{"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/9","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":9,"pages_in_order":13,"rows_per_page":100,"rows":[801,900],"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/8","next":"/task/optical-character-recognition/papers/10","papers":[{"url":null,"slug":"businet-a-light-and-fast-text-detection","title":"BusiNet -- a Light and Fast Text Detection Network for Business Documents","date":"2022-07-04","arxiv_id":"2207.01220","repositories_listed":0,"syntology":null},{"url":null,"slug":"challenging-america-modeling-language-in-1","title":"Challenging America: Modeling language in longer time scales","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multistep-automated-data-labelling-procedure","title":"Multistep Automated Data Labelling Procedure (MADLaP) for Thyroid Nodules on Ultrasound: An Artificial Intelligence Approach for Automating Image Annotation","date":"2022-06-28","arxiv_id":"2206.14305","repositories_listed":0,"syntology":null},{"url":null,"slug":"broken-news-making-newspapers-accessible-to","title":"Broken News: Making Newspapers Accessible to Print-Impaired","date":"2022-06-21","arxiv_id":"2206.10225","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-optimizing-ocr-for-accessibility","title":"Towards Optimizing OCR for Accessibility","date":"2022-06-21","arxiv_id":"2206.10254","repositories_listed":0,"syntology":null},{"url":null,"slug":"rdu-a-region-based-approach-to-form-style","title":"RDU: A Region-based Approach to Form-style Document Understanding","date":"2022-06-14","arxiv_id":"2206.06890","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-based-urdu-handwritten-text","title":"Transformer based Urdu Handwritten Text Optical Character Reader","date":"2022-06-09","arxiv_id":"2206.04575","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-graph-multimodal-model-for-text","title":"Contrastive Graph Multimodal Model for Text Classification in Videos","date":"2022-06-06","arxiv_id":"2206.02343","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-decades-of-bengali-handwritten-digit","title":"Two Decades of Bengali Handwritten Digit Recognition: A Survey","date":"2022-06-05","arxiv_id":"2206.02234","repositories_listed":0,"syntology":null},{"url":null,"slug":"introducing-one-sided-margin-loss-for-solving","title":"Introducing One Sided Margin Loss for Solving Classification Problems in Deep Networks","date":"2022-06-02","arxiv_id":"2206.01002","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-language-modelling-approach-to-quality","title":"A Language Modelling Approach to Quality Assessment of OCR’ed Historical Text","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"between-history-and-natural-language","title":"Between History and Natural Language Processing: Study, Enrichment and Online Publication of French Parliamentary Debates of the Early Third Republic (1881-1899)","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"camio-a-corpus-for-ocr-in-multiple-languages","title":"CAMIO: A Corpus for OCR in Multiple Languages","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-monolingual-dataset-for-low","title":"Generating Monolingual Dataset for Low Resource Language Bodo from old books using Google Keep","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"handwritten-character-generation-using-y","title":"Handwritten Character Generation using Y-Autoencoder for Character Recognition Model Training","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/maskocr-text-recognition-with-masked-encoder","slug":"maskocr-text-recognition-with-masked-encoder","title":"MaskOCR: Text Recognition with Masked Encoder-Decoder Pretraining","date":"2022-06-01","arxiv_id":"2206.00311","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-named-entity-recognition-for","title":"Multilingual Named Entity Recognition for Medieval Charters Using Stacked Embeddings and Bert-based Models.","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"optical-character-recognition-quality-affects","title":"Optical character recognition quality affects perceived usefulness of historical newspaper clippings","date":"2022-06-01","arxiv_id":"2206.00369","repositories_listed":0,"syntology":null},{"url":null,"slug":"reconnaissance-dentites-nommees-sur-des","title":"Reconnaissance d’entités nommées sur des sorties OCR bruitées : des pistes pour la désambiguïsation morphologique automatique (Resolution of entity linking issues on noisy OCR output : automatic disambiguation