{"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","name":"Scene Text Recognition","slug":"scene-text-recognition","description_markdown":"See [Scene Text Detection](https://paperswithcode.com/task/scene-text-detection) for leaderboards in this task.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":269,"papers_with_code":146,"benchmarks":15,"benchmark_tables_in_archive":15,"benchmark_tables_shown":15,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":29,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/scene-text-recognition-on-icdar2013","slug":"scene-text-recognition-on-icdar2013","dataset":"ICDAR2013","dataset_url":"/dataset/icdar-2013","rows_in_archive":38,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CLIP4STR-L*","paper_title":"An Empirical Study of Scaling Law for OCR","paper_url":"/paper/an-empirical-study-of-scaling-law-for-ocr","paper_date":"2023-12-29","arxiv_id":"2401.00028","code_links":[{"title":"large-ocr-model/large-ocr-model.github.io","url":"https://github.com/large-ocr-model/large-ocr-model.github.io"}],"syntology":null}},{"leaderboard":"/sota/scene-text-recognition-on-svt","slug":"scene-text-recognition-on-svt","dataset":"SVT","dataset_url":"/dataset/svt","rows_in_archive":37,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CLIP4STR-H (DFN-5B)","paper_title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model","paper_url":"/paper/clip4str-a-simple-baseline-for-scene-text-1","paper_date":"2023-05-23","arxiv_id":"2305.14014","code_links":[{"title":"VamosC/CLIP4STR","url":"https://github.com/VamosC/CLIP4STR"}],"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"6 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; 3 where Syntology's instrument failed) · 4 unverified","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"}},"official":null}}},{"leaderboard":"/sota/scene-text-recognition-on-icdar2015","slug":"scene-text-recognition-on-icdar2015","dataset":"ICDAR2015","dataset_url":null,"rows_in_archive":27,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"DTrOCR 105M","paper_title":"DTrOCR: Decoder-only Transformer for Optical Character Recognition","paper_url":"/paper/dtrocr-decoder-only-transformer-for-optical","paper_date":"2023-08-30","arxiv_id":"2308.15996","code_links":[{"title":"arvindrajan92/DTrOCR","url":"https://github.com/arvindrajan92/DTrOCR"}],"syntology":null}},{"leaderboard":"/sota/scene-text-recognition-on-cute80","slug":"scene-text-recognition-on-cute80","dataset":"CUTE80","dataset_url":"/dataset/cute80","rows_in_archive":18,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CPPD","paper_title":"Context Perception Parallel Decoder for Scene Text Recognition","paper_url":"/paper/context-perception-parallel-decoder-for-scene","paper_date":"2023-07-23","arxiv_id":"2307.12270","code_links":[{"title":"PaddlePaddle/PaddleOCR","url":"https://github.com/PaddlePaddle/PaddleOCR"},{"title":"topdu/openocr","url":"https://github.com/topdu/openocr"}],"syntology":null}},{"leaderboard":"/sota/scene-text-recognition-on-iiit5k","slug":"scene-text-recognition-on-iiit5k","dataset":"IIIT5k","dataset_url":"/dataset/iiit5k","rows_in_archive":17,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CLIP4STR-L (DataComp-1B)","paper_title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model","paper_url":"/paper/clip4str-a-simple-baseline-for-scene-text-1","paper_date":"2023-05-23","arxiv_id":"2305.14014","code_links":[{"title":"VamosC/CLIP4STR","url":"https://github.com/VamosC/CLIP4STR"}],"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"6 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; 3 where Syntology's instrument failed) · 4 unverified","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"}},"official":null}}},{"leaderboard":"/sota/scene-text-recognition-on-svtp","slug":"scene-text-recognition-on-svtp","dataset":"SVTP","dataset_url":"/dataset/svtp","rows_in_archive":17,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"DTrOCR 105M","paper_title":"DTrOCR: Decoder-only Transformer for Optical Character Recognition","paper_url":"/paper/dtrocr-decoder-only-transformer-for-optical","paper_date":"2023-08-30","arxiv_id":"2308.15996","code_links":[{"title":"arvindrajan92/DTrOCR","url":"https://github.com/arvindrajan92/DTrOCR"}],"syntology":null}},{"leaderboard":"/sota/scene-text-recognition-on-icdar-2003","slug":"scene-text-recognition-on-icdar-2003","dataset":"ICDAR 