{"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/2","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":2,"pages_in_order":3,"rows_per_page":100,"rows":[101,200],"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","next":"/task/scene-text-recognition/papers/3","papers":[{"url":"/paper/pushing-the-performance-limit-of-scene-text","slug":"pushing-the-performance-limit-of-scene-text","title":"Pushing the Performance Limit of Scene Text Recognizer without Human Annotation","date":"2022-04-16","arxiv_id":"2204.07714","repositories_listed":1,"syntology":null},{"url":"/paper/itervm-iterative-vision-modeling-module-for","slug":"itervm-iterative-vision-modeling-module-for","title":"IterVM: Iterative Vision Modeling Module for Scene Text Recognition","date":"2022-04-06","arxiv_id":"2204.02630","repositories_listed":1,"syntology":null},{"url":"/paper/siman-exploring-self-supervised","slug":"siman-exploring-self-supervised","title":"SimAN: Exploring Self-Supervised Representation Learning of Scene Text via Similarity-Aware Normalization","date":"2022-03-20","arxiv_id":"2203.10492","repositories_listed":1,"syntology":null},{"url":"/paper/text-diae-degradation-invariant-autoencoders","slug":"text-diae-degradation-invariant-autoencoders","title":"Text-DIAE: A Self-Supervised Degradation Invariant Autoencoders for Text Recognition and Document Enhancement","date":"2022-03-09","arxiv_id":"2203.04814","repositories_listed":1,"syntology":null},{"url":"/paper/a-glyph-driven-topology-enhancement-network","slug":"a-glyph-driven-topology-enhancement-network","title":"Self-supervised Implicit Glyph Attention for Text Recognition","date":"2022-03-07","arxiv_id":"2203.03382","repositories_listed":1,"syntology":null},{"url":"/paper/towards-boosting-the-accuracy-of-non-latin","slug":"towards-boosting-the-accuracy-of-non-latin","title":"Towards Boosting the Accuracy of Non-Latin Scene Text Recognition","date":"2022-01-10","arxiv_id":"2201.03185","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/visual-semantics-allow-for-textual-reasoning-1","slug":"visual-semantics-allow-for-textual-reasoning-1","title":"Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition","date":"2021-12-24","arxiv_id":"2112.12916","repositories_listed":1,"syntology":null},{"url":"/paper/traditional-chinese-synthetic-datasets","slug":"traditional-chinese-synthetic-datasets","title":"Traditional Chinese Synthetic Datasets Verified with Labeled Data for Scene Text Recognition","date":"2021-11-26","arxiv_id":"2111.13327","repositories_listed":1,"syntology":null},{"url":"/paper/tpsnet-thin-plate-spline-representation-for","slug":"tpsnet-thin-plate-spline-representation-for","title":"TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representation","date":"2021-10-25","arxiv_id":"2110.12826","repositories_listed":1,"syntology":null},{"url":"/paper/scene-text-image-super-resolution-via","slug":"scene-text-image-super-resolution-via","title":"Scene Text Image Super-Resolution via Parallelly Contextual Attention Network","date":"2021-10-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/pimnet-a-parallel-iterative-and-mimicking","slug":"pimnet-a-parallel-iterative-and-mimicking","title":"PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition","date":"2021-09-09","arxiv_id":"2109.04145","repositories_listed":1,"syntology":null},{"url":"/paper/meta-self-learning-for-multi-source-domain","slug":"meta-self-learning-for-multi-source-domain","title":"Meta Self-Learning for Multi-Source Domain Adaptation: A Benchmark","date":"2021-08-24","arxiv_id":"2108.10840","repositories_listed":1,"syntology":null},{"url":"/paper/data-augmentation-for-scene-text-recognition","slug":"data-augmentation-for-scene-text-recognition","title":"Data Augmentation for Scene Text Recognition","date":"2021-08-16","arxiv_id":"2108.06949","repositories_listed":1,"syntology":null},{"url":"/paper/why-you-should-try-the-real-data-for-the","slug":"why-you-should-try-the-real-data-for-the","title":"Why You Should Try the Real Data for the Scene Text