Open-set Recognition

Open-Set Recognition is a paradigm in computer vision that enables a model to correctly identify known classes during inference while simultaneously rejecting samples from unknown classes that were not present during training.

329

Publications

22.2K

Citations

1.1K

Authors

369

Institutions

Publications per year

2017–2026

228

Authors

1.1K

  1. TE
    Terrance E. Boult

    University of Colorado Colorado Springs, United States

    8 publications · 2.5K citations

    8

    h-index

  2. RS
    Richard S. Tyler

    University of Iowa, United States

    6 publications · 512 citations

    6

    h-index

  3. ZL
    Ziwei Liu

    Nanyang Technological University, Singapore

    6 publications · 2K citations

    6

    h-index

  4. SB
    Susan B. Waltzman

    New York University, United States

    6 publications · 279 citations

    6

    h-index

  5. AR
    Anderson Rocha

    Universidade Estadual de Campinas (UNICAMP), Brazil

    5 publications · 128 citations

    5

    h-index

1–5 of 1.1K

Venues

  1. IEEE Transactions on Pattern Analysis and Machine Intelligence

    TPAMI · 19 publications · 4.8K citations

    19

    h-index

  2. arXiv (Cornell University)

    Repository · 33 publications · 1.5K citations

    18

    h-index

  3. PubMed

    Repository · 14 publications · 546 citations

    13

    h-index

  4. Journal of Speech Language and Hearing Research

    JSLHR · 8 publications · 560 citations

    8

    h-index

  5. The Journal of the Acoustical Society of America

    JASA · 8 publications · 237 citations

    8

    h-index

1–5