tracks)","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"simulation-derreurs-docr-dans-les-systemes-de","title":"Simulation d’erreurs d’OCR dans les systèmes de TAL pour le traitement de données anachroniques (Simulation of OCR errors in NLP systems for processing anachronistic data)","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"toolbox-une-chaine-de-traitement-de-corpus","title":"Toolbox : une chaîne de traitement de corpus pour les humanités numériques (Toolbox : a corpus processing pipeline for digital humanities)","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"disinfomeme-a-multimodal-dataset-for","title":"DisinfoMeme: A Multimodal Dataset for Detecting Meme Intentionally Spreading Out Disinformation","date":"2022-05-25","arxiv_id":"2205.12617","repositories_listed":0,"syntology":null},{"url":null,"slug":"detection-masking-for-improved-ocr-on-noisy","title":"Detection Masking for Improved OCR on Noisy Documents","date":"2022-05-17","arxiv_id":"2205.08257","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-empirical-study-of-ctc-based-models-for","title":"Towards Deployable OCR models for Indic languages","date":"2022-05-13","arxiv_id":"2205.06740","repositories_listed":0,"syntology":null},{"url":null,"slug":"ocr-synthetic-benchmark-dataset-for-indic","title":"OCR Synthetic Benchmark Dataset for Indic Languages","date":"2022-05-05","arxiv_id":"2205.02543","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-detection-on-technical-drawings-for-the","title":"Text Detection on Technical Drawings for the Digitization of Brown-field Processes","date":"2022-05-05","arxiv_id":"2205.02659","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-publication-year-prediction-of","title":"Explainable Publication Year Prediction of Eighteenth Century Texts with the BERT Model","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hybrid-defense-method-against-adversarial","title":"A Hybrid Defense Method against Adversarial Attacks on Traffic Sign Classifiers in Autonomous Vehicles","date":"2022-04-25","arxiv_id":"2205.01225","repositories_listed":0,"syntology":null},{"url":"/paper/unitail-detecting-reading-and-matching-in","slug":"unitail-detecting-reading-and-matching-in","title":"Unitail: Detecting, Reading, and Matching in Retail Scene","date":"2022-04-01","arxiv_id":"2204.00298","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-algorithms-for-automatic-license","title":"Benchmarking Algorithms for Automatic License Plate Recognition","date":"2022-03-27","arxiv_id":"2203.14298","repositories_listed":0,"syntology":null},{"url":null,"slug":"plagiarism-detection-in-the-bengali-language","title":"Plagiarism Detection in the Bengali Language: A Text Similarity-Based Approach","date":"2022-03-25","arxiv_id":"2203.13430","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-escaping-from-language-bias-and-ocr","title":"Towards Escaping from Language Bias and OCR Error: Semantics-Centered Text Visual Question Answering","date":"2022-03-24","arxiv_id":"2203.12929","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-matters-a-weakly-supervised-pre","title":"Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and Spotting","date":"2022-03-08","arxiv_id":"2203.03911","repositories_listed":0,"syntology":null},{"url":null,"slug":"ocr-quality-affects-perceived-usefulness-of","title":"OCR quality affects perceived usefulness of historical newspaper clippings -- a user study","date":"2022-03-04","arxiv_id":"2203.03557","repositories_listed":0,"syntology":null},{"url":null,"slug":"ocr-improves-machine-translation-for-low","title":"OCR Improves Machine Translation for Low-Resource Languages","date":"2022-02-27","arxiv_id":"2202.13274","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-amharic-handwritten-word","title":"Improving Amharic Handwritten Word Recognition Using Auxiliary Task","date":"2022-02-25","arxiv_id":"2202.12687","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-structured-query-grounding-for-document","title":"Semi-Structured Query Grounding for Document-Oriented Databases with Deep Retrieval and Its Application to Receipt and POI Matching","date":"2022-02-23","arxiv_id":"2202.13959","repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-ocrs-in-cfdna-wgs-data-by","title":"Identifying OCRs in cfDNA WGS Data by Correlation Clustering","date":"2022-02-19","arxiv_id":"2202.09618","repositories_listed":0,"syntology":null},{"url":null,"slug":"blpnet-a-new-dnn-model-and-bengali-ocr-engine","title":"BLPnet: A new DNN model and