Attention-based Querying

Attention-Based Query, within the academic context of Visual Querying, is a computational querying method that belongs to the class of attention mechanisms and is distinguished by its use of learned attention weights to selectively focus on relevant visual regions or features in response to a query, thereby enabling fine-grained and context-sensitive visual information retrieval.

19

Publications

3.9K

Citations

90

Authors

30

Institutions

Publications per year

2017–2026

16

Authors

90

  1. AS
    Alex Smola

    Carnegie Mellon University, United States

    2 publications · 2.3K citations

    2

    h-index

  2. AN
    Asaf Noy

    Alibaba Group (United States), United States

    2 publications · 123 citations

    2

    h-index

  3. GS
    Gilad Sharir

    Alibaba Group (Cayman Islands), Cayman Islands

    2 publications · 123 citations

    2

    h-index

  4. AB
    Avi Ben-Cohen

    Tel Aviv University, Israel

    2 publications · 123 citations

    2

    h-index

  5. TR
    Tal Ridnik

    Alibaba Group (Cayman Islands), Cayman Islands

    2 publications · 123 citations

    2

    h-index

1–5 of 90

Venues

  1. arXiv (Cornell University)

    Repository · 6 publications · 1K citations

    6

    h-index

  2. Proceedings of the VLDB Endowment

    PVLDB · 1 publications · 39 citations

    1

    h-index

  3. 1

    h-index

  4. 1

    h-index

  5. Proceedings of the National Academy of Sciences

    PNAS · 1 publications · 94 citations

    1

    h-index

1–5