{"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":"/dataset/icdar-2013","name":"ICDAR 2013","full_name":null,"description_markdown":"The **ICDAR 2013** dataset consists of 229 training images and 233 testing images, with word-level annotations provided. It is the standard benchmark dataset for evaluating near-horizontal text detection.\r\n\r\nSource: [Single Shot Text Detector with Regional Attention](https://arxiv.org/abs/1709.00138)\r\nImage Source: [https://plos.figshare.com/articles/Detection_examples_of_the_proposed_method_on_the_ICDAR_2013_dataset_17_/5325856](https://plos.figshare.com/articles/Detection_examples_of_the_proposed_method_on_the_ICDAR_2013_dataset_17_/5325856)","description_withheld":null,"homepage":"https://rrc.cvc.uab.es/?ch=2","introduced_date":"2013-01-01","introduced_date_note":null,"introduced_by":{"paper":null,"title":"ICDAR 2013 Robust Reading Competition","first_author":null,"url":"https://doi.org/10.1109/ICDAR.2013.221"},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Scene Text Recognition","url":"/task/scene-text-recognition","datasets_with_task":"/datasets/task/scene-text-recognition"},{"name":"Scene Text Detection","url":"/task/scene-text-detection","datasets_with_task":"/datasets/task/scene-text-detection"},{"name":"Table Detection","url":"/task/table-detection","datasets_with_task":"/datasets/task/table-detection"},{"name":"Handwritten Chinese Text Recognition","url":"/task/handwritten-chinese-text-recognition","datasets_with_task":"/datasets/task/handwritten-chinese-text-recognition"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["ICDAR 2013","ICDAR2013"],"data_loaders":[{"repo":"https://github.com/activeloopai/Hub","url":"https://docs.activeloop.ai/datasets/icdar-2013-dataset","frameworks":["tf","pytorch"]},{"repo":"https://github.com/mindee/doctr","url":"https://mindee.github.io/doctr/latest/datasets.html#doctr.datasets.IC13","frameworks":["tf","pytorch"]},{"repo":"https://github.com/tanglang96/DataLoaders_DALI","url":"https://github.com/tanglang96/DataLoaders_DALI","frameworks":["pytorch"]}],"num_papers_in_archive":246,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/scene-text-recognition-on-icdar2013","task":"Scene Text Recognition","dataset_variant":"ICDAR2013","rows":38,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CLIP4STR-L*","paper":"/paper/an-empirical-study-of-scaling-law-for-ocr","metrics":{"Accuracy":"99.42"},"code_links":[{"title":"large-ocr-model/large-ocr-model.github.io","url":"https://github.com/large-ocr-model/large-ocr-model.github.io"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/scene-text-detection-on-icdar-2013","task":"Scene Text Detection","dataset_variant":"ICDAR 2013","rows":16,"metrics":["F-Measure","Precision","Recall","H-Mean"],"first_row_in_archive_order":{"model":"TextFuseNet (ResNeXt-101)","paper":"/paper/textfusenet-scene-text-detection-with-richer","metrics":{"F-Measure":"94.61%","Precision":"97.27","Recall":"92.09"},"code_links":[{"title":"ying09/TextFuseNet","url":"https://github.com/ying09/TextFuseNet"},{"title":"mindspore-ai/models","url":"https://github.com/mindspore-ai/models/tree/master/research/cv/textfusenet"},{"title":"kingcong/textfusenet","url":"https://github.com/kingcong/textfusenet"},{"title":"2023-MindSpore-1/ms-code-217","url":"https://github.com/2023-MindSpore-1/ms-code-217/tree/main/textfusenet"},{"title":"2023-MindSpore-1/ms-code-7","url":"https://github.com/2023-MindSpore-1/ms-code-7/tree/main/textfusenet"},{"title":"MindSpore-paper-code-2/code3","url":"https://github.com/MindSpore-paper-code-2/code3/tree/main/textfusenet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/table-detection-on-icdar2013-1","task":"Table Detection","dataset_variant":"ICDAR2013","rows":3,"metrics":["Avg F1"],"first_row_in_archive_order":{"model":"cascadetabnet","paper":"/paper/cascadetabnet-an-approach-for-end-to-end","metrics":{"Avg F1":"1.0"},"code_links":[{"title":"DevashishPrasad/CascadeTabNet","url":"https://github.com/DevashishPrasad/CascadeTabNet"},{"title":"virtualsociety/ai-table-recognition","url":"https://github.com/virtualsociety/ai-table-recognition"},{"title":"hmnth1/table_ocr","url":"https://github.com/hmnth1/table_ocr"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":50,"of":50,"counts":{"papers_with_a_benchmark_row":50,"with_a_code_link":44,"where_syntology_ran_a_sample":11,"not_listed_spam_title":0,"listed":50,"listed_where_code_ran":11,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":10,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":10,"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 with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/an-empirical-study-of-scaling-law-for-ocr","slug":"an-empirical-study-of-scaling-law-for-ocr","title":"An