Bengali OCR engine for Automatic License Plate Recognition","date":"2022-02-18","arxiv_id":"2202.12250","repositories_listed":0,"syntology":null},{"url":null,"slug":"omnifont-persian-ocr-system-using-primitives","title":"Omnifont Persian OCR System Using Primitives","date":"2022-02-13","arxiv_id":"2202.06371","repositories_listed":0,"syntology":null},{"url":null,"slug":"docbed-a-multi-stage-ocr-solution-for","title":"DocBed: A Multi-Stage OCR Solution for Documents with Complex Layouts","date":"2022-02-03","arxiv_id":"2202.01414","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-paced-learning-to-improve-text-row","title":"Self-paced learning to improve text row detection in historical documents with missing labels","date":"2022-01-28","arxiv_id":"2201.12216","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-assessment-of-the-impact-of-ocr-noise-on","title":"An Assessment of the Impact of OCR Noise on Language Models","date":"2022-01-26","arxiv_id":"2202.00470","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-classical-approach-to-handcrafted-feature","title":"A Classical Approach to Handcrafted Feature Extraction Techniques for Bangla Handwritten Digit Recognition","date":"2022-01-25","arxiv_id":"2201.10102","repositories_listed":0,"syntology":null},{"url":null,"slug":"classroom-slide-narration-system","title":"Classroom Slide Narration System","date":"2022-01-21","arxiv_id":"2201.08574","repositories_listed":0,"syntology":null},{"url":null,"slug":"legal-entity-extraction-using-a-pointer","title":"Legal Entity Extraction using a Pointer Generator Network","date":"2022-01-20","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improve-sentence-alignment-by-divide-and","title":"Improve Sentence Alignment by Divide-and-conquer","date":"2022-01-18","arxiv_id":"2201.06907","repositories_listed":0,"syntology":null},{"url":null,"slug":"intelligent-document-processing-methods-and","title":"Intelligent Document Processing -- Methods and Tools in the real world","date":"2021-12-28","arxiv_id":"2112.14070","repositories_listed":0,"syntology":null},{"url":null,"slug":"challenging-america-modeling-language-in","title":"Challenging America: Modeling language in longer time scales","date":"2021-12-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lesan-machine-translation-for-low-resource","title":"Lesan -- Machine Translation for Low Resource Languages","date":"2021-12-15","arxiv_id":"2112.08191","repositories_listed":0,"syntology":null},{"url":null,"slug":"tracing-text-provenance-via-context-aware","title":"Tracing Text Provenance via Context-Aware Lexical Substitution","date":"2021-12-15","arxiv_id":"2112.07873","repositories_listed":0,"syntology":null},{"url":null,"slug":"blpnet-a-new-dnn-model-for-automatic-license","title":"Modelling Lips-State Detection Using CNN for Non-Verbal Communications","date":"2021-12-09","arxiv_id":"2112.04752","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-deep-learning-based-document","title":"A Survey on Deep learning based Document Image Enhancement","date":"2021-12-06","arxiv_id":"2112.02719","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-device-spatial-attention-based-sequence","title":"On-Device Spatial Attention based Sequence Learning Approach for Scene Text Script Identification","date":"2021-12-01","arxiv_id":"2112.00448","repositories_listed":0,"syntology":null},{"url":null,"slug":"transferring-modern-named-entity-recognition","title":"Transferring Modern Named Entity Recognition to the Historical Domain: How to Take the Step?","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"image-preprocessing-and-modified-adaptive","title":"Image preprocessing and modified adaptive thresholding for improving OCR","date":"2021-11-28","arxiv_id":"2111.14075","repositories_listed":0,"syntology":null},{"url":null,"slug":"ice-hockey-player-identification-via","title":"Ice hockey player identification via transformers and weakly supervised learning","date":"2021-11-22","arxiv_id":"2111.11535","repositories_listed":0,"syntology":null},{"url":null,"slug":"discriminative-dictionary-learning-based-on","title":"Discriminative Dictionary Learning based on Statistical Methods","date":"2021-11-17","arxiv_id":"2111.09027","repositories_listed":0,"syntology":null},{"url":null,"slug":"handwritten-digit-recognition-using-improved","title":"Handwritten Digit Recognition Using Improved Bounding Box Recognition Technique","date":"2021-11-10","arxiv_id":"2111.05483","repositories_listed":0,"syntology":null},{"url":null,"slug":"bart-for-post-correction-of-ocr-newspaper","title":"BART