{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/optical-character-recognition/papers/4","list_of":"/task/optical-character-recognition","task":"Optical Character Recognition (OCR)","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":4,"pages_in_order":13,"rows_per_page":100,"rows":[301,400],"of":1243,"counts":{"archive_papers_tagged":1243,"with_a_code_link":462,"where_syntology_ran_a_sample":76,"not_listed_spam_title":0,"listed":1243,"listed_where_code_ran":76,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":64,"every_run_a_failure_of_syntologys_instrument":12,"listed_with_a_run_with_no_instrument_failure":64,"listed_every_run_a_failure_of_syntologys_instrument":12,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/optical-character-recognition","prev":"/task/optical-character-recognition/papers/3","next":"/task/optical-character-recognition/papers/5","papers":[{"url":"/paper/noisy-parallel-data-alignment","slug":"noisy-parallel-data-alignment","title":"Noisy Parallel Data Alignment","date":"2023-01-23","arxiv_id":"2301.09685","repositories_listed":1,"syntology":null},{"url":"/paper/imkga-sm-interpretable-multimodal-knowledge","slug":"imkga-sm-interpretable-multimodal-knowledge","title":"IMKGA-SM: Interpretable Multimodal Knowledge Graph Answer Prediction via Sequence Modeling","date":"2023-01-06","arxiv_id":"2301.02445","repositories_listed":1,"syntology":null},{"url":"/paper/a-comprehensive-gold-standard-and-benchmark","slug":"a-comprehensive-gold-standard-and-benchmark","title":"A Comprehensive Gold Standard and Benchmark for Comics Text Detection and Recognition","date":"2022-12-27","arxiv_id":"2212.14674","repositories_listed":1,"syntology":null},{"url":"/paper/transferring-general-multimodal-pretrained","slug":"transferring-general-multimodal-pretrained","title":"Transferring General Multimodal Pretrained Models to Text Recognition","date":"2022-12-19","arxiv_id":"2212.09297","repositories_listed":1,"syntology":null},{"url":"/paper/wukong-reader-multi-modal-pre-training-for","slug":"wukong-reader-multi-modal-pre-training-for","title":"Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding","date":"2022-12-19","arxiv_id":"2212.09621","repositories_listed":1,"syntology":null},{"url":"/paper/ledcnet-a-lightweight-and-efficient-semantic","slug":"ledcnet-a-lightweight-and-efficient-semantic","title":"LOANet: A Lightweight Network Using Object Attention for Extracting Buildings and Roads from UAV Aerial Remote Sensing Images","date":"2022-12-16","arxiv_id":"2212.08490","repositories_listed":1,"syntology":null},{"url":"/paper/softctc-unicode-x2013-semi-supervised","slug":"softctc-unicode-x2013-semi-supervised","title":"SoftCTC -- Semi-Supervised Learning for Text Recognition using Soft Pseudo-Labels","date":"2022-12-05","arxiv_id":"2212.02135","repositories_listed":1,"syntology":null},{"url":"/paper/let-s-enhance-a-deep-learning-approach-to","slug":"let-s-enhance-a-deep-learning-approach-to","title":"Let's Enhance: A Deep Learning Approach to Extreme Deblurring of Text Images","date":"2022-11-18","arxiv_id":"2211.10103","repositories_listed":1,"syntology":null},{"url":"/paper/a-benchmark-and-dataset-for-post-ocr-text","slug":"a-benchmark-and-dataset-for-post-ocr-text","title":"A Benchmark and Dataset for Post-OCR text correction in Sanskrit","date":"2022-11-15","arxiv_id":"2211.07980","repositories_listed":1,"syntology":null},{"url":"/paper/nevis-22-a-stream-of-100-tasks-sampled-from","slug":"nevis-22-a-stream-of-100-tasks-sampled-from","title":"NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research","date":"2022-11-15","arxiv_id":"2211.11747","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/nevis-22-a-stream-of-100-tasks-sampled-from#ran","syntology_url":"https://syntology.ai/paper/2211.11747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.11747"}},"official":{"repos":["deepmind/dm_nevis"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/technical-report-on-web-based-visual-corpus","slug":"technical-report-on-web-based-visual-corpus","title":"On