Empirical Study of Scaling Law for OCR","date":"2023-12-29","arxiv_id":"2401.00028","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dtrocr-decoder-only-transformer-for-optical","slug":"dtrocr-decoder-only-transformer-for-optical","title":"DTrOCR: Decoder-only Transformer for Optical Character Recognition","date":"2023-08-30","arxiv_id":"2308.15996","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/clip4str-a-simple-baseline-for-scene-text-1","slug":"clip4str-a-simple-baseline-for-scene-text-1","title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model","date":"2023-05-23","arxiv_id":"2305.14014","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":3,"samples_unverified":4,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/clip4str-a-simple-baseline-for-scene-text-1#ran","syntology_url":"https://syntology.ai/paper/2305.14014","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14014"}}}},{"paper":"/paper/self-supervised-character-to-character","slug":"self-supervised-character-to-character","title":"Self-supervised Character-to-Character Distillation for Text Recognition","date":"2022-11-01","arxiv_id":"2211.00288","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/multi-granularity-prediction-for-scene-text","slug":"multi-granularity-prediction-for-scene-text","title":"Multi-Granularity Prediction for Scene Text Recognition","date":"2022-09-08","arxiv_id":"2209.03592","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/scene-text-recognition-with-permuted","slug":"scene-text-recognition-with-permuted","title":"Scene Text Recognition with Permuted Autoregressive Sequence Models","date":"2022-07-14","arxiv_id":"2207.06966","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":5,"samples_constructed":5,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["baudm/parseq"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/scene-text-recognition-with-permuted#ran","syntology_url":"https://syntology.ai/paper/2207.06966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.06966"}}}},{"paper":"/paper/svtr-scene-text-recognition-with-a-single","slug":"svtr-scene-text-recognition-with-a-single","title":"SVTR: Scene Text Recognition with a Single Visual Model","date":"2022-04-30","arxiv_id":"2205.00159","rows_on_this_dataset":4,"code_links":4,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-modal-text-recognition-networks","slug":"multi-modal-text-recognition-networks","title":"Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features","date":"2021-11-30","arxiv_id":"2111.15263","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/cdistnet-perceiving-multi-domain-character","slug":"cdistnet-perceiving-multi-domain-character","title":"CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition","date":"2021-11-22","arxiv_id":"2111.11011","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/look-back-again-dual-parallel-attention","slug":"look-back-again-dual-parallel-attention","title":"Look Back Again: Dual Parallel Attention Network for Accurate and Robust Scene Text Recognition","date":"2021-08-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vision-transformer-for-fast-and-efficient","slug":"vision-transformer-for-fast-and-efficient","title":"Vision Transformer for Fast and Efficient Scene Text Recognition","date":"2021-05-18","arxiv_id":"2105.08582","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cdec-net-composite-deformable-cascade-network","slug":"cdec-net-composite-deformable-cascade-network","title":"CDeC-Net: Composite Deformable Cascade Network for Table Detection in Document Images","date":"2020-08-25","arxiv_id":"2008.10831","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["mdv3101/CDeCNet"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cdec-net-composite-deformable-cascade-network#ran","syntology_url":"https://syntology.ai/paper/2008.10831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.10831"}}}},{"paper":"/paper/seed-semantics-enhanced-encoder-decoder","slug":"seed-semantics-enhanced-encoder-decoder","title":"SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition","date":"2020-05-22","arxiv_id":"2005.10977","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/textfusenet-scene-text-detection-with-richer","slug":"textfusenet-scene-text-detection-with-richer","title":"TextFuseNet: Scene Text Detection with Richer Fused