for Post-Correction of OCR Newspaper Text","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"named-entity-recognition-in-historic-legal","title":"Named Entity Recognition in Historic Legal Text: A Transformer and State Machine Ensemble Method","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"spellbert-a-lightweight-pretrained-model-for","title":"SpellBERT: A Lightweight Pretrained Model for Chinese Spelling Check","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-multi-view-post-ocr-error","title":"Unsupervised Multi-View Post-OCR Error Correction With Language Models","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ultra-light-ocr-competition-technical-report","title":"Ultra Light OCR Competition Technical Report","date":"2021-10-25","arxiv_id":"2110.12623","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-ui-navigation-through-demonstrations","title":"Learning UI Navigation through Demonstrations composed of Macro Actions","date":"2021-10-16","arxiv_id":"2110.08653","repositories_listed":0,"syntology":null},{"url":null,"slug":"asking-questions-on-handwritten-document","title":"Asking questions on handwritten document collections","date":"2021-10-02","arxiv_id":"2110.00711","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-proposal-of-automatic-error-correction-in","title":"A Proposal of Automatic Error Correction in Text","date":"2021-09-24","arxiv_id":"2112.01846","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-based-nlp-data-pipeline-for-ehr","title":"Deep learning-based NLP Data Pipeline for EHR Scanned Document Information Extraction","date":"2021-09-14","arxiv_id":"2110.11864","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-machine-learning-based-approach-for","title":"A Novel Machine Learning Based Approach for Post-OCR Error Detection","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ocr-processing-of-swedish-historical","title":"OCR Processing of Swedish Historical Newspapers Using Deep Hybrid CNN–LSTM Networks","date":"2021-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multimodal-framework-for-video-ads","title":"A Multimodal Framework for Video Ads Understanding","date":"2021-08-29","arxiv_id":"2108.12868","repositories_listed":0,"syntology":null},{"url":null,"slug":"external-knowledge-augmented-text-visual","title":"EKTVQA: Generalized use of External Knowledge to empower Scene Text in Text-VQA","date":"2021-08-22","arxiv_id":"2108.09717","repositories_listed":0,"syntology":null},{"url":null,"slug":"localize-group-and-select-boosting-text-vqa","title":"Localize, Group, and Select: Boosting Text-VQA by Scene Text Modeling","date":"2021-08-20","arxiv_id":"2108.08965","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-license-plate-recognition-pipeline","title":"Real-time Bangla License Plate Recognition System for Low Resource Video-based Applications","date":"2021-08-18","arxiv_id":"2108.08339","repositories_listed":0,"syntology":null},{"url":null,"slug":"visbuddy-a-smart-wearable-assistant-for-the","title":"VisBuddy -- A Smart Wearable Assistant for the Visually Challenged","date":"2021-08-17","arxiv_id":"2108.07761","repositories_listed":0,"syntology":null},{"url":null,"slug":"mind-at-semeval-2021-task-6-propaganda","title":"MinD at SemEval-2021 Task 6: Propaganda Detection using Transfer Learning and Multimodal Fusion","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-corpora-they-are-a-changing-a-case-study","title":"The Corpora They Are a-Changing: a Case Study in Italian Newspapers","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-text-recognition-with-full","title":"Scene Text recognition with Full Normalization","date":"2021-07-13","arxiv_id":"2109.01034","repositories_listed":0,"syntology":null},{"url":null,"slug":"memes-in-the-wild-assessing-the","title":"Memes in the Wild: Assessing the Generalizability of the Hateful Memes Challenge Dataset","date":"2021-07-09","arxiv_id":"2107.04313","repositories_listed":0,"syntology":null},{"url":null,"slug":"donet-learning-category-level-6d-object-pose","title":"SAR-Net: Shape Alignment and Recovery Network for Category-level 6D Object Pose and Size Estimation","date":"2021-06-27","arxiv_id":"2106.14193","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-simple-and-practical-approach-to-improve","title":"A Simple and Practical Approach to Improve Misspellings in OCR Text","date":"2021-06-22","arxiv_id":"2106.12030","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-end-to-end-khmer-optical-character","title":"An