2003","dataset_url":"/dataset/icdar-2003","rows_in_archive":12,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Yet Another Text Recognizer","paper_title":"Why You Should Try the Real Data for the Scene Text Recognition","paper_url":"/paper/why-you-should-try-the-real-data-for-the","paper_date":"2021-07-29","arxiv_id":"2107.13938","code_links":[{"title":"openvinotoolkit/training_extensions","url":"https://github.com/openvinotoolkit/training_extensions"}],"syntology":null}},{"leaderboard":"/sota/scene-text-recognition-on-ic19-art","slug":"scene-text-recognition-on-ic19-art","dataset":"IC19-Art","dataset_url":null,"rows_in_archive":5,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"CLIP4STR-L (DataComp-1B)","paper_title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model","paper_url":"/paper/clip4str-a-simple-baseline-for-scene-text-1","paper_date":"2023-05-23","arxiv_id":"2305.14014","code_links":[{"title":"VamosC/CLIP4STR","url":"https://github.com/VamosC/CLIP4STR"}],"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"6 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; 3 where Syntology's instrument failed) · 4 unverified","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"}},"official":null}}},{"leaderboard":"/sota/scene-text-recognition-on-wost","slug":"scene-text-recognition-on-wost","dataset":"WOST","dataset_url":"/dataset/wost","rows_in_archive":5,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"CLIP4STR-H (DFN-5B)","paper_title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model","paper_url":"/paper/clip4str-a-simple-baseline-for-scene-text-1","paper_date":"2023-05-23","arxiv_id":"2305.14014","code_links":[{"title":"VamosC/CLIP4STR","url":"https://github.com/VamosC/CLIP4STR"}],"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"6 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; 3 where Syntology's instrument failed) · 4 unverified","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"}},"official":null}}},{"leaderboard":"/sota/scene-text-recognition-on-coco-text","slug":"scene-text-recognition-on-coco-text","dataset":"COCO-Text","dataset_url":"/dataset/coco-text","rows_in_archive":4,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"CLIP4STR-L","paper_title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model","paper_url":"/paper/clip4str-a-simple-baseline-for-scene-text-1","paper_date":"2023-05-23","arxiv_id":"2305.14014","code_links":[{"title":"VamosC/CLIP4STR","url":"https://github.com/VamosC/CLIP4STR"}],"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"6 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; 3 where Syntology's instrument failed) · 4 unverified","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"}},"official":null}}},{"leaderboard":"/sota/scene-text-recognition-on-host","slug":"scene-text-recognition-on-host","dataset":"HOST","dataset_url":"/dataset/host","rows_in_archive":3,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"CLIP4STR-L","paper_title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model","paper_url":"/paper/clip4str-a-simple-baseline-for-scene-text-1","paper_date":"2023-05-23","arxiv_id":"2305.14014","code_links":[{"title":"VamosC/CLIP4STR","url":"https://github.com/VamosC/CLIP4STR"}],"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"6 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; 3 where Syntology's instrument failed) · 4 unverified","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"}},"official":null}}},{"leaderboard":"/sota/scene-text-recognition-on-uber-text","slug":"scene-text-recognition-on-uber-text","dataset":"Uber-Text","dataset_url":null,"rows_in_archive":3,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"CLIP4STR-L (DataComp-1B)","paper_title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model","paper_url":"/paper/clip4str-a-simple-baseline-for-scene-text-1","paper_date":"2023-05-23","arxiv_id":"2305.14014","code_links":[{"title":"VamosC/CLIP4STR","url":"https://github.com/VamosC/CLIP4STR"}],"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"6 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; 3 where Syntology's instrument failed) · 4 