Recognition","date":"2021-07-29","arxiv_id":"2107.13938","repositories_listed":1,"syntology":null},{"url":"/paper/synthtiger-synthetic-text-image-generator","slug":"synthtiger-synthetic-text-image-generator","title":"SynthTIGER: Synthetic Text Image GEneratoR Towards Better Text Recognition Models","date":"2021-07-20","arxiv_id":"2107.09313","repositories_listed":1,"syntology":null},{"url":"/paper/centripetaltext-an-efficient-text-instance","slug":"centripetaltext-an-efficient-text-instance","title":"CentripetalText: An Efficient Text Instance Representation for Scene Text Detection","date":"2021-07-13","arxiv_id":"2107.05945","repositories_listed":1,"syntology":null},{"url":"/paper/dictionary-guided-scene-text-recognition","slug":"dictionary-guided-scene-text-recognition","title":"Dictionary-Guided Scene Text Recognition","date":"2021-06-19","arxiv_id":null,"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/representation-and-correlation-enhanced","slug":"representation-and-correlation-enhanced","title":"Representation and Correlation Enhanced Encoder-Decoder Framework for Scene Text Recognition","date":"2021-06-13","arxiv_id":"2106.06960","repositories_listed":1,"syntology":null},{"url":"/paper/convolutional-neural-networks-with-gated","slug":"convolutional-neural-networks-with-gated","title":"Convolutional Neural Networks with Gated Recurrent Connections","date":"2021-06-05","arxiv_id":"2106.02859","repositories_listed":1,"syntology":{"n":7,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/convolutional-neural-networks-with-gated#ran","syntology_url":"https://syntology.ai/paper/2106.02859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02859"}},"official":{"repos":["Jianf-Wang/GRCNN"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"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/textadain-fine-grained-adain-for-robust-text","slug":"textadain-fine-grained-adain-for-robust-text","title":"TextAdaIN: Paying Attention to Shortcut Learning in Text Recognizers","date":"2021-05-09","arxiv_id":"2105.03906","repositories_listed":1,"syntology":null},{"url":"/paper/what-if-we-only-use-real-datasets-for-scene","slug":"what-if-we-only-use-real-datasets-for-scene","title":"What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels","date":"2021-03-07","arxiv_id":"2103.04400","repositories_listed":1,"syntology":null},{"url":"/paper/cstr-a-classification-perspective-on-scene","slug":"cstr-a-classification-perspective-on-scene","title":"Revisiting Classification Perspective on Scene Text Recognition","date":"2021-02-22","arxiv_id":"2102.10884","repositories_listed":1,"syntology":null},{"url":"/paper/gaussian-constrained-attention-network-for","slug":"gaussian-constrained-attention-network-for","title":"Gaussian Constrained Attention Network for Scene Text Recognition","date":"2020-10-19","arxiv_id":"2010.09169","repositories_listed":1,"syntology":null},{"url":"/paper/plugnet-degradation-aware-scene-text","slug":"plugnet-degradation-aware-scene-text","title":"PlugNet: Degradation Aware Scene Text Recognition Supervised by a Pluggable Super-Resolution Unit","date":"2020-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-comprehensive-study-on-sign-language","slug":"a-comprehensive-study-on-sign-language","title":"A Comprehensive Study on Deep Learning-based Methods for Sign Language Recognition","date":"2020-07-24","arxiv_id":"2007.12530","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"9 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-comprehensive-study-on-sign-language#ran","syntology_url":"https://syntology.ai/paper/2007.12530","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.12530"}},"official":{"repos":["iliasprc/slrzoo"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/text-recognition-in-the-wild-a-survey","slug":"text-recognition-in-the-wild-a-survey","title":"Text Recognition in the Wild: A Survey","date":"2020-05-07","arxiv_id":"2005.03492","repositories_listed":1,"syntology":null},{"url":"/paper/bidirectional-scene-text-recognition-with-a","slug":"bidirectional-scene-text-recognition-with-a","title":"Bidirectional Scene Text Recognition with a Single