Web-based Visual Corpus Construction for Visual Document Understanding","date":"2022-11-07","arxiv_id":"2211.03256","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-audio-visual-lecture","slug":"unsupervised-audio-visual-lecture","title":"Unsupervised Audio-Visual Lecture Segmentation","date":"2022-10-29","arxiv_id":"2210.16644","repositories_listed":1,"syntology":null},{"url":"/paper/mcscset-a-specialist-annotated-dataset-for","slug":"mcscset-a-specialist-annotated-dataset-for","title":"MCSCSet: A Specialist-annotated Dataset for Medical-domain Chinese Spelling Correction","date":"2022-10-21","arxiv_id":"2210.11720","repositories_listed":1,"syntology":null},{"url":"/paper/task-grouping-for-multilingual-text","slug":"task-grouping-for-multilingual-text","title":"Task Grouping for Multilingual Text Recognition","date":"2022-10-13","arxiv_id":"2210.07423","repositories_listed":1,"syntology":null},{"url":"/paper/chandojnanam-a-sanskrit-meter-identification","slug":"chandojnanam-a-sanskrit-meter-identification","title":"Chandojnanam: A Sanskrit Meter Identification and Utilization System","date":"2022-09-29","arxiv_id":"2209.14924","repositories_listed":1,"syntology":null},{"url":"/paper/hapi-a-large-scale-longitudinal-dataset-of","slug":"hapi-a-large-scale-longitudinal-dataset-of","title":"HAPI: A Large-scale Longitudinal Dataset of Commercial ML API Predictions","date":"2022-09-18","arxiv_id":"2209.08443","repositories_listed":1,"syntology":null},{"url":"/paper/aim-taking-answers-in-mind-to-correct-chinese","slug":"aim-taking-answers-in-mind-to-correct-chinese","title":"AiM: Taking Answers in Mind to Correct Chinese Cloze Tests in Educational Applications","date":"2022-08-26","arxiv_id":"2208.12505","repositories_listed":1,"syntology":null},{"url":"/paper/graph-neural-networks-and-representation","slug":"graph-neural-networks-and-representation","title":"Graph Neural Networks and Representation Embedding for Table Extraction in PDF Documents","date":"2022-08-23","arxiv_id":"2208.11203","repositories_listed":1,"syntology":null},{"url":"/paper/character-decomposition-to-resolve-class","slug":"character-decomposition-to-resolve-class","title":"Character decomposition to resolve class imbalance problem in Hangul OCR","date":"2022-08-12","arxiv_id":"2208.06079","repositories_listed":1,"syntology":null},{"url":"/paper/marior-margin-removal-and-iterative-content","slug":"marior-margin-removal-and-iterative-content","title":"Marior: Margin Removal and Iterative Content Rectification for Document Dewarping in the Wild","date":"2022-07-23","arxiv_id":"2207.11515","repositories_listed":1,"syntology":null},{"url":"/paper/you-actually-look-twice-at-it-yaltai-using-an","slug":"you-actually-look-twice-at-it-yaltai-using-an","title":"You Actually Look Twice At it (YALTAi): using an object detection approach instead of region segmentation within the Kraken engine","date":"2022-07-19","arxiv_id":"2207.11230","repositories_listed":1,"syntology":null},{"url":"/paper/davarocr-a-toolbox-for-ocr-and-multi-modal","slug":"davarocr-a-toolbox-for-ocr-and-multi-modal","title":"DavarOCR: A Toolbox for OCR and Multi-Modal Document Understanding","date":"2022-07-14","arxiv_id":"2207.06695","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-low-resolution-distillation-for-cost","slug":"dynamic-low-resolution-distillation-for-cost","title":"Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting","date":"2022-07-14","arxiv_id":"2207.06694","repositories_listed":1,"syntology":null},{"url":"/paper/detection-of-furigana-text-in-images","slug":"detection-of-furigana-text-in-images","title":"Detection of Furigana Text in