unverified","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"}},"official":null}}},{"leaderboard":"/sota/scene-text-recognition-on-msda","slug":"scene-text-recognition-on-msda","dataset":"MSDA","dataset_url":"/dataset/msda","rows_in_archive":2,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"MetaSelf-Learning","paper_title":"Meta Self-Learning for Multi-Source Domain Adaptation: A Benchmark","paper_url":"/paper/meta-self-learning-for-multi-source-domain","paper_date":"2021-08-24","arxiv_id":"2108.10840","code_links":[{"title":"bupt-ai-cz/Meta-SelfLearning","url":"https://github.com/bupt-ai-cz/Meta-SelfLearning"}],"syntology":null}},{"leaderboard":"/sota/scene-text-recognition-on-ic13","slug":"scene-text-recognition-on-ic13","dataset":"IC13","dataset_url":"/dataset/ic13","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ABINet-LV+TPS++","paper_title":"TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition","paper_url":"/paper/tps-attention-enhanced-thin-plate-spline-for","paper_date":"2023-05-09","arxiv_id":"2305.05322","code_links":[{"title":"simplify23/tps_pp","url":"https://github.com/simplify23/tps_pp"}],"syntology":null}},{"leaderboard":"/sota/scene-text-recognition-on-svt-p","slug":"scene-text-recognition-on-svt-p","dataset":"SVT-P","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ABINet-LV+TPS++","paper_title":"TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition","paper_url":"/paper/tps-attention-enhanced-thin-plate-spline-for","paper_date":"2023-05-09","arxiv_id":"2305.05322","code_links":[{"title":"simplify23/tps_pp","url":"https://github.com/simplify23/tps_pp"}],"syntology":null}}],"datasets":[{"url":"/dataset/icdar-2013","name":"ICDAR 2013","full_name":"","num_papers_in_archive":246},{"url":"/dataset/coco-text","name":"COCO-Text","full_name":"COCO-Text","num_papers_in_archive":89},{"url":"/dataset/icdar-2003","name":"ICDAR 2003","full_name":"ICDAR 2003","num_papers_in_archive":53},{"url":"/dataset/textocr","name":"TextOCR","full_name":"","num_papers_in_archive":37},{"url":"/dataset/svt","name":"SVT","full_name":"Street View Text Dataset","num_papers_in_archive":35},{"url":"/dataset/rctw-17","name":"RCTW-17","full_name":"Reading Chinese Text in the Wild","num_papers_in_archive":20},{"url":"/dataset/host","name":"HOST","full_name":"","num_papers_in_archive":18},{"url":"/dataset/cute80","name":"CUTE80","full_name":"","num_papers_in_archive":17},{"url":"/dataset/wost","name":"WOST","full_name":"","num_papers_in_archive":17},{"url":"/dataset/ufpr-alpr","name":"UFPR-ALPR","full_name":"","num_papers_in_archive":15},{"url":"/dataset/iiit5k","name":"IIIT5k","full_name":"","num_papers_in_archive":14},{"url":"/dataset/svtp","name":"SVTP","full_name":"","num_papers_in_archive":14},{"url":"/dataset/gsl","name":"GSL","full_name":"Greek Sign Language","num_papers_in_archive":11},{"url":"/dataset/rodosol-alpr","name":"RodoSol-ALPR","full_name":"","num_papers_in_archive":8},{"url":"/dataset/ssig-segplate","name":"SSIG-SegPlate","full_name":"","num_papers_in_archive":8},{"url":"/dataset/iiit-ilst","name":"IIIT-ILST","full_name":"","num_papers_in_archive":6},{"url":"/dataset/mle2e","name":"MLe2e","full_name":"","num_papers_in_archive":6},{"url":"/dataset/chineselp","name":"ChineseLP","full_name":"","num_papers_in_archive":4},{"url":"/dataset/vehicle-rear","name":"Vehicle-Rear","full_name":"","num_papers_in_archive":3},{"url":"/dataset/msda","name":"MSDA","full_name":"Multi-source domain adaptation dataset for text recognition","num_papers_in_archive":2},{"url":"/dataset/mtst","name":"MTST","full_name":"Mobile Turkish Scene Text","num_papers_in_archive":2},{"url":"/dataset/ufpr-amr-dataset","name":"UFPR-AMR","full_name":"","num_papers_in_archive":2},{"url":"/dataset/copel-amr-dataset","name":"Copel-AMR","full_name":"","num_papers_in_archive":1},{"url":"/dataset/ic13","name":"IC13","full_name":"","num_papers_in_archive":1},{"url":"/dataset/utrset-real","name":"UTRSet-Real","full_name":"","num_papers_in_archive":1},{"url":"/dataset/utrset-synth","name":"UTRSet-Synth","full_name":"","num_papers_in_archive":1},{"url":"/dataset/benchmarking-chinese-text-recognition-1","name":"Benchmarking-Chinese-Text-Recognition","full_name":"","num_papers_in_archive":0},{"url":"/dataset/thanh","name":"SignboardText","full_name":"","num_papers_in_archive":0},{"url":"/dataset/ts-tr","name":"TS-TR","full_name":"Turkish