Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

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

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

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

Models/HTR-VT(line-level)

HTR-VT(line-level)

Reported on 8 benchmarks across 2 tasks · 1 paper · 2 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
WER· 2024-09-13
14.9
SOTA
HTR-VT: Handwritten Text Recognition with Vision Transformer arXiv:2409.08573
Optical Character Recognition (OCR)onREAD 2016
CER (%)· 2024-09-13
3.9
best: 3.22 (DAN)
HTR-VT: Handwritten Text Recognition with Vision Transformer arXiv:2409.08573
Optical Character Recognition (OCR)onREAD 2016
WER (%)· 2024-09-13
16.5
best: 13.63 (DAN)
HTR-VT: Handwritten Text Recognition with Vision Transformer arXiv:2409.08573
Optical Character Recognition (OCR)onIAM
CER· 2024-09-13
4.7
best: 2.38 (DTrOCR 105M)
HTR-VT: Handwritten Text Recognition with Vision Transformer arXiv:2409.08573

Adversarial4 results

Handwritten Text RecognitiononIAM
WER· 2024-09-13
14.9
SOTA
HTR-VT: Handwritten Text Recognition with Vision Transformer arXiv:2409.08573
Handwritten Text RecognitiononREAD 2016
CER (%)· 2024-09-13
3.9
best: 3.22 (DAN)
HTR-VT: Handwritten Text Recognition with Vision Transformer arXiv:2409.08573
Handwritten Text RecognitiononREAD 2016
WER (%)· 2024-09-13
16.5
best: 13.63 (DAN)
HTR-VT: Handwritten Text Recognition with Vision Transformer arXiv:2409.08573
Handwritten Text RecognitiononIAM
CER· 2024-09-13
4.7
best: 2.38 (DTrOCR 105M)
HTR-VT: Handwritten Text Recognition with Vision Transformer arXiv:2409.08573