Images","date":"2022-07-08","arxiv_id":"2207.03960","repositories_listed":1,"syntology":null},{"url":"/paper/sequence-aware-multimodal-page-classification","slug":"sequence-aware-multimodal-page-classification","title":"Sequence-aware multimodal page classification of Brazilian legal documents","date":"2022-07-02","arxiv_id":"2207.00748","repositories_listed":1,"syntology":null},{"url":"/paper/iexam-a-novel-online-exam-monitoring-and","slug":"iexam-a-novel-online-exam-monitoring-and","title":"iExam: A Novel Online Exam Monitoring and Analysis System Based on Face Detection and Recognition","date":"2022-06-27","arxiv_id":"2206.13356","repositories_listed":1,"syntology":null},{"url":"/paper/an-evaluation-of-ocr-on-egocentric-data","slug":"an-evaluation-of-ocr-on-egocentric-data","title":"An Evaluation of OCR on Egocentric Data","date":"2022-06-11","arxiv_id":"2206.05496","repositories_listed":1,"syntology":null},{"url":"/paper/pp-ocrv3-more-attempts-for-the-improvement-of","slug":"pp-ocrv3-more-attempts-for-the-improvement-of","title":"PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System","date":"2022-06-07","arxiv_id":"2206.03001","repositories_listed":1,"syntology":null},{"url":"/paper/an-open-source-contractual-language","slug":"an-open-source-contractual-language","title":"An Open Source Contractual Language Understanding Application Using Machine Learning","date":"2022-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/delivering-document-conversion-as-a-cloud","slug":"delivering-document-conversion-as-a-cloud","title":"Delivering Document Conversion as a Cloud Service with High Throughput and Responsiveness","date":"2022-06-01","arxiv_id":"2206.00785","repositories_listed":1,"syntology":null},{"url":"/paper/hmbert-historical-multilingual-language","slug":"hmbert-historical-multilingual-language","title":"hmBERT: Historical Multilingual Language Models for Named Entity Recognition","date":"2022-05-31","arxiv_id":"2205.15575","repositories_listed":1,"syntology":null},{"url":"/paper/easter2-0-improving-convolutional-models-for","slug":"easter2-0-improving-convolutional-models-for","title":"Easter2.0: Improving convolutional models for handwritten text recognition","date":"2022-05-30","arxiv_id":"2205.14879","repositories_listed":1,"syntology":null},{"url":"/paper/git-a-generative-image-to-text-transformer","slug":"git-a-generative-image-to-text-transformer","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","date":"2022-05-27","arxiv_id":"2205.14100","repositories_listed":1,"syntology":{"n":21,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/git-a-generative-image-to-text-transformer#ran","syntology_url":"https://syntology.ai/paper/2205.14100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14100"}},"official":{"repos":["microsoft/GenerativeImage2Text"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/lila-boti-leveraging-isolated-letter","slug":"lila-boti-leveraging-isolated-letter","title":"LILA-BOTI : Leveraging Isolated Letter Accumulations By Ordering Teacher Insights for Bangla Handwriting Recognition","date":"2022-05-23","arxiv_id":"2205.11420","repositories_listed":1,"syntology":null},{"url":"/paper/banknote-net-open-dataset-for-assistive","slug":"banknote-net-open-dataset-for-assistive","title":"BankNote-Net: Open dataset for assistive universal currency recognition","date":"2022-04-07","arxiv_id":"2204.03738","repositories_listed":1,"syntology":null},{"url":"/paper/digitizing-historical-balance-sheet-data-a","slug":"digitizing-historical-balance-sheet-data-a","title":"Digitizing Historical Balance Sheet Data: A Practitioner's Guide","date":"2022-03-31","arxiv_id":"2204.00052","repositories_listed":1,"syntology":null},{"url":"/paper/document-dewarping-with-control-points","slug":"document-dewarping-with-control-points","title":"Document Dewarping with