Scene Text Recognition Dataset","num_papers_in_archive":0}],"subtasks":[{"url":"/task/jersey-number-recognition","name":"Jersey Number Recognition"}],"parent_tasks":[{"url":"/task/scene-parsing","name":"Scene Parsing"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":3,"rows_per_page":100,"shown":100,"of":269,"of_with_code":146,"tagged_in_all":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"},"items":[{"url":"/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","repositories_listed":85,"syntology":{"n":81,"n_ran":66,"n_constructed":0,"n_ran_checked":49,"n_instrument":17,"n_unverified":15,"n_honours":1,"n_violates":1,"n_no_contract":47,"n_pointer_only":17,"phrase":"66 ran (of which 0 constructed an object rather than computing a result; 49 with no instrument failure: 1 honoured, 1 violated, 47 with no contract checked; 17 where Syntology's instrument failed) · 15 unverified","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"}},"official":null}},{"url":"/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","repositories_listed":13,"syntology":{"n":19,"n_ran":17,"n_constructed":0,"n_ran_checked":17,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":17,"n_pointer_only":0,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","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"}},"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"]}}},{"url":"/paper/trocr-transformer-based-optical-character","slug":"trocr-transformer-based-optical-character","title":"TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models","date":"2021-09-21","arxiv_id":"2109.10282","repositories_listed":8,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/trocr-transformer-based-optical-character#ran","syntology_url":"https://syntology.ai/paper/2109.10282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.10282"}},"official":{"repos":["microsoft/unilm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/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","repositories_listed":8,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/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"}},"official":null}},{"url":"/paper/master-multi-aspect-non-local-network-for","slug":"master-multi-aspect-non-local-network-for","title":"MASTER: Multi-Aspect Non-local Network for Scene Text Recognition","date":"2019-10-07","arxiv_id":"1910.02562","repositories_listed":7,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/master-multi-aspect-non-local-network-for#ran","syntology_url":"https://syntology.ai/paper/1910.02562","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.02562"}},"official":{"repos":["jiangxiluning/MASTER-TF","wenwenyu/MASTER-pytorch"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/a-multi-object-rectified-attention-network","slug":"a-multi-object-rectified-attention-network","title":"A Multi-Object Rectified Attention Network for Scene Text Recognition","date":"2019-01-10","arxiv_id":"1901.03003","repositories_listed":7,"syntology":null},{"url":"/paper/fots-fast-oriented-text-spotting-with-a","slug":"fots-fast-oriented-text-spotting-with-a","title":"FOTS: Fast Oriented Text Spotting with a Unified Network","date":"2018-01-05","arxiv_id":"1801.01671","repositories_listed":7,"syntology":null},{"url":"/paper/from-two-to-one-a-new-scene-text-recognizer","slug":"from-two-to-one-a-new-scene-text-recognizer","title":"From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network","date":"2021-08-22","arxiv_id":"2108.09661","repositories_listed":5,"syntology":null},{"url":"/paper/robustscanner-dynamically-enhancing","slug":"robustscanner-dynamically-enhancing","title":"RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition","date":"2020-07-15","arxiv_id":"2007.07542","repositories_listed":5,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":2,"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, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/robustscanner-dynamically-enhancing#ran","syntology_url":"https://syntology.ai/paper/2007.07542","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.07542"}},"official":{"repos":["open-mmlab/mmocr"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/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","repositories_listed":5,"syntology":null},{"url":"/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","repositories_listed":5,"syntology":null},{"url":"/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","repositories_listed":4,"syntology":null},{"url":"/paper/primitive-representation-learning-for-scene","slug":"primitive-representation-learning-for-scene","title":"Primitive