Embedding Learning For Retrieval

Embedding Learning for Retrieval is a machine learning framework that maps visual and/or textual data into a shared semantic space such that the relative proximity of embeddings reflects the relevance between images and their associated queries, enabling effective content-based image retrieval.

286

Publications

20.7K

Citations

966

Authors

305

Institutions

Publications per year

2017–2026

237

Authors

966

  1. SX
    Shitao Xiao

    Beijing University of Posts and Telecommunications, China

    6 publications · 548 citations

    7

    h-index

  2. JC
    Jamie Callan

    Carnegie Mellon University, United States

    6 publications · 406 citations

    6

    h-index

  3. ZL
    Zheng Liu

    Microsoft Research Asia (China), China

    6 publications · 548 citations

    6

    h-index

  4. SL
    Svetlana Lazebnik

    University of Illinois Urbana-Champaign, United States

    6 publications · 3.1K citations

    6

    h-index

  5. CG
    Cathal Gurrin

    Dublin City University, Ireland

    5 publications · 150 citations

    5

    h-index

1–5 of 966

Venues

  1. arXiv (Cornell University)

    Repository · 39 publications · 2.4K citations

    24

    h-index

  2. Pattern Recognition

    10 publications · 317 citations

    10

    h-index

  3. 7

    h-index

  4. IEEE Transactions on Multimedia

    6 publications · 209 citations

    6

    h-index

  5. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 6 publications · 321 citations

    6

    h-index

1–5