OrigamiNet-24

Reported on 4 benchmarks across 2 tasks · 1 paper · 4 SOTA

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

Methodology2 results

Optical Character Recognition (OCR)onLAM(line-level)
Test CER· 2020-06-12
3
best: 2.8 (HTR-VT)
SOTA
OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold arXiv:2006.07491
Optical Character Recognition (OCR)onLAM(line-level)
Test WER· 2020-06-12
11
best: 7.4 (HTR-VT)
SOTA
OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold arXiv:2006.07491

Adversarial2 results

Handwritten Text RecognitiononLAM(line-level)
Test CER· 2020-06-12
3
best: 2.8 (HTR-VT)
SOTA
OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold arXiv:2006.07491
Handwritten Text RecognitiononLAM(line-level)
Test WER· 2020-06-12
11
best: 7.4 (HTR-VT)
SOTA
OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold arXiv:2006.07491