Representation Learning for Scene Text Recognition","date":"2021-05-10","arxiv_id":"2105.04286","repositories_listed":4,"syntology":null},{"url":"/paper/read-like-humans-autonomous-bidirectional-and","slug":"read-like-humans-autonomous-bidirectional-and","title":"Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition","date":"2021-03-11","arxiv_id":"2103.06495","repositories_listed":4,"syntology":{"n":28,"n_ran":18,"n_constructed":11,"n_ran_checked":13,"n_instrument":5,"n_unverified":10,"n_honours":0,"n_violates":1,"n_no_contract":12,"n_pointer_only":18,"phrase":"18 ran (of which 11 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 1 violated, 12 with no contract checked; 5 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/read-like-humans-autonomous-bidirectional-and#ran","syntology_url":"https://syntology.ai/paper/2103.06495","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.06495"}},"official":{"repos":["FangShancheng/ABINet"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":8,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/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,"repositories_listed":4,"syntology":null},{"url":"/paper/nrtr-a-no-recurrence-sequence-to-sequence","slug":"nrtr-a-no-recurrence-sequence-to-sequence","title":"NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition","date":"2018-06-04","arxiv_id":"1806.00926","repositories_listed":4,"syntology":null},{"url":"/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","repositories_listed":3,"syntology":null},{"url":"/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","repositories_listed":3,"syntology":null},{"url":"/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","repositories_listed":3,"syntology":null},{"url":"/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","repositories_listed":3,"syntology":null},{"url":"/paper/spin-structure-preserving-inner-offset","slug":"spin-structure-preserving-inner-offset","title":"SPIN: Structure-Preserving Inner Offset Network for Scene Text Recognition","date":"2020-05-27","arxiv_id":"2005.13117","repositories_listed":3,"syntology":null},{"url":"/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","repositories_listed":3,"syntology":null},{"url":"/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","repositories_listed":3,"syntology":null},{"url":"/paper/unrealtext-synthesizing-realistic-scene-text","slug":"unrealtext-synthesizing-realistic-scene-text","title":"UnrealText: Synthesizing Realistic Scene Text Images from the Unreal World","date":"2020-03-24","arxiv_id":"2003.10608","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/unrealtext-synthesizing-realistic-scene-text#ran","syntology_url":"https://syntology.ai/paper/2003.10608","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.10608"}},"official":{"repos":["Jyouhou/UnrealText","Jyouhou/Case-Sensitive-Scene-Text-Recognition-Datasets"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/visual-re-ranking-with-natural-language","slug":"visual-re-ranking-with-natural-language","title":"Visual Re-ranking with Natural Language Understanding for Text Spotting","date":"2018-10-29","arxiv_id":"1810.12738","repositories_listed":3,"syntology":null},{"url":"/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","repositories_listed":3,"syntology":null},{"url":"/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","repositories_listed":3,"syntology":null},{"url":"/paper/class-aware-mask-guided-feature-refinement","slug":"class-aware-mask-guided-feature-refinement","title":"Class-Aware Mask-Guided Feature Refinement for Scene Text Recognition","date":"2024-02-21","arxiv_id":"2402.13643","repositories_listed":2,"syntology":null},{"url":"/paper/text-image-inpainting-via-global-structure","slug":"text-image-inpainting-via-global-structure","title":"Text Image Inpainting via Global Structure-Guided Diffusion