End-to-End Khmer Optical Character Recognition using Sequence-to-Sequence with Attention","date":"2021-06-21","arxiv_id":"2106.10875","repositories_listed":0,"syntology":null},{"url":null,"slug":"tag-copy-or-predict-a-unified-weakly","title":"Tag, Copy or Predict: A Unified Weakly-Supervised Learning Framework for Visual Information Extraction using Sequences","date":"2021-06-20","arxiv_id":"2106.10681","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-ocr-based-image-captioning-by","title":"Improving OCR-Based Image Captioning by Incorporating Geometrical Relationship","date":"2021-06-19","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"classification-of-documents-extracted-from","title":"Classification of Documents Extracted from Images with Optical Character Recognition Methods","date":"2021-06-15","arxiv_id":"2106.11125","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixed-model-ocr-training-on-historical-latin","title":"Mixed Model OCR Training on Historical Latin Script for Out-of-the-Box Recognition and Finetuning","date":"2021-06-15","arxiv_id":"2106.07881","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-free-textspotter-for-real-time-and","title":"Context-Free TextSpotter for Real-Time and Mobile End-to-End Text Detection and Recognition","date":"2021-06-10","arxiv_id":"2106.05611","repositories_listed":0,"syntology":null},{"url":null,"slug":"classification-of-contract-amendment","title":"Classification of Contract-Amendment Relationships","date":"2021-06-08","arxiv_id":"2106.14619","repositories_listed":0,"syntology":null},{"url":null,"slug":"pam-understanding-product-images-in-cross","title":"PAM: Understanding Product Images in Cross Product Category Attribute Extraction","date":"2021-06-08","arxiv_id":"2106.04630","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-creation-of-ancash-lexical-resources","title":"Toward Creation of Ancash Lexical Resources from OCR","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bangla-natural-language-processing-a","title":"Bangla Natural Language Processing: A Comprehensive Analysis of Classical, Machine Learning, and Deep Learning Based Methods","date":"2021-05-31","arxiv_id":"2105.14875","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-full-stack-accelerator-search-technique-for","title":"A Full-Stack Search Technique for Domain Optimized Deep Learning Accelerators","date":"2021-05-26","arxiv_id":"2105.12842","repositories_listed":0,"syntology":null},{"url":null,"slug":"simple-transparent-adversarial-examples","title":"Simple Transparent Adversarial Examples","date":"2021-05-20","arxiv_id":"2105.09685","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-unsupervised-document-image-blind","title":"End-to-End Unsupervised Document Image Blind Denoising","date":"2021-05-19","arxiv_id":"2105.09437","repositories_listed":0,"syntology":null},{"url":null,"slug":"stride-scene-text-recognition-in-device","title":"STRIDE : Scene Text Recognition In-Device","date":"2021-05-17","arxiv_id":"2105.07795","repositories_listed":0,"syntology":null},{"url":null,"slug":"mining-legacy-issues-in-open-pit-mining-sites","title":"Supporting Land Reuse of Former Open Pit Mining Sites using Text Classification and Active Learning","date":"2021-05-12","arxiv_id":"2105.05557","repositories_listed":0,"syntology":null},{"url":"/paper/textocr-towards-large-scale-end-to-end","slug":"textocr-towards-large-scale-end-to-end","title":"TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text","date":"2021-05-12","arxiv_id":"2105.05486","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-end-to-end-optical-character-recognition","title":"An end-to-end Optical Character Recognition approach for ultra-low-resolution printed text images","date":"2021-05-10","arxiv_id":"2105.04515","repositories_listed":0,"syntology":null},{"url":null,"slug":"grouplink-an-end-to-end-multitask-method-for","title":"GroupLink: An End-to-end Multitask Method for Word Grouping and Relation Extraction in Form Understanding","date":"2021-05-10","arxiv_id":"2105.04650","repositories_listed":0,"syntology":null},{"url":null,"slug":"tablext-a-combined-neural-network-and","title":"Tablext: A Combined Neural Network And Heuristic Based Table Extractor","date":"2021-04-22","arxiv_id":"2104.11287","repositories_listed":0,"syntology":null}],"record_sha256":"fde31f44c8def155adf2eb5c1eabf01eb978526e3beb3d9fa08d8901e74ef20d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}