Transformer-based Recognition

Transformer-Based Recognition is a paradigm in optical character recognition that employs transformer architectures to model long-range dependencies and contextual relationships in text imagery through self-attention mechanisms, distinguishing itself from convolutional or recurrent approaches by its global receptive field and parallel sequence processing.

330

Publications

81K

Citations

1.4K

Authors

386

Institutions

Publications per year

2017–2026

327

Authors

1.4K

  1. JF
    Jiashi Feng

    National University of Singapore, Singapore

    5 publications · 980 citations

    5

    h-index

  2. YW
    Yongqiang Wang

    Clemson University, United States

    4 publications · 171 citations

    4

    h-index

  3. SL
    Shujie Liu

    Microsoft Research Asia (China), China

    4 publications · 262 citations

    4

    h-index

  4. YW
    Yixuan Wei

    Tsinghua University, China

    4 publications · 32.5K citations

    4

    h-index

  5. WL
    Wenyu Liu

    Huazhong University of Science and Technology, China

    4 publications · 291 citations

    4

    h-index

1–5 of 1.4K

Venues

  1. arXiv (Cornell University)

    Repository · 73 publications · 26K citations

    33

    h-index

  2. 17

    h-index

  3. IEEE Access

    8 publications · 280 citations

    8

    h-index

  4. Sensors

    7 publications · 214 citations

    7

    h-index

  5. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 7 publications · 1.1K citations

    7

    h-index

1–5