TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/OrigamiNet-12

OrigamiNet-12

Reported on 8 benchmarks across 2 tasks · 1 paper · 6 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology4 results

  • Optical Character Recognition (OCR)onIAM(line-level)
    Test CER· 2020-06-12
    6
    best: 3.4 (TrOCR)
    SOTA
    OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfoldarXiv:2006.07491
  • Optical Character Recognition (OCR)onIAM(line-level)
    Test WER· 2020-06-12
    22.3
    best: 14.9 (HTR-VT)
    SOTA
    OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfoldarXiv:2006.07491
  • Optical Character Recognition (OCR)onLAM(line-level)
    Test WER· 2020-06-12
    11.2
    best: 7.4 (HTR-VT)
    SOTA
    OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfoldarXiv:2006.07491
  • Optical Character Recognition (OCR)onLAM(line-level)
    Test CER· 2020-06-12
    3.1
    best: 2.8 (HTR-VT)
    OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfoldarXiv:2006.07491

Adversarial4 results

  • Handwritten Text RecognitiononIAM(line-level)
    Test CER· 2020-06-12
    6
    best: 3.4 (TrOCR)
    SOTA
    OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfoldarXiv:2006.07491
  • Handwritten Text RecognitiononIAM(line-level)
    Test WER· 2020-06-12
    22.3
    best: 14.9 (HTR-VT)
    SOTA
    OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfoldarXiv:2006.07491
  • Handwritten Text RecognitiononLAM(line-level)
    Test WER· 2020-06-12
    11.2
    best: 7.4 (HTR-VT)
    SOTA
    OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfoldarXiv:2006.07491
  • Handwritten Text RecognitiononLAM(line-level)
    Test CER· 2020-06-12
    3.1
    best: 2.8 (HTR-VT)
    OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfoldarXiv:2006.07491