Concepedia

Sequence-to-sequence Recognition

Sequence-to-Sequence Recognition is a machine learning framework within optical character recognition that models the transcription of variable-length input sequences, such as images of text lines, into corresponding output sequences of characters or words by leveraging an encoder-decoder architecture with attention mechanisms.

606

Publications

49.2K

Citations

2K

Authors

505

Institutions

Publications per year

2017–2026

465

Variants

Seq2seq Recognition

Parents

Publications

606

Generating Sequences With Recurrent Neural Networks

DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · 2013 · 3.1K citations · Full text

, , +15

Longformer: The Long-Document Transformer

arXiv (Cornell University) · 2020 · 2.2K citations · Full text

, , +14

Convolutional Sequence to Sequence Learning

Jonas Gehring, Michael Auli, David Grangier et al. · arXiv (Cornell University) · 2017 · 1.9K citations · Full text

, , +10

Convolutional Sequence to Sequence Learning

Jonas Gehring, Michael Auli, David Grangier et al. · International Conference on Machine Learning · 2017 · 1.3K citations

, , +10

BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension

Mike Lewis, Yinhan Liu, Naman Goyal et al. · 2020 · 1.2K citations · Full text

, , +11

1–5 of 606

Authors

2K

  1. SW
    Shinji Watanabe

    Johns Hopkins University, United States

    11 publications · 1.3K citations

    11

    h-index

  2. RP
    Rohit Prabhavalkar

    Google (United States), United States

    12 publications · 1.3K citations

    11

    h-index

  3. NJ
    Navdeep Jaitly

    Pacific Northwest National Laboratory, United States

    12 publications · 1.9K citations

    11

    h-index

  4. TN
    Tara N. Sainath

    Google (United States), United States

    10 publications · 1K citations

    10

    h-index

  5. YW
    Yonghui Wu

    Google (United States), United States

    10 publications · 948 citations

    10

    h-index

1–5 of 2K

Institutions

505

  1. Google (United States)

    Mountain View, United States

    20 h-index

    125 publications

    11.1K citations

  2. Chinese Academy of Sciences

    Beijing, China

    20 h-index

    68 publications

    6.9K citations

  3. University of Chinese Academy of Sciences

    Beijing, China

    14 h-index

    44 publications

    5.5K citations

  4. Meta (Israel)

    Tel Aviv, Israel

    11 h-index

    45 publications

    20.6K citations

  5. Johns Hopkins University

    Baltimore, United States

    11 h-index

    33 publications

    5K citations

  6. Microsoft Research Asia (China)

    Beijing, China

    10 h-index

    25 publications

    1.3K citations

  7. Institute of Automation

    Beijing, China

    10 h-index

    33 publications

    4.6K citations

  8. Microsoft (United States)

    Redmond, United States

    10 h-index

    25 publications

    1.5K citations

1–8 of 505

Venues

  1. arXiv (Cornell University)

    Repository · 97 publications · 9K citations

    39

    h-index

  2. Pattern Recognition

    12 publications · 895 citations

    12

    h-index

  3. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 12 publications · 699 citations

    12

    h-index

  4. IEEE Access

    9 publications · 205 citations

    9

    h-index

  5. 8

    h-index

1–5