Control Points","date":"2022-03-20","arxiv_id":"2203.10543","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/document-dewarping-with-control-points#ran","syntology_url":"https://syntology.ai/paper/2203.10543","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.10543"}},"official":{"repos":["gwxie/document-dewarping-with-control-points"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/xylayoutlm-towards-layout-aware-multimodal","slug":"xylayoutlm-towards-layout-aware-multimodal","title":"XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding","date":"2022-03-14","arxiv_id":"2203.06947","repositories_listed":1,"syntology":null},{"url":"/paper/ocr-idl-ocr-annotations-for-industry-document","slug":"ocr-idl-ocr-annotations-for-industry-document","title":"OCR-IDL: OCR Annotations for Industry Document Library Dataset","date":"2022-02-25","arxiv_id":"2202.12985","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-cross-dataset-generalization-for","slug":"on-the-cross-dataset-generalization-for","title":"On the Cross-dataset Generalization in License Plate Recognition","date":"2022-01-02","arxiv_id":"2201.00267","repositories_listed":1,"syntology":null},{"url":"/paper/safl-a-self-attention-scene-text-recognizer-1","slug":"safl-a-self-attention-scene-text-recognizer-1","title":"SAFL: A Self-Attention Scene Text Recognizer with Focal Loss","date":"2022-01-01","arxiv_id":"2201.00132","repositories_listed":1,"syntology":null},{"url":"/paper/latr-layout-aware-transformer-for-scene-text","slug":"latr-layout-aware-transformer-for-scene-text","title":"LaTr: Layout-Aware Transformer for Scene-Text VQA","date":"2021-12-23","arxiv_id":"2112.12494","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/latr-layout-aware-transformer-for-scene-text#ran","syntology_url":"https://syntology.ai/paper/2112.12494","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.12494"}},"official":null}},{"url":"/paper/an-automatic-approach-for-generating-rich","slug":"an-automatic-approach-for-generating-rich","title":"An Automatic Approach for Generating Rich, Linked Geo-Metadata from Historical Map Images","date":"2021-12-03","arxiv_id":"2112.01671","repositories_listed":1,"syntology":null},{"url":"/paper/indian-licence-plate-dataset-in-the-wild","slug":"indian-licence-plate-dataset-in-the-wild","title":"Indian Licence Plate Dataset in the wild","date":"2021-11-11","arxiv_id":"2111.06054","repositories_listed":1,"syntology":null},{"url":"/paper/lexically-aware-semi-supervised-learning-for","slug":"lexically-aware-semi-supervised-learning-for","title":"Lexically Aware Semi-Supervised Learning for OCR Post-Correction","date":"2021-11-04","arxiv_id":"2111.02622","repositories_listed":1,"syntology":null},{"url":"/paper/cleaning-dirty-books-post-ocr-processing-for","slug":"cleaning-dirty-books-post-ocr-processing-for","title":"Cleaning Dirty Books: Post-OCR Processing for Previously Scanned Texts","date":"2021-10-22","arxiv_id":"2110.11934","repositories_listed":1,"syntology":null},{"url":"/paper/henet-forcing-a-network-to-think-more-for","slug":"henet-forcing-a-network-to-think-more-for","title":"HENet: Forcing a Network to Think More for Font Recognition","date":"2021-10-21","arxiv_id":"2110.10872","repositories_listed":1,"syntology":null},{"url":"/paper/optical-character-recognition-of-19th-century","slug":"optical-character-recognition-of-19th-century","title":"Optical Character Recognition of 19th Century Classical Commentaries: the Current State of Affairs","date":"2021-10-13","arxiv_id":"2110.06817","repositories_listed":1,"syntology":null},{"url":"/paper/robustness-evaluation-of-transformer-based","slug":"robustness-evaluation-of-transformer-based","title":"Robustness Evaluation of Transformer-based Form Field Extractors via Form