Features","date":"2020-05-17","arxiv_id":null,"rows_on_this_dataset":1,"code_links":6,"syntology":null},{"paper":"/paper/cascadetabnet-an-approach-for-end-to-end","slug":"cascadetabnet-an-approach-for-end-to-end","title":"CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents","date":"2020-04-27","arxiv_id":"2004.12629","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["DevashishPrasad/CascadeTabNet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cascadetabnet-an-approach-for-end-to-end#ran","syntology_url":"https://syntology.ai/paper/2004.12629","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.12629"}}}},{"paper":"/paper/towards-accurate-scene-text-recognition-with","slug":"towards-accurate-scene-text-recognition-with","title":"Towards Accurate Scene Text Recognition with Semantic Reasoning Networks","date":"2020-03-27","arxiv_id":"2003.12294","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/tablenet-deep-learning-model-for-end-to-end","slug":"tablenet-deep-learning-model-for-end-to-end","title":"TableNet: Deep Learning model for end-to-end Table detection and Tabular data extraction from Scanned Document Images","date":"2020-01-06","arxiv_id":"2001.01469","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tablenet-deep-learning-model-for-end-to-end#ran","syntology_url":"https://syntology.ai/paper/2001.01469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.01469"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/decoupled-attention-network-for-text","slug":"decoupled-attention-network-for-text","title":"Decoupled Attention Network for Text Recognition","date":"2019-12-21","arxiv_id":"1912.10205","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/on-recognizing-texts-of-arbitrary-shapes-with","slug":"on-recognizing-texts-of-arbitrary-shapes-with","title":"On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention","date":"2019-10-10","arxiv_id":"1910.04396","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/unsharp-masking-layer-injecting-prior","slug":"unsharp-masking-layer-injecting-prior","title":"Unsharp Masking Layer: Injecting Prior Knowledge in Convolutional Networks for Image Classification","date":"2019-09-29","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/character-region-awareness-for-text-detection","slug":"character-region-awareness-for-text-detection","title":"Character Region Awareness for Text Detection","date":"2019-04-03","arxiv_id":"1904.01941","rows_on_this_dataset":1,"code_links":18,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":40,"samples_ran":25,"samples_constructed":0,"samples_ran_checked":20,"samples_ran_instrument_failed":5,"samples_unverified":15,"pointer_only_for_licence":4,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/character-region-awareness-for-text-detection#ran","syntology_url":"https://syntology.ai/paper/1904.01941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01941"}}}},{"paper":"/paper/what-is-wrong-with-scene-text-recognition","slug":"what-is-wrong-with-scene-text-recognition","title":"What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis","date":"2019-04-03","arxiv_id":"1904.01906","rows_on_this_dataset":1,"code_links":13,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":19,"samples_ran":17,"samples_constructed":0,"samples_ran_checked":17,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["clovaai/deep-text-recognition-benchmark"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/what-is-wrong-with-scene-text-recognition#ran","syntology_url":"https://syntology.ai/paper/1904.01906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01906"}}}},{"paper":"/paper/scene-text-detection-with-supervised-pyramid","slug":"scene-text-detection-with-supervised-pyramid","title":"Scene Text Detection with Supervised Pyramid Context Network","date":"2018-11-21","arxiv_id":"1811.08605","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/show-attend-and-read-a-simple-and-strong","slug":"show-attend-and-read-a-simple-and-strong","title":"Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition","date":"2018-11-02","arxiv_id":"1811.00751","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/show-attend-and-read-a-simple-and-strong#ran","syntology_url":"https://syntology.ai/paper/1811.00751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.00751"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/mask-textspotter-an-end-to-end-trainable","slug":"mask-textspotter-an-end-to-end-trainable","title":"Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes","date":"2018-07-06","arxiv_id":"1807.02242","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/aster-an-attentional-scene-text-recognizer","slug":"aster-an-attentional-scene-text-recognizer","title":"ASTER: An Attentional Scene Text Recognizer with Flexible Rectification","date":"2018-06-25","arxiv_id":null,"rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/detecting-multi-oriented-text-with-corner","slug":"detecting-multi-oriented-text-with-corner","title":"Detecting Multi-Oriented Text with Corner-based Region