Cross-domain Transfer

Cross-Domain Transfer is a transfer learning paradigm in which knowledge is transferred from a source domain to a target domain that differs in data distribution, feature space, or underlying context, thereby enabling learning in the target domain despite domain discrepancies.

930

Publications

96.4K

Citations

3K

Authors

737

Institutions

Publications per year

2017–2026

734

Authors

3K

  1. QY
    Qiang Yang

    Hong Kong University of Science and Technology, Hong Kong SAR China

    21 publications · 25.3K citations

    20

    h-index

  2. JW
    Jianmin Wang

    Tsinghua University, China

    21 publications · 6.4K citations

    18

    h-index

  3. ML
    Mingsheng Long

    Tsinghua University, China

    21 publications · 6.4K citations

    18

    h-index

  4. ZD
    Zhengming Ding

    Northeastern University, United States

    17 publications · 1.2K citations

    15

    h-index

  5. JL
    Jingjing Li

    University of Electronic Science and Technology of China, China

    13 publications · 1.3K citations

    13

    h-index

1–5 of 3K

Venues

  1. arXiv (Cornell University)

    Repository · 107 publications · 9K citations

    36

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 33 publications · 2.8K citations

    25

    h-index

  3. IEEE Transactions on Image Processing

    29 publications · 2.5K citations

    23

    h-index

  4. IEEE Transactions on Multimedia

    18 publications · 911 citations

    18

    h-index

  5. IEEE Transactions on Cybernetics

    16 publications · 668 citations

    16

    h-index

1–5