Attacks","date":"2021-10-08","arxiv_id":"2110.04413","repositories_listed":1,"syntology":null},{"url":"/paper/rerunning-ocr-a-machine-learning-approach-to","slug":"rerunning-ocr-a-machine-learning-approach-to","title":"Rerunning OCR: A Machine Learning Approach to Quality Assessment and Enhancement Prediction","date":"2021-10-04","arxiv_id":"2110.01661","repositories_listed":1,"syntology":null},{"url":"/paper/post-ocr-document-correction-with-large","slug":"post-ocr-document-correction-with-large","title":"Post-OCR Document Correction with large Ensembles of Character Sequence-to-Sequence Models","date":"2021-09-13","arxiv_id":"2109.06264","repositories_listed":1,"syntology":null},{"url":"/paper/tamizhi-net-ocr-creating-a-quality-large","slug":"tamizhi-net-ocr-creating-a-quality-large","title":"Adapting the Tesseract Open-Source OCR Engine for Tamil and Sinhala Legacy Fonts and Creating a Parallel Corpus for Tamil-Sinhala-English","date":"2021-09-13","arxiv_id":"2109.05952","repositories_listed":1,"syntology":null},{"url":"/paper/layoutreader-pre-training-of-text-and-layout","slug":"layoutreader-pre-training-of-text-and-layout","title":"LayoutReader: Pre-training of Text and Layout for Reading Order Detection","date":"2021-08-26","arxiv_id":"2108.11591","repositories_listed":1,"syntology":null},{"url":"/paper/mmocr-a-comprehensive-toolbox-for-text","slug":"mmocr-a-comprehensive-toolbox-for-text","title":"MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding","date":"2021-08-14","arxiv_id":"2108.06543","repositories_listed":1,"syntology":null},{"url":"/paper/lights-camera-action-a-framework-to-improve","slug":"lights-camera-action-a-framework-to-improve","title":"Lights, Camera, Action! A Framework to Improve NLP Accuracy over OCR documents","date":"2021-08-06","arxiv_id":"2108.02899","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/lights-camera-action-a-framework-to-improve#ran","syntology_url":"https://syntology.ai/paper/2108.02899","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.02899"}},"official":{"repos":["microsoft/genalog"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/robust-learning-for-text-classification-with","slug":"robust-learning-for-text-classification-with","title":"Robust Learning for Text Classification with Multi-source Noise Simulation and Hard Example Mining","date":"2021-07-15","arxiv_id":"2107.07113","repositories_listed":1,"syntology":null},{"url":"/paper/data-centric-domain-adaptation-for-historical","slug":"data-centric-domain-adaptation-for-historical","title":"Data Centric Domain Adaptation for Historical Text with OCR Errors","date":"2021-07-02","arxiv_id":"2107.00927","repositories_listed":1,"syntology":null},{"url":"/paper/scene-text-telescope-text-focused-scene-image","slug":"scene-text-telescope-text-focused-scene-image","title":"Scene Text Telescope: Text-Focused Scene Image Super-Resolution","date":"2021-06-19","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/implicit-feature-alignment-learn-to-convert","slug":"implicit-feature-alignment-learn-to-convert","title":"Implicit Feature Alignment: Learn to Convert Text Recognizer to Text Spotter","date":"2021-06-10","arxiv_id":"2106.05920","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/implicit-feature-alignment-learn-to-convert#ran","syntology_url":"https://syntology.ai/paper/2106.05920","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05920"}},"official":{"repos":["Wang-Tianwei/Implicit-feature-alignment"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/end-to-end-information-extraction-by","slug":"end-to-end-information-extraction-by","title":"End-to-End Information Extraction by Character-Level Embedding and Multi-Stage Attentional U-Net","date":"2021-06-02","arxiv_id":"2106.00952","repositories_listed":1,"syntology":null},{"url":"/paper/empirical-error-modeling-improves-robustness","slug":"empirical-error-modeling-improves-robustness","title":"Empirical