Decoder","date":"2019-12-08","arxiv_id":"1912.03656","repositories_listed":1,"syntology":null},{"url":"/paper/kiss-keeping-it-simple-for-scene-text","slug":"kiss-keeping-it-simple-for-scene-text","title":"KISS: Keeping It Simple for Scene Text Recognition","date":"2019-11-19","arxiv_id":"1911.08400","repositories_listed":1,"syntology":null},{"url":"/paper/icdar2019-robust-reading-challenge-on","slug":"icdar2019-robust-reading-challenge-on","title":"ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT)","date":"2019-09-16","arxiv_id":"1909.07145","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"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) · 2 unverified","sample_list":"/paper/icdar2019-robust-reading-challenge-on#ran","syntology_url":"https://syntology.ai/paper/1909.07145","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.07145"}},"official":{"repos":["cs-chan/Total-Text-Dataset"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/textsr-content-aware-text-super-resolution","slug":"textsr-content-aware-text-super-resolution","title":"TextSR: Content-Aware Text Super-Resolution Guided by Recognition","date":"2019-09-16","arxiv_id":"1909.07113","repositories_listed":1,"syntology":null},{"url":"/paper/focus-enhanced-scene-text-recognition-with","slug":"focus-enhanced-scene-text-recognition-with","title":"Focus-Enhanced Scene Text Recognition with Deformable Convolutions","date":"2019-08-29","arxiv_id":"1908.10998","repositories_listed":1,"syntology":null},{"url":"/paper/mask-textspotter-an-end-to-end-trainable-2","slug":"mask-textspotter-an-end-to-end-trainable-2","title":"Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes","date":"2019-08-22","arxiv_id":"1908.08207","repositories_listed":1,"syntology":null},{"url":"/paper/a-simple-and-robust-convolutional-attention","slug":"a-simple-and-robust-convolutional-attention","title":"A Holistic Representation Guided Attention Network for Scene Text Recognition","date":"2019-04-02","arxiv_id":"1904.01375","repositories_listed":1,"syntology":null},{"url":"/paper/accurate-data-efficient-unconstrained-text","slug":"accurate-data-efficient-unconstrained-text","title":"Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural Networks","date":"2018-12-31","arxiv_id":"1812.11894","repositories_listed":1,"syntology":null},{"url":"/paper/connectionist-temporal-classification-with","slug":"connectionist-temporal-classification-with","title":"Connectionist Temporal Classification with Maximum Entropy Regularization","date":"2018-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/aon-towards-arbitrarily-oriented-text","slug":"aon-towards-arbitrarily-oriented-text","title":"AON: Towards Arbitrarily-Oriented Text Recognition","date":"2017-11-12","arxiv_id":"1711.04226","repositories_listed":1,"syntology":null},{"url":"/paper/total-text-a-comprehensive-dataset-for-scene","slug":"total-text-a-comprehensive-dataset-for-scene","title":"Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition","date":"2017-10-28","arxiv_id":"1710.10400","repositories_listed":1,"syntology":null},{"url":"/paper/improving-text-proposals-for-scene-images","slug":"improving-text-proposals-for-scene-images","title":"Improving Text Proposals for Scene Images with Fully Convolutional Networks","date":"2017-02-16","arxiv_id":"1702.05089","repositories_listed":1,"syntology":null},{"url":"/paper/star-net-a-spatial-attention-residue-network","slug":"star-net-a-spatial-attention-residue-network","title":"Star-net: A spatial attention residue network for scene text recognition.","date":"2016-09-20","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/reading-scene-text-in-deep-convolutional","slug":"reading-scene-text-in-deep-convolutional","title":"Reading Scene Text in Deep Convolutional Sequences","date":"2015-06-14","arxiv_id":"1506.04395","repositories_listed":1,"syntology":null},{"url":"/paper/synthetic-data-and-artificial-neural-networks","slug":"synthetic-data-and-artificial-neural-networks","title":"Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition","date":"2014-06-09","arxiv_id":"1406.2227","repositories_listed":1,"syntology":null},{"url":"/paper/scene-text-recognition-using-higher-order","slug":"scene-text-recognition-using-higher-order","title":"Scene