Proposals","date":"2018-04-08","arxiv_id":"1804.02690","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-oriented-scene-text-detection-via","slug":"multi-oriented-scene-text-detection-via","title":"Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation","date":"2018-02-25","arxiv_id":"1802.08948","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/textboxes-a-single-shot-oriented-scene-text","slug":"textboxes-a-single-shot-oriented-scene-text","title":"TextBoxes++: A Single-Shot Oriented Scene Text Detector","date":"2018-01-09","arxiv_id":"1801.02765","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/pixellink-detecting-scene-text-via-instance","slug":"pixellink-detecting-scene-text-via-instance","title":"PixelLink: Detecting Scene Text via Instance Segmentation","date":"2018-01-04","arxiv_id":"1801.01315","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/single-shot-text-detector-with-regional","slug":"single-shot-text-detector-with-regional","title":"Single Shot Text Detector with Regional Attention","date":"2017-09-01","arxiv_id":"1709.00138","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/wordsup-exploiting-word-annotations-for","slug":"wordsup-exploiting-word-annotations-for","title":"WordSup: Exploiting Word Annotations for Character based Text Detection","date":"2017-08-22","arxiv_id":"1708.06720","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/stn-ocr-a-single-neural-network-for-text","slug":"stn-ocr-a-single-neural-network-for-text","title":"STN-OCR: A single Neural Network for Text Detection and Text Recognition","date":"2017-07-27","arxiv_id":"1707.08831","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/detecting-oriented-text-in-natural-images-by","slug":"detecting-oriented-text-in-natural-images-by","title":"Detecting Oriented Text in Natural Images by Linking Segments","date":"2017-03-19","arxiv_id":"1703.06520","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/detecting-oriented-text-in-natural-images-by#ran","syntology_url":"https://syntology.ai/paper/1703.06520","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.06520"}}}},{"paper":"/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,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/synthetic-data-for-text-localisation-in","slug":"synthetic-data-for-text-localisation-in","title":"Synthetic Data for Text Localisation in Natural Images","date":"2016-04-22","arxiv_id":"1604.06646","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/synthetic-data-for-text-localisation-in#ran","syntology_url":"https://syntology.ai/paper/1604.06646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06646"}}}},{"paper":"/paper/robust-scene-text-recognition-with-automatic","slug":"robust-scene-text-recognition-with-automatic","title":"Robust Scene Text Recognition with Automatic Rectification","date":"2016-03-12","arxiv_id":"1603.03915","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/an-end-to-end-trainable-neural-network-for","slug":"an-end-to-end-trainable-neural-network-for","title":"An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition","date":"2015-07-21","arxiv_id":"1507.05717","rows_on_this_dataset":1,"code_links":85,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":81,"samples_ran":66,"samples_constructed":0,"samples_ran_checked":49,"samples_ran_instrument_failed":17,"samples_unverified":15,"pointer_only_for_licence":17,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/an-end-to-end-trainable-neural-network-for#ran","syntology_url":"https://syntology.ai/paper/1507.05717","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1507.05717"}}}},{"paper":"/paper/efficient-scene-text-localization-and","slug":"efficient-scene-text-localization-and","title":"Efficient Scene Text Localization and Recognition with Local Character Refinement","date":"2015-04-14","arxiv_id":"1504.03522","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/reading-text-in-the-wild-with-convolutional","slug":"reading-text-in-the-wild-with-convolutional","title":"Reading Text in the Wild with Convolutional Neural Networks","date":"2014-12-04","arxiv_id":"1412.1842","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/an-empirical-study-of-scaling-law-for-ocr","slug":"an-empirical-study-of-scaling-law-for-ocr","title":"An Empirical Study of Scaling Law for OCR","date":"2023-12-29","arxiv_id":"2401.00028","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dtrocr-decoder-only-transformer-for-optical","slug":"dtrocr-decoder-only-transformer-for-optical","title":"DTrOCR: Decoder-only Transformer for Optical Character