SOTAVerified

Optical Character Recognition

Papers

Showing 5175 of 526 papers

TitleStatusHype
Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image ClassificationCode1
A Comprehensive Gold Standard and Benchmark for Comics Text Detection and RecognitionCode1
SoftCTC -- Semi-Supervised Learning for Text Recognition using Soft Pseudo-LabelsCode1
Let's Enhance: A Deep Learning Approach to Extreme Deblurring of Text ImagesCode1
MCSCSet: A Specialist-annotated Dataset for Medical-domain Chinese Spelling CorrectionCode1
You Actually Look Twice At it (YALTAi): using an object detection approach instead of region segmentation within the Kraken engineCode1
Detection of Furigana Text in ImagesCode1
hmBERT: Historical Multilingual Language Models for Named Entity RecognitionCode1
BankNote-Net: Open dataset for assistive universal currency recognitionCode1
Digitizing Historical Balance Sheet Data: A Practitioner's GuideCode1
On the Cross-dataset Generalization in License Plate RecognitionCode1
An Automatic Approach for Generating Rich, Linked Geo-Metadata from Historical Map ImagesCode1
Lexically Aware Semi-Supervised Learning for OCR Post-CorrectionCode1
WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech RecognitionCode1
TrOCR: Transformer-based Optical Character Recognition with Pre-trained ModelsCode1
Post-OCR Document Correction with large Ensembles of Character Sequence-to-Sequence ModelsCode1
Lights, Camera, Action! A Framework to Improve NLP Accuracy over OCR documentsCode1
Robust Learning for Text Classification with Multi-source Noise Simulation and Hard Example MiningCode1
Implicit Feature Alignment: Learn to Convert Text Recognizer to Text SpotterCode1
Multi-Type-TD-TSR -- Extracting Tables from Document Images using a Multi-stage Pipeline for Table Detection and Table Structure Recognition: from OCR to Structured Table RepresentationsCode1
Unknown-box Approximation to Improve Optical Character Recognition PerformanceCode1
Operationalizing a National Digital Library: The Case for a Norwegian Transformer ModelCode1
Combining Morphological and Histogram based Text Line Segmentation in the OCR ContextCode1
Neural OCR Post-Hoc Correction of Historical CorporaCode1
Iranis: A Large-scale Dataset of Farsi License Plate CharactersCode1
Show:102550
← PrevPage 3 of 22Next →

No leaderboard results yet.