{"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/scene-text-recognition/papers/3","list_of":"/task/scene-text-recognition","task":"Scene Text Recognition","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":3,"pages_in_order":3,"rows_per_page":100,"rows":[201,269],"of":269,"counts":{"archive_papers_tagged":269,"with_a_code_link":146,"where_syntology_ran_a_sample":27,"not_listed_spam_title":0,"listed":269,"listed_where_code_ran":27,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":26,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":26,"listed_every_run_a_failure_of_syntologys_instrument":1,"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/scene-text-recognition","prev":"/task/scene-text-recognition/papers/2","next":null,"papers":[{"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":"i2c2w-image-to-character-to-word-transformers","title":"I2C2W: Image-to-Character-to-Word Transformers for Accurate Scene Text Recognition","date":"2021-05-18","arxiv_id":"2105.08383","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":"pingan-vcgroup-s-solution-for-icdar-2021-1","title":"PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Table Image Recognition to Latex","date":"2021-05-05","arxiv_id":"2105.01846","repositories_listed":0,"syntology":null},{"url":null,"slug":"parallel-scale-wise-attention-network-for","title":"Parallel Scale-wise Attention Network for Effective Scene Text Recognition","date":"2021-04-25","arxiv_id":"2104.12076","repositories_listed":0,"syntology":null},{"url":"/paper/benchmarking-scene-text-recognition-in","slug":"benchmarking-scene-text-recognition-in","title":"Benchmarking Scene Text Recognition in Devanagari, Telugu and Malayalam","date":"2021-04-09","arxiv_id":"2104.04437","repositories_listed":0,"syntology":null},{"url":null,"slug":"feds-filtered-edit-distance-surrogate","title":"FEDS -- Filtered Edit Distance Surrogate","date":"2021-03-08","arxiv_id":"2103.04635","repositories_listed":0,"syntology":null},{"url":null,"slug":"frugalmct-efficient-online-ml-api-selection","title":"Efficient Online ML API Selection for Multi-Label Classification Tasks","date":"2021-02-18","arxiv_id":"2102.09127","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-calibration-of-scene-text-recognition","title":"On Calibration of Scene-Text Recognition Models","date":"2020-12-23","arxiv_id":"2012.12643","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-high-level-vision-with-joint","title":"Boosting High-Level Vision with Joint Compression Artifacts Reduction and Super-Resolution","date":"2020-10-18","arxiv_id":"2010.08919","repositories_listed":0,"syntology":null},{"url":null,"slug":"hamming-ocr-a-locality-sensitive-hashing","title":"Hamming OCR: A Locality Sensitive Hashing Neural Network for Scene Text Recognition","date":"2020-09-23","arxiv_id":"2009.10874","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-font-independent-features-for-scene","title":"Exploring Font-independent Features for Scene Text Recognition","date":"2020-09-16","arxiv_id":"2009.07447","repositories_listed":0,"syntology":null},{"url":null,"slug":"variational-connectionist-temporal","title":"Variational Connectionist Temporal Classification","date":"2020-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fedocr-communication-efficient-federated","title":"FedOCR: Communication-Efficient Federated Learning for Scene Text Recognition","date":"2020-07-22","arxiv_id":"2007.11462","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-surrogates-via-deep-embedding","title":"Learning Surrogates via Deep Embedding","date":"2020-07-01","arxiv_id":"2007.00799","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-human-psychophysics-to-evaluate","title":"Using Human Psychophysics to Evaluate Generalization in Scene Text Recognition Models","date":"2020-06-30","arxiv_id":"2007.00083","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-recognition-in-real-scenarios-with-a-few","title":"Text Recognition in Real Scenarios with a Few Labeled Samples","date":"2020-06-22","arxiv_id":"2006.12209","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-machines-see-is-not-what-they-get","title":"What Machines See Is Not What They Get: Fooling Scene Text Recognition Models With Adversarial Text Images","date":"2020-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-vocabulary-reliance-in-scene-text","title":"On Vocabulary Reliance in Scene Text Recognition","date":"2020-05-08","arxiv_id":"2005.03959","repositories_listed":0,"syntology":null},{"url":null,"slug":"reads-a-rectified-attentional-double","title":"ReADS: A Rectified Attentional Double Supervised Network for Scene Text Recognition","date":"2020-04-05","arxiv_id":"2004.02070","repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-text-recognition-via-transformer","title":"Scene Text Recognition via Transformer","date":"2020-03-18","arxiv_id":"2003.08077","repositories_listed":0,"syntology":null},{"url":null,"slug":"refined-gate-a-simple-and-effective-gating","title":"Refined Gate: A Simple and Effective Gating Mechanism for Recurrent Units","date":"2020-02-26","arxiv_id":"2002.11338","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-new-perspective-for-flexible-feature","title":"A New