Recognition","date":"2023-08-30","arxiv_id":"2308.15996","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/clip4str-a-simple-baseline-for-scene-text-1","slug":"clip4str-a-simple-baseline-for-scene-text-1","title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model","date":"2023-05-23","arxiv_id":"2305.14014","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":3,"samples_unverified":4,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/clip4str-a-simple-baseline-for-scene-text-1#ran","syntology_url":"https://syntology.ai/paper/2305.14014","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14014"}}}},{"paper":"/paper/self-supervised-character-to-character","slug":"self-supervised-character-to-character","title":"Self-supervised Character-to-Character Distillation for Text Recognition","date":"2022-11-01","arxiv_id":"2211.00288","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/multi-granularity-prediction-for-scene-text","slug":"multi-granularity-prediction-for-scene-text","title":"Multi-Granularity Prediction for Scene Text Recognition","date":"2022-09-08","arxiv_id":"2209.03592","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/scene-text-recognition-with-permuted","slug":"scene-text-recognition-with-permuted","title":"Scene Text Recognition with Permuted Autoregressive Sequence Models","date":"2022-07-14","arxiv_id":"2207.06966","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":5,"samples_constructed":5,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":0,"official":{"repos":["baudm/parseq"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/scene-text-recognition-with-permuted#ran","syntology_url":"https://syntology.ai/paper/2207.06966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.06966"}}}},{"paper":"/paper/svtr-scene-text-recognition-with-a-single","slug":"svtr-scene-text-recognition-with-a-single","title":"SVTR: Scene Text Recognition with a Single Visual Model","date":"2022-04-30","arxiv_id":"2205.00159","rows_on_this_dataset":4,"code_links":4,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-modal-text-recognition-networks","slug":"multi-modal-text-recognition-networks","title":"Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features","date":"2021-11-30","arxiv_id":"2111.15263","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/cdistnet-perceiving-multi-domain-character","slug":"cdistnet-perceiving-multi-domain-character","title":"CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition","date":"2021-11-22","arxiv_id":"2111.11011","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/look-back-again-dual-parallel-attention","slug":"look-back-again-dual-parallel-attention","title":"Look Back Again: Dual Parallel Attention Network for Accurate and Robust Scene Text Recognition","date":"2021-08-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vision-transformer-for-fast-and-efficient","slug":"vision-transformer-for-fast-and-efficient","title":"Vision Transformer for Fast and Efficient Scene Text Recognition","date":"2021-05-18","arxiv_id":"2105.08582","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cdec-net-composite-deformable-cascade-network","slug":"cdec-net-composite-deformable-cascade-network","title":"CDeC-Net: Composite Deformable Cascade Network for Table Detection in Document Images","date":"2020-08-25","arxiv_id":"2008.10831","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["mdv3101/CDeCNet"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cdec-net-composite-deformable-cascade-network#ran","syntology_url":"https://syntology.ai/paper/2008.10831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.10831"}}}},{"paper":"/paper/seed-semantics-enhanced-encoder-decoder","slug":"seed-semantics-enhanced-encoder-decoder","title":"SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition","date":"2020-05-22","arxiv_id":"2005.10977","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/textfusenet-scene-text-detection-with-richer","slug":"textfusenet-scene-text-detection-with-richer","title":"TextFuseNet: Scene Text Detection with Richer Fused Features","date":"2020-05-17","arxiv_id":null,"rows_on_this_dataset":1,"code_links":6,"syntology":null},{"paper":"/paper/cascadetabnet-an-approach-for-end-to-end","slug":"cascadetabnet-an-approach-for-end-to-end","title":"CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents","date":"2020-04-27","arxiv_id":"2004.12629","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["DevashishPrasad/CascadeTabNet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cascadetabnet-an-approach-for-end-to-end#ran","syntology_url":"https://syntology.ai/paper/2004.12629","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.12629"}}}},{"paper":"/paper/towards-accurate-scene-text-recognition-with","slug":"towards-accurate-scene-text-recognition-with","title":"Towards Accurate Scene Text Recognition with Semantic