Error Modeling Improves Robustness of Noisy Neural Sequence Labeling","date":"2021-05-25","arxiv_id":"2105.11872","repositories_listed":1,"syntology":null},{"url":"/paper/multi-type-td-tsr-extracting-tables-from","slug":"multi-type-td-tsr-extracting-tables-from","title":"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 Representations","date":"2021-05-23","arxiv_id":"2105.11021","repositories_listed":1,"syntology":null},{"url":"/paper/unknown-box-approximation-to-improve-optical","slug":"unknown-box-approximation-to-improve-optical","title":"Unknown-box Approximation to Improve Optical Character Recognition Performance","date":"2021-05-17","arxiv_id":"2105.07983","repositories_listed":1,"syntology":null},{"url":"/paper/reciprocal-feature-learning-via-explicit-and","slug":"reciprocal-feature-learning-via-explicit-and","title":"Reciprocal Feature Learning via Explicit and Implicit Tasks in Scene Text Recognition","date":"2021-05-13","arxiv_id":"2105.06229","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-optical-character-recognition-for","slug":"end-to-end-optical-character-recognition-for","title":"End-to-End Optical Character Recognition for Bengali Handwritten Words","date":"2021-05-09","arxiv_id":"2105.04020","repositories_listed":1,"syntology":null},{"url":"/paper/word-level-alignment-of-paper-documents-with","slug":"word-level-alignment-of-paper-documents-with","title":"Word-Level Alignment of Paper Documents with their Electronic Full-Text Counterparts","date":"2021-04-30","arxiv_id":"2104.14925","repositories_listed":1,"syntology":null},{"url":"/paper/at-st-self-training-adaptation-strategy-for","slug":"at-st-self-training-adaptation-strategy-for","title":"AT-ST: Self-Training Adaptation Strategy for OCR in Domains with Limited Transcriptions","date":"2021-04-27","arxiv_id":"2104.13037","repositories_listed":1,"syntology":null},{"url":"/paper/green-view-index-analysis-and-optimal-green","slug":"green-view-index-analysis-and-optimal-green","title":"Analyzing Green View Index and Green View Index best path using Google Street View and deep learning","date":"2021-04-26","arxiv_id":"2104.12627","repositories_listed":1,"syntology":null},{"url":"/paper/samanantar-the-largest-publicly-available","slug":"samanantar-the-largest-publicly-available","title":"Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages","date":"2021-04-12","arxiv_id":"2104.05596","repositories_listed":1,"syntology":null},{"url":"/paper/video-aided-unsupervised-grammar-induction","slug":"video-aided-unsupervised-grammar-induction","title":"Video-aided Unsupervised Grammar Induction","date":"2021-04-09","arxiv_id":"2104.04369","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/video-aided-unsupervised-grammar-induction#ran","syntology_url":"https://syntology.ai/paper/2104.04369","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.04369"}},"official":{"repos":["Sy-Zhang/MMC-PCFG"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/a-multiplexed-network-for-end-to-end","slug":"a-multiplexed-network-for-end-to-end","title":"A Multiplexed Network for End-to-End, Multilingual OCR","date":"2021-03-29","arxiv_id":"2103.15992","repositories_listed":1,"syntology":null},{"url":"/paper/icdar2019-competition-on-scanned-receipt-ocr","slug":"icdar2019-competition-on-scanned-receipt-ocr","title":"ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction","date":"2021-03-18","arxiv_id":"2103.10213","repositories_listed":1,"syntology":null},{"url":"/paper/combining-morphological-and-histogram-based","slug":"combining-morphological-and-histogram-based","title":"Combining Morphological and Histogram based Text Line Segmentation in the OCR Context","date":"2021-03-16","arxiv_id":"2103.08922","repositories_listed":1,"syntology":null},{"url":"/paper/generating-synthetic-handwritten-historical","slug":"generating-synthetic-handwritten-historical","title":"Generating