Perspective for Flexible Feature Gathering in Scene Text Recognition Via Character Anchor Pooling","date":"2020-02-10","arxiv_id":"2002.03509","repositories_listed":0,"syntology":null},{"url":null,"slug":"gtc-guided-training-of-ctc-towards-efficient","title":"GTC: Guided Training of CTC Towards Efficient and Accurate Scene Text Recognition","date":"2020-02-04","arxiv_id":"2002.01276","repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-text-recognition-with-finer-grid","title":"Scene Text Recognition With Finer Grid Rectification","date":"2020-01-26","arxiv_id":"2001.09389","repositories_listed":0,"syntology":null},{"url":"/paper/textscanner-reading-characters-in-order-for","slug":"textscanner-reading-characters-in-order-for","title":"TextScanner: Reading Characters in Order for Robust Scene Text Recognition","date":"2019-12-28","arxiv_id":"1912.12422","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-long-handwritten-text-line","title":"Improving Long Handwritten Text Line Recognition with Convolutional Multi-way Associative Memory","date":"2019-11-05","arxiv_id":"1911.01577","repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-text-recognition-with-temporal","title":"Scene Text Recognition with Temporal Convolutional Encoder","date":"2019-11-04","arxiv_id":"1911.01051","repositories_listed":0,"syntology":null},{"url":null,"slug":"running-event-visualization-using-videos-from","title":"Running Event Visualization using Videos from Multiple Cameras","date":"2019-09-06","arxiv_id":"1909.02835","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-embedding-gate-for-attention-based","title":"Adaptive Embedding Gate for Attention-Based Scene Text Recognition","date":"2019-08-26","arxiv_id":"1908.09475","repositories_listed":0,"syntology":null},{"url":null,"slug":"symmetry-constrained-rectification-network","title":"Symmetry-constrained Rectification Network for Scene Text Recognition","date":"2019-08-06","arxiv_id":"1908.01957","repositories_listed":0,"syntology":null},{"url":null,"slug":"2d-ctc-for-scene-text-recognition","title":"2D-CTC for Scene Text Recognition","date":"2019-07-23","arxiv_id":"1907.09705","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hardware-oriented-and-memory-efficient","title":"A Hardware-Oriented and Memory-Efficient Method for CTC Decoding","date":"2019-05-08","arxiv_id":"1905.03175","repositories_listed":0,"syntology":null},{"url":null,"slug":"190409405","title":"FACLSTM: ConvLSTM with Focused Attention for Scene Text Recognition","date":"2019-04-20","arxiv_id":"1904.09405","repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-text-synthesis-for-efficient-and","title":"Scene Text Synthesis for Efficient and Effective Deep Network Training","date":"2019-01-26","arxiv_id":"1901.09193","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-scale-aware-feature-encoder-for-scene","title":"SAFE: Scale Aware Feature Encoder for Scene Text Recognition","date":"2019-01-17","arxiv_id":"1901.05770","repositories_listed":0,"syntology":null},{"url":null,"slug":"recurrent-calibration-network-for-irregular","title":"Recurrent Calibration Network for Irregular Text Recognition","date":"2018-12-18","arxiv_id":"1812.07145","repositories_listed":0,"syntology":null},{"url":null,"slug":"esir-end-to-end-scene-text-recognition-via","title":"ESIR: End-to-end Scene Text Recognition via Iterative Image Rectification","date":"2018-12-14","arxiv_id":"1812.05824","repositories_listed":0,"syntology":null},{"url":null,"slug":"simultaneous-recognition-of-horizontal-and","title":"Simultaneous Recognition of Horizontal and Vertical Text in Natural Images","date":"2018-12-06","arxiv_id":"1812.07059","repositories_listed":0,"syntology":null},{"url":null,"slug":"cursive-scene-text-analysis-by-deep","title":"Cursive Scene Text Analysis by Deep Convolutional Linear Pyramids","date":"2018-09-27","arxiv_id":"1809.10792","repositories_listed":0,"syntology":null},{"url":"/paper/scene-text-recognition-from-two-dimensional","slug":"scene-text-recognition-from-two-dimensional","title":"Scene Text Recognition from Two-Dimensional Perspective","date":"2018-09-18","arxiv_id":"1809.06508","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetically-supervised-feature-learning-for","title":"Synthetically Supervised Feature Learning for Scene Text Recognition","date":"2018-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"double-supervised-network-with-attention","title":"Double Supervised Network with Attention Mechanism for Scene Text Recognition","date":"2018-08-02","arxiv_id":"1808.00677","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-adversarial-attack-on-scene-text","title":"Adaptive Adversarial Attack on Scene Text Recognition","date":"2018-07-09","arxiv_id":"1807.03326","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-scene-character-recognition","title":"Multilingual Scene Character Recognition System using Sparse Auto-Encoder for Efficient Local Features Representation in Bag of Features","date":"2018-06-11","arxiv_id":"1806.07374","repositories_listed":0,"syntology":null},{"url":null,"slug":"scan-sliding-convolutional-attention-network","title":"SCAN: Sliding Convolutional Attention Network for Scene Text