Reasoning Networks","date":"2020-03-27","arxiv_id":"2003.12294","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/tablenet-deep-learning-model-for-end-to-end","slug":"tablenet-deep-learning-model-for-end-to-end","title":"TableNet: Deep Learning model for end-to-end Table detection and Tabular data extraction from Scanned Document Images","date":"2020-01-06","arxiv_id":"2001.01469","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tablenet-deep-learning-model-for-end-to-end#ran","syntology_url":"https://syntology.ai/paper/2001.01469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.01469"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/decoupled-attention-network-for-text","slug":"decoupled-attention-network-for-text","title":"Decoupled Attention Network for Text Recognition","date":"2019-12-21","arxiv_id":"1912.10205","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/on-recognizing-texts-of-arbitrary-shapes-with","slug":"on-recognizing-texts-of-arbitrary-shapes-with","title":"On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention","date":"2019-10-10","arxiv_id":"1910.04396","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/unsharp-masking-layer-injecting-prior","slug":"unsharp-masking-layer-injecting-prior","title":"Unsharp Masking Layer: Injecting Prior Knowledge in Convolutional Networks for Image Classification","date":"2019-09-29","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/character-region-awareness-for-text-detection","slug":"character-region-awareness-for-text-detection","title":"Character Region Awareness for Text Detection","date":"2019-04-03","arxiv_id":"1904.01941","rows_on_this_dataset":1,"code_links":18,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":40,"samples_ran":25,"samples_constructed":0,"samples_ran_checked":20,"samples_ran_instrument_failed":5,"samples_unverified":15,"pointer_only_for_licence":4,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/character-region-awareness-for-text-detection#ran","syntology_url":"https://syntology.ai/paper/1904.01941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01941"}}}},{"paper":"/paper/what-is-wrong-with-scene-text-recognition","slug":"what-is-wrong-with-scene-text-recognition","title":"What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis","date":"2019-04-03","arxiv_id":"1904.01906","rows_on_this_dataset":1,"code_links":13,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":19,"samples_ran":17,"samples_constructed":0,"samples_ran_checked":17,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["clovaai/deep-text-recognition-benchmark"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/what-is-wrong-with-scene-text-recognition#ran","syntology_url":"https://syntology.ai/paper/1904.01906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01906"}}}},{"paper":"/paper/scene-text-detection-with-supervised-pyramid","slug":"scene-text-detection-with-supervised-pyramid","title":"Scene Text Detection with Supervised Pyramid Context Network","date":"2018-11-21","arxiv_id":"1811.08605","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/show-attend-and-read-a-simple-and-strong","slug":"show-attend-and-read-a-simple-and-strong","title":"Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition","date":"2018-11-02","arxiv_id":"1811.00751","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/show-attend-and-read-a-simple-and-strong#ran","syntology_url":"https://syntology.ai/paper/1811.00751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.00751"}}}},{"paper":"/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","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/mask-textspotter-an-end-to-end-trainable","slug":"mask-textspotter-an-end-to-end-trainable","title":"Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes","date":"2018-07-06","arxiv_id":"1807.02242","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/aster-an-attentional-scene-text-recognizer","slug":"aster-an-attentional-scene-text-recognizer","title":"ASTER: An Attentional Scene Text Recognizer with Flexible Rectification","date":"2018-06-25","arxiv_id":null,"rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/detecting-multi-oriented-text-with-corner","slug":"detecting-multi-oriented-text-with-corner","title":"Detecting Multi-Oriented Text with Corner-based Region Proposals","date":"2018-04-08","arxiv_id":"1804.02690","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-oriented-scene-text-detection-via","slug":"multi-oriented-scene-text-detection-via","title":"Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation","date":"2018-02-25","arxiv_id":"1802.08948","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/textboxes-a-single-shot-oriented-scene-text","slug":"textboxes-a-single-shot-oriented-scene-text","title":"TextBoxes++: A Single-Shot Oriented Scene Text Detector","date":"2018-01-09","arxiv_id":"1801.02765","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/pixellink-detecting-scene-text-via-instance","slug":"pixellink-detecting-scene-text-via-instance","title":"PixelLink: Detecting Scene Text via Instance Segmentation","date":"2018-01-04","arxiv_id":"1801.01315","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/single-shot-text-detector-with-regional","slug":"single-shot-text-detector-with-regional","title":"Single Shot Text Detector with Regional Attention","date":"2017-09-01","arxiv_id":"1709.00138","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/wordsup-exploiting-word-annotations-for","slug":"wordsup-exploiting-word-annotations-for","title":"WordSup: Exploiting Word Annotations for Character based Text Detection","date":"2017-08-22","arxiv_id":"1708.06720","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/stn-ocr-a-single-neural-network-for-text","slug":"stn-ocr-a-single-neural-network-for-text","title":"STN-OCR: A single Neural Network for Text Detection and Text Recognition","date":"2017-07-27","arxiv_id":"1707.08831","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/detecting-oriented-text-in-natural-images-by","slug":"detecting-oriented-text-in-natural-images-by","title":"Detecting Oriented Text in Natural Images by Linking Segments","date":"2017-03-19","arxiv_id":"1703.06520","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/detecting-oriented-text-in-natural-images-by#ran","syntology_url":"https://syntology.ai/paper/1703.06520","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.06520"}}}},{"paper":"/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,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/synthetic-data-for-text-localisation-in","slug":"synthetic-data-for-text-localisation-in","title":"Synthetic Data for Text Localisation in Natural Images","date":"2016-04-22","arxiv_id":"1604.06646","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/synthetic-data-for-text-localisation-in#ran","syntology_url":"https://syntology.ai/paper/1604.06646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06646"}}}},{"paper":"/paper/robust-scene-text-recognition-with-automatic","slug":"robust-scene-text-recognition-with-automatic","title":"Robust Scene Text Recognition with Automatic Rectification","date":"2016-03-12","arxiv_id":"1603.03915","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/an-end-to-end-trainable-neural-network-for","slug":"an-end-to-end-trainable-neural-network-for","title":"An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition","date":"2015-07-21","arxiv_id":"1507.05717","rows_on_this_dataset":1,"code_links":85,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":81,"samples_ran":66,"samples_constructed":0,"samples_ran_checked":49,"samples_ran_instrument_failed":17,"samples_unverified":15,"pointer_only_for_licence":17,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/an-end-to-end-trainable-neural-network-for#ran","syntology_url":"https://syntology.ai/paper/1507.05717","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1507.05717"}}}},{"paper":"/paper/efficient-scene-text-localization-and","slug":"efficient-scene-text-localization-and","title":"Efficient Scene Text Localization and Recognition with Local Character Refinement","date":"2015-04-14","arxiv_id":"1504.03522","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/reading-text-in-the-wild-with-convolutional","slug":"reading-text-in-the-wild-with-convolutional","title":"Reading Text in the Wild with Convolutional Neural Networks","date":"2014-12-04","arxiv_id":"1412.1842","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"papers_where_code_ran":11,"papers_where_code_ran_first_page":"/dataset/icdar-2013/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/icdar-2013/papers/ran/1","json":"/dataset/icdar-2013/papers/ran/1.json","rows":11}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":11,"samples_harvested":183,"samples_ran":140,"samples_constructed":5,"samples_ran_checked":114,"samples_ran_instrument_failed":26,"samples_unverified":43,"pointer_only_for_licence":24,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":11,"papers_with_a_run_with_no_instrument_failure":10,"papers_where_every_run_was_an_instrument_failure":1,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_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'","samples_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)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"07e82abfa8791447a5849a06975c14562b8dd2631595d1aec856c3d6f5491576","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}