Synthetic Handwritten Historical Documents With OCR Constrained GANs","date":"2021-03-15","arxiv_id":"2103.08236","repositories_listed":1,"syntology":null},{"url":"/paper/select-substitute-search-a-new-benchmark-for","slug":"select-substitute-search-a-new-benchmark-for","title":"Select, Substitute, Search: A New Benchmark for Knowledge-Augmented Visual Question Answering","date":"2021-03-09","arxiv_id":"2103.05568","repositories_listed":1,"syntology":null},{"url":"/paper/span-a-simple-predict-align-network-for","slug":"span-a-simple-predict-align-network-for","title":"SPAN: a Simple Predict & Align Network for Handwritten Paragraph Recognition","date":"2021-02-17","arxiv_id":"2102.08742","repositories_listed":1,"syntology":null},{"url":"/paper/neural-ocr-post-hoc-correction-of-historical","slug":"neural-ocr-post-hoc-correction-of-historical","title":"Neural OCR Post-Hoc Correction of Historical Corpora","date":"2021-02-01","arxiv_id":"2102.00583","repositories_listed":1,"syntology":null},{"url":"/paper/it-takes-two-to-tango-combining-visual-and","slug":"it-takes-two-to-tango-combining-visual-and","title":"It Takes Two to Tango: Combining Visual and Textual Information for Detecting Duplicate Video-Based Bug Reports","date":"2021-01-22","arxiv_id":"2101.09194","repositories_listed":1,"syntology":null},{"url":"/paper/an-unsupervised-normalization-algorithm-for","slug":"an-unsupervised-normalization-algorithm-for","title":"An Unsupervised Normalization Algorithm for Noisy Text: A Case Study for Information Retrieval and Stance Detection","date":"2021-01-09","arxiv_id":"2101.03303","repositories_listed":1,"syntology":null},{"url":"/paper/iranis-a-large-scale-dataset-of-farsi-license","slug":"iranis-a-large-scale-dataset-of-farsi-license","title":"Iranis: A Large-scale Dataset of Farsi License Plate Characters","date":"2021-01-01","arxiv_id":"2101.00295","repositories_listed":1,"syntology":null},{"url":"/paper/fawa-fast-adversarial-watermark-attack-on","slug":"fawa-fast-adversarial-watermark-attack-on","title":"FAWA: Fast Adversarial Watermark Attack on Optical Character Recognition (OCR) Systems","date":"2020-12-15","arxiv_id":"2012.08096","repositories_listed":1,"syntology":null},{"url":"/paper/simple-is-not-easy-a-simple-strong-baseline","slug":"simple-is-not-easy-a-simple-strong-baseline","title":"Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps","date":"2020-12-09","arxiv_id":"2012.05153","repositories_listed":1,"syntology":null},{"url":"/paper/tap-text-aware-pre-training-for-text-vqa-and","slug":"tap-text-aware-pre-training-for-text-vqa-and","title":"TAP: Text-Aware Pre-training for Text-VQA and Text-Caption","date":"2020-12-08","arxiv_id":"2012.04638","repositories_listed":1,"syntology":null},{"url":"/paper/confidence-aware-non-repetitive-multimodal","slug":"confidence-aware-non-repetitive-multimodal","title":"Confidence-aware Non-repetitive Multimodal Transformers for TextCaps","date":"2020-12-07","arxiv_id":"2012.03662","repositories_listed":1,"syntology":null},{"url":"/paper/a-two-step-approach-for-automatic-ocr-post","slug":"a-two-step-approach-for-automatic-ocr-post","title":"A Two-Step Approach for Automatic OCR Post-Correction","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/building-a-part-of-speech-tagged-corpus-for","slug":"building-a-part-of-speech-tagged-corpus-for","title":"Building a Part-of-Speech Tagged Corpus for Drenjongke (Bhutia)","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/intrinsic-decomposition-of-document-images-in","slug":"intrinsic-decomposition-of-document-images-in","title":"Intrinsic Decomposition of Document Images In-the-Wild","date":"2020-11-29","arxiv_id":"2011.14447","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-of-deep-learning-approaches-for-ocr","slug":"a-survey-of-deep-learning-approaches-for-ocr","title":"A