Recognition","date":"2018-06-02","arxiv_id":"1806.00578","repositories_listed":0,"syntology":null},{"url":null,"slug":"edit-probability-for-scene-text-recognition","title":"Edit Probability for Scene Text Recognition","date":"2018-05-09","arxiv_id":"1805.03384","repositories_listed":0,"syntology":null},{"url":null,"slug":"char-net-a-character-aware-neural-network-for","title":"Char-Net: A Character-Aware Neural Network for Distorted Scene Text Recognition","date":"2018-04-27","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/see-towards-semi-supervisedend-to-end-scene","slug":"see-towards-semi-supervisedend-to-end-scene","title":"SEE: Towards Semi-SupervisedEnd-to-End Scene Text Recognition","date":"2017-12-14","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unconstrained-scene-text-and-video-text","title":"Unconstrained Scene Text and Video Text Recognition for Arabic Script","date":"2017-11-07","arxiv_id":"1711.02396","repositories_listed":0,"syntology":null},{"url":null,"slug":"adadnns-adaptive-ensemble-of-deep-neural","title":"AdaDNNs: Adaptive Ensemble of Deep Neural Networks for Scene Text Recognition","date":"2017-10-10","arxiv_id":"1710.03425","repositories_listed":0,"syntology":null},{"url":null,"slug":"reading-scene-text-with-attention","title":"Reading Scene Text with Attention Convolutional Sequence Modeling","date":"2017-09-13","arxiv_id":"1709.04303","repositories_listed":0,"syntology":null},{"url":null,"slug":"focusing-attention-towards-accurate-text","title":"Focusing Attention: Towards Accurate Text Recognition in Natural Images","date":"2017-09-07","arxiv_id":"1709.02054","repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-text-recognition-with-sliding","title":"Scene Text Recognition with Sliding Convolutional Character Models","date":"2017-09-06","arxiv_id":"1709.01727","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-attention-models-for-scene-text","title":"Visual attention models for scene text recognition","date":"2017-06-05","arxiv_id":"1706.01487","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-based-isolated-arabic-scene","title":"Deep Learning based Isolated Arabic Scene Character Recognition","date":"2017-04-22","arxiv_id":"1704.06821","repositories_listed":0,"syntology":null},{"url":null,"slug":"smart-library-identifying-books-in-a-library","title":"Smart Library: Identifying Books in a Library using Richly Supervised Deep Scene Text Reading","date":"2016-11-22","arxiv_id":"1611.07385","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-shape-models-joint-text","title":"Generative Shape Models: Joint Text Recognition and Segmentation with Very Little Training Data","date":"2016-11-09","arxiv_id":"1611.02788","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequence-to-sequence-learning-for","title":"Sequence to sequence learning for unconstrained scene text recognition","date":"2016-07-20","arxiv_id":"1607.06125","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-cnn-based-scene-chinese-text-recognition","title":"A CNN Based Scene Chinese Text Recognition Algorithm With Synthetic Data Engine","date":"2016-04-07","arxiv_id":"1604.01891","repositories_listed":0,"syntology":null},{"url":"/paper/a-fine-grained-approach-to-scene-text-script","slug":"a-fine-grained-approach-to-scene-text-script","title":"A fine-grained approach to scene text script identification","date":"2016-02-24","arxiv_id":"1602.07475","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-energy-minimization-framework-for","title":"Enhancing Energy Minimization Framework for Scene Text Recognition with Top-Down Cues","date":"2016-01-13","arxiv_id":"1601.03128","repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-matters-convolutional-recurrent-neural","title":"Memory Matters: Convolutional Recurrent Neural Network for Scene Text Recognition","date":"2016-01-06","arxiv_id":"1601.01100","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-local-structures-with-the","title":"Exploiting Local Structures with the Kronecker Layer in Convolutional Networks","date":"2015-12-31","arxiv_id":"1512.09194","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-scene-text-recognition-using-sparse","title":"Robust Scene Text Recognition Using Sparse Coding based Features","date":"2015-12-29","arxiv_id":"1512.08669","repositories_listed":0,"syntology":null},{"url":null,"slug":"region-based-discriminative-feature-pooling","title":"Region-based Discriminative Feature Pooling for Scene Text Recognition","date":"2014-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"strokelets-a-learned-multi-scale","title":"Strokelets: A Learned Multi-Scale Representation for Scene Text Recognition","date":"2014-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-text-recognition-using-part-based-tree","title":"Scene Text Recognition Using Part-Based Tree-Structured Character Detection","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reading-ancient-coin-legends-object","title":"Reading Ancient Coin Legends: Object Recognition vs. OCR","date":"2013-04-26","arxiv_id":"1304.7184","repositories_listed":0,"syntology":null}],"record_sha256":"e01bc3d3367b86ded51039cda5367f64795a3a92467af6bee958c5f299eae4d7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}