned Feature Embeddings is a type of representation learning method in which high-dimensional data are mapped into a lower-dimensional latent space through data-driven optimization, distinguishing itself from handcrafted feature extraction by enabling the model to autonomously discover and encode semantically meaningful patterns under task-specific objectives.

1.2K

Publications

124.9K

Citations

4.4K

Authors

962

Institutions

Publications per year

2017–2026

1K

Authors

4.4K

  1. LS
    Ling Shao

    Inception Institute of Artificial Intelligence, United Arab Emirates

    14 publications · 1.2K citations

    13

    h-index

  2. PS
    Philip S. Yu

    University of Illinois Chicago, United States

    11 publications · 2.4K citations

    11

    h-index

  3. SW
    Shiping Wang

    Fuzhou University, China

    7 publications · 269 citations

    7

    h-index

  4. WO
    Wanli Ouyang

    The University of Sydney, Australia

    6 publications · 1.7K citations

    6

    h-index

  5. YL
    Yong Li

    Tsinghua University, China

    6 publications · 475 citations

    6

    h-index

1–5 of 4.4K

Venues

  1. arXiv (Cornell University)

    Repository · 198 publications · 14K citations

    55

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 48 publications · 3.5K citations

    29

    h-index

  3. Pattern Recognition

    25 publications · 1.5K citations

    20

    h-index

  4. IEEE Transactions on Multimedia

    26 publications · 1.3K citations

    19

    h-index

  5. 19

    h-index

1–5