Survey of Deep Learning Approaches for OCR and Document Understanding","date":"2020-11-27","arxiv_id":"2011.13534","repositories_listed":1,"syntology":null},{"url":"/paper/an-unsupervised-method-for-ocr-post","slug":"an-unsupervised-method-for-ocr-post","title":"An Unsupervised method for OCR Post-Correction and Spelling Normalisation for Finnish","date":"2020-11-06","arxiv_id":"2011.03502","repositories_listed":1,"syntology":null},{"url":"/paper/handwriting-classification-for-the-analysis","slug":"handwriting-classification-for-the-analysis","title":"Handwriting Classification for the Analysis of Art-Historical Documents","date":"2020-11-04","arxiv_id":"2011.02264","repositories_listed":1,"syntology":null},{"url":"/paper/alleviating-digitization-errors-in-named","slug":"alleviating-digitization-errors-in-named","title":"Alleviating Digitization Errors in Named Entity Recognition for Historical Documents","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/ruart-a-novel-text-centered-solution-for-text","slug":"ruart-a-novel-text-centered-solution-for-text","title":"RUArt: A Novel Text-Centered Solution for Text-Based Visual Question Answering","date":"2020-10-24","arxiv_id":"2010.12917","repositories_listed":1,"syntology":null},{"url":"/paper/tlgan-document-text-localization-using","slug":"tlgan-document-text-localization-using","title":"TLGAN: document Text Localization using Generative Adversarial Nets","date":"2020-10-22","arxiv_id":"2010.11547","repositories_listed":1,"syntology":null},{"url":"/paper/table-structure-recognition-using-top-down-1","slug":"table-structure-recognition-using-top-down-1","title":"Table Structure Recognition using Top-Down and Bottom-Up Cues","date":"2020-10-09","arxiv_id":"2010.04565","repositories_listed":1,"syntology":null},{"url":"/paper/mrz-code-extraction-from-visa-and-passport","slug":"mrz-code-extraction-from-visa-and-passport","title":"MRZ code extraction from visa and passport documents using convolutional neural networks","date":"2020-09-11","arxiv_id":"2009.05489","repositories_listed":1,"syntology":null},{"url":"/paper/adapting-ocr-with-limited-supervision","slug":"adapting-ocr-with-limited-supervision","title":"Adapting OCR with limited supervision","date":"2020-07-27","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/spatially-aware-multimodal-transformers-for","slug":"spatially-aware-multimodal-transformers-for","title":"Spatially Aware Multimodal Transformers for TextVQA","date":"2020-07-23","arxiv_id":"2007.12146","repositories_listed":1,"syntology":null},{"url":"/paper/fused-text-recogniser-and-deep-embeddings","slug":"fused-text-recogniser-and-deep-embeddings","title":"Fused Text Recogniser and Deep Embeddings Improve Word Recognition and Retrieval","date":"2020-07-01","arxiv_id":"2007.00166","repositories_listed":1,"syntology":null},{"url":"/paper/improving-accuracy-and-speeding-up-document","slug":"improving-accuracy-and-speeding-up-document","title":"Improving accuracy and speeding up Document Image Classification through parallel systems","date":"2020-06-16","arxiv_id":"2006.09141","repositories_listed":1,"syntology":null},{"url":"/paper/cleval-character-level-evaluation-for-text","slug":"cleval-character-level-evaluation-for-text","title":"CLEval: Character-Level Evaluation for Text Detection and Recognition Tasks","date":"2020-06-11","arxiv_id":"2006.06244","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cleval-character-level-evaluation-for-text#ran","syntology_url":"https://syntology.ai/paper/2006.06244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.06244"}},"official":{"repos":["clovaai/CLEval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"4c551676331b9ab22613c57c338f54fb61e8402420bbd6ef85e59a1f094490a7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}