Text Recognition using Higher Order Language Priors","date":"2012-09-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"efficient-and-accurate-scene-text-recognition","title":"Efficient and Accurate Scene Text Recognition with Cascaded-Transformers","date":"2025-03-24","arxiv_id":"2503.18883","repositories_listed":0,"syntology":null},{"url":null,"slug":"accurate-scene-text-recognition-with","title":"Accurate Scene Text Recognition with Efficient Model Scaling and Cloze Self-Distillation","date":"2025-03-20","arxiv_id":"2503.16184","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-context-driven-training-free-network-for","title":"A Context-Driven Training-Free Network for Lightweight Scene Text Segmentation and Recognition","date":"2025-03-19","arxiv_id":"2503.15639","repositories_listed":0,"syntology":null},{"url":null,"slug":"billet-number-recognition-based-on-test-time","title":"Billet Number Recognition Based on Test-Time Adaptation","date":"2025-02-13","arxiv_id":"2502.09026","repositories_listed":0,"syntology":null},{"url":null,"slug":"arbitrary-reading-order-scene-text-spotter","title":"Arbitrary Reading Order Scene Text Spotter with Local Semantics Guidance","date":"2024-12-13","arxiv_id":"2412.10159","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-image-generation-for-low-resource","title":"Text Image Generation for Low-Resource Languages with Dual Translation Learning","date":"2024-09-26","arxiv_id":"2409.17747","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-model-for-two-tasks-cooperatively","title":"One Model for Two Tasks: Cooperatively Recognizing and Recovering Low-Resolution Scene Text Images by Iterative Mutual Guidance","date":"2024-09-22","arxiv_id":"2409.14483","repositories_listed":0,"syntology":null},{"url":null,"slug":"vl-reader-vision-and-language-reconstructor","title":"VL-Reader: Vision and Language Reconstructor is an Effective Scene Text Recognizer","date":"2024-09-18","arxiv_id":"2409.11656","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-02036","title":"LEGO: Self-Supervised Representation Learning for Scene Text Images","date":"2024-08-04","arxiv_id":"2408.02036","repositories_listed":0,"syntology":null},{"url":null,"slug":"haap-vision-context-hierarchical-attention","title":"HAAP: Vision-context Hierarchical Attention Autoregressive with Adaptive Permutation for Scene Text Recognition","date":"2024-05-15","arxiv_id":"2405.09125","repositories_listed":0,"syntology":null},{"url":null,"slug":"choose-what-you-need-disentangled","title":"Choose What You Need: Disentangled Representation Learning for Scene Text Recognition, Removal and Editing","date":"2024-05-07","arxiv_id":"2405.04377","repositories_listed":0,"syntology":null},{"url":null,"slug":"dlora-trocr-mixed-text-mode-optical-character","title":"Mixed Text Recognition with Efficient Parameter Fine-Tuning and Transformer","date":"2024-04-19","arxiv_id":"2404.12734","repositories_listed":0,"syntology":null},{"url":null,"slug":"jstr-judgment-improves-scene-text-recognition","title":"JSTR: Judgment Improves Scene Text Recognition","date":"2024-04-09","arxiv_id":"2404.05967","repositories_listed":0,"syntology":null},{"url":null,"slug":"indicstr12-a-dataset-for-indic-scene-text","title":"IndicSTR12: A Dataset for Indic Scene Text Recognition","date":"2024-03-12","arxiv_id":"2403.08007","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-vocabulary-scene-text-recognition-via","title":"Open-Vocabulary Scene Text Recognition via Pseudo-Image Labeling and Margin Loss","date":"2024-03-12","arxiv_id":"2403.07518","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficiently-leveraging-linguistic-priors-for","title":"Efficiently Leveraging Linguistic Priors for Scene Text Spotting","date":"2024-02-27","arxiv_id":"2402.17134","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequential-visual-and-semantic-consistency","title":"Sequential Visual and Semantic Consistency for Semi-supervised Text