Attention-based Classification

Attention-Based Classification is a classification framework that employs attention mechanisms to selectively emphasize informative temporal segments or features within time series data, thereby improving model interpretability and predictive accuracy by differentiating relevant from irrelevant input regions.

453

Publications

32.6K

Citations

1.9K

Authors

578

Institutions

Publications per year

2017–2026

425

Authors

1.9K

  1. FP
    Felix Putze

    University of Bremen, Germany

    5 publications · 171 citations

    5

    h-index

  2. QK
    Qiuqiang Kong

    University of Surrey, United Kingdom

    4 publications · 378 citations

    4

    h-index

  3. LV
    Lisa-Marie Vortmann

    University of Bremen, Germany

    4 publications · 143 citations

    4

    h-index

  4. MD
    Mark D. Plumbley

    Queen Mary University of London, United Kingdom

    3 publications · 314 citations

    3

    h-index

  5. YX
    Yong Xu

    University of Surrey, United Kingdom

    3 publications · 314 citations

    3

    h-index

1–5 of 1.9K

Venues

  1. arXiv (Cornell University)

    Repository · 33 publications · 1.4K citations

    19

    h-index

  2. Neurocomputing

    15 publications · 1.7K citations

    15

    h-index

  3. IEEE Access

    13 publications · 2.1K citations

    13

    h-index

  4. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 11 publications · 1.4K citations

    11

    h-index

  5. Applied Sciences

    11 publications · 329 citations

    11

    h-index

1–5