Recognition","date":"2024-02-24","arxiv_id":"2402.15806","repositories_listed":0,"syntology":null},{"url":null,"slug":"lumos-empowering-multimodal-llms-with-scene","title":"Lumos : Empowering Multimodal LLMs with Scene Text Recognition","date":"2024-02-12","arxiv_id":"2402.08017","repositories_listed":0,"syntology":null},{"url":null,"slug":"cmfn-cross-modal-fusion-network-for-irregular","title":"CMFN: Cross-Modal Fusion Network for Irregular Scene Text Recognition","date":"2024-01-18","arxiv_id":"2401.10041","repositories_listed":0,"syntology":null},{"url":null,"slug":"choose-what-you-need-disentangled-1","title":"Choose What You Need: Disentangled Representation Learning for Scene Text Recognition Removal and Editing","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ote-exploring-accurate-scene-text-recognition","title":"OTE: Exploring Accurate Scene Text Recognition Using One Token","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"str-cert-robustness-certification-for-deep","title":"STR-Cert: Robustness Certification for Deep Text Recognition on Deep Learning Pipelines and Vision Transformers","date":"2023-11-28","arxiv_id":"2401.05338","repositories_listed":0,"syntology":null},{"url":null,"slug":"recognition-guided-diffusion-model-for-scene","title":"Recognition-Guided Diffusion Model for Scene Text Image Super-Resolution","date":"2023-11-22","arxiv_id":"2311.13317","repositories_listed":0,"syntology":null},{"url":"/paper/diffusionstr-diffusion-model-for-scene-text","slug":"diffusionstr-diffusion-model-for-scene-text","title":"DiffusionSTR: Diffusion Model for Scene Text Recognition","date":"2023-06-29","arxiv_id":"2306.16707","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-scene-text-generation-for","title":"Weakly Supervised Scene Text Generation for Low-resource Languages","date":"2023-06-25","arxiv_id":"2306.14269","repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-text-recognition-with-image-text","title":"Scene Text Recognition with Image-Text Matching-guided Dictionary","date":"2023-05-08","arxiv_id":"2305.04524","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-scene-text-recognition-for","title":"Improving Scene Text Recognition for Character-Level Long-Tailed Distribution","date":"2023-03-31","arxiv_id":"2304.08592","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-aware-selective-label-smoothing-for","title":"Context-Aware Selective Label Smoothing for Calibrating Sequence Recognition Model","date":"2023-03-13","arxiv_id":"2303.06946","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusion-in-the-dark-a-diffusion-model-for","title":"Diffusion in the Dark: A Diffusion Model for Low-Light Text Recognition","date":"2023-03-07","arxiv_id":"2303.04291","repositories_listed":0,"syntology":null},{"url":null,"slug":"augmented-transformers-with-adaptive-n-grams","title":"Augmented Transformers with Adaptive n-grams Embedding for Multilingual Scene Text Recognition","date":"2023-02-28","arxiv_id":"2302.14261","repositories_listed":0,"syntology":null},{"url":null,"slug":"clipter-looking-at-the-bigger-picture-in","title":"CLIPTER: Looking at the Bigger Picture in Scene Text Recognition","date":"2023-01-18","arxiv_id":"2301.07464","repositories_listed":0,"syntology":null},{"url":null,"slug":"portmanteauing-features-for-scene-text","title":"Portmanteauing Features for Scene Text Recognition","date":"2022-11-09","arxiv_id":"2211.05036","repositories_listed":0,"syntology":null},{"url":null,"slug":"pure-transformer-with-integrated-experts-for","title":"Pure Transformer with Integrated Experts for Scene Text Recognition","date":"2022-11-09","arxiv_id":"2211.04963","repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-text-recognition-with-semantics","title":"Scene Text Recognition with Semantics","date":"2022-10-19","arxiv_id":"2210.10836","repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-text-image-super-resolution-via-content","title":"Scene Text Image Super-Resolution via Content Perceptual Loss and Criss-Cross Transformer Blocks","date":"2022-10-13","arxiv_id":"2210.06924","repositories_listed":0,"syntology":null},{"url":null,"slug":"reading-chinese-in-natural-scenes-with-a-bag","title":"Reading Chinese in Natural Scenes with a Bag-of-Radicals Prior","date":"2022-10-05","arxiv_id":"2210.02576","repositories_listed":0,"syntology":null},{"url":null,"slug":"out-of-vocabulary-challenge-report","title":"Out-of-Vocabulary Challenge Report","date":"2022-09-14","arxiv_id":"2209.06717","repositories_listed":0,"syntology":null},{"url":null,"slug":"scene-text-recognition-with-single-point","title":"Scene Text Recognition with Single-Point Decoding Network","date":"2022-09-05","arxiv_id":"2209.01914","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-language-adaptive-mutual-decoder-for","title":"Vision-Language Adaptive Mutual Decoder for OOV-STR","date":"2022-09-02","arxiv_id":"2209.00859","repositories_listed":0,"syntology":null},{"url":null,"slug":"1st-place-solution-to-eccv-2022-challenge-on-1","title":"1st Place Solution to ECCV 2022 Challenge on Out of Vocabulary Scene Text Understanding: End-to-End Recognition of Out of Vocabulary Words","date":"2022-09-01","arxiv_id":"2209.00224","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-boxes-boosting-end-to-end-scene-text","title":"Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning","date":"2022-07-25","arxiv_id":"2207.11934","repositories_listed":0,"syntology":null},{"url":null,"slug":"sgbanet-semantic-gan-and-balanced-attention","title":"SGBANet: Semantic GAN and Balanced Attention Network for Arbitrarily Oriented Scene Text Recognition","date":"2022-07-21","arxiv_id":"2207.10256","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-open-set-text-recognition-via-label","title":"Towards Open-Set Text Recognition via Label-to-Prototype Learning","date":"2022-03-10","arxiv_id":"2203.05179","repositories_listed":0,"syntology":null},{"url":null,"slug":"transfer-learning-for-scene-text-recognition","title":"Transfer Learning for Scene Text Recognition in Indian Languages","date":"2022-01-10","arxiv_id":"2201.03180","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-semantic-transformer-for-scene-text","title":"Visual-Semantic Transformer for Scene Text Recognition","date":"2021-12-02","arxiv_id":"2112.00948","repositories_listed":0,"syntology":null},{"url":null,"slug":"decoupling-visual-semantic-feature-learning","title":"Decoupling Visual-Semantic Feature Learning for Robust Scene Text Recognition","date":"2021-11-24","arxiv_id":"2111.12351","repositories_listed":0,"syntology":null},{"url":null,"slug":"utilizing-resource-rich-language-datasets-for","title":"Utilizing Resource-Rich Language Datasets for End-to-End Scene Text Recognition in Resource-Poor Languages","date":"2021-11-24","arxiv_id":"2111.12276","repositories_listed":0,"syntology":null},{"url":null,"slug":"trig-transformer-based-text-recognizer-with","title":"TRIG: Transformer-Based Text Recognizer with Initial Embedding Guidance","date":"2021-11-16","arxiv_id":"2111.08314","repositories_listed":0,"syntology":null},{"url":null,"slug":"oracle-teacher-towards-better-knowledge","title":"Oracle Teacher: Leveraging Target Information for Better Knowledge Distillation of CTC Models","date":"2021-11-05","arxiv_id":"2111.03664","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":"sharp-attention-for-sequence-to-sequence","title":"Sharp Attention for Sequence to Sequence Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ifr-iterative-fusion-based-recognizer-for-low","title":"IFR: Iterative Fusion Based Recognizer For Low Quality Scene Text Recognition","date":"2021-08-13","arxiv_id":"2108.06166","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-is-text-no-matter-what-unifying-text","title":"Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillation","date":"2021-07-26","arxiv_id":"2107.12087","repositories_listed":0,"syntology":null},{"url":null,"slug":"rewritenet-realistic-scene-text-image","title":"RewriteNet: Reliable Scene Text Editing with Implicit Decomposition of Text Contents and Styles","date":"2021-07-23","arxiv_id":"2107.11041","repositories_listed":0,"syntology":null}],"record_sha256":"976af92b6fca91d067179bdeabcfd275f5b4752b3b1cb947fe1784aa9dc590dc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}