Models","date":"2024-01-26","arxiv_id":"2401.14832","repositories_listed":2,"syntology":{"n":11,"n_ran":4,"n_constructed":3,"n_ran_checked":4,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/text-image-inpainting-via-global-structure#ran","syntology_url":"https://syntology.ai/paper/2401.14832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.14832"}},"official":{"repos":["blackprotoss/gsdm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-granularity-prediction-with-learnable","slug":"multi-granularity-prediction-with-learnable","title":"Multi-Granularity Prediction with Learnable Fusion for Scene Text Recognition","date":"2023-07-25","arxiv_id":"2307.13244","repositories_listed":2,"syntology":null},{"url":"/paper/context-perception-parallel-decoder-for-scene","slug":"context-perception-parallel-decoder-for-scene","title":"Context Perception Parallel Decoder for Scene Text Recognition","date":"2023-07-23","arxiv_id":"2307.12270","repositories_listed":2,"syntology":null},{"url":"/paper/revisiting-scene-text-recognition-a-data","slug":"revisiting-scene-text-recognition-a-data","title":"Revisiting Scene Text Recognition: A Data Perspective","date":"2023-07-17","arxiv_id":"2307.08723","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/revisiting-scene-text-recognition-a-data#ran","syntology_url":"https://syntology.ai/paper/2307.08723","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.08723"}},"official":{"repos":["Mountchicken/Union14M"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/linguistic-more-taking-a-further-step-toward","slug":"linguistic-more-taking-a-further-step-toward","title":"Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognition","date":"2023-05-09","arxiv_id":"2305.05140","repositories_listed":2,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/linguistic-more-taking-a-further-step-toward#ran","syntology_url":"https://syntology.ai/paper/2305.05140","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.05140"}},"official":{"repos":["CyrilSterling/LPV"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/levenshtein-ocr","slug":"levenshtein-ocr","title":"Levenshtein OCR","date":"2022-09-08","arxiv_id":"2209.03594","repositories_listed":2,"syntology":null},{"url":"/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","repositories_listed":2,"syntology":{"n":8,"n_ran":5,"n_constructed":5,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 5 samples that ran constructed an object rather than computing a result","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"}},"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"]}}},{"url":"/paper/multimodal-semi-supervised-learning-for-text","slug":"multimodal-semi-supervised-learning-for-text","title":"Multimodal Semi-Supervised Learning for Text Recognition","date":"2022-05-08","arxiv_id":"2205.03873","repositories_listed":2,"syntology":null},{"url":"/paper/training-protocol-matters-towards-accurate","slug":"training-protocol-matters-towards-accurate","title":"Training Protocol Matters: Towards Accurate Scene Text Recognition via Training Protocol Searching","date":"2022-03-13","arxiv_id":"2203.06696","repositories_listed":2,"syntology":null},{"url":"/paper/text-gestalt-stroke-aware-scene-text-image","slug":"text-gestalt-stroke-aware-scene-text-image","title":"Text Gestalt: Stroke-Aware Scene Text Image Super-Resolution","date":"2021-12-13","arxiv_id":"2112.08171","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/text-gestalt-stroke-aware-scene-text-image#ran","syntology_url":"https://syntology.ai/paper/2112.08171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.08171"}},"official":{"repos":["fudanvi/fudanocr"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/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,"repositories_listed":2,"syntology":null},{"url":"/paper/arabic-scene-text-recognition-in-the-deep","slug":"arabic-scene-text-recognition-in-the-deep","title":"Arabic Scene Text Recognition in the Deep Learning Era: Analysis on A Novel Dataset","date":"2021-07-27","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/scatter-selective-context-attentional-scene","slug":"scatter-selective-context-attentional-scene","title":"SCATTER: Selective Context Attentional Scene Text Recognizer","date":"2020-03-25","arxiv_id":"2003.11288","repositories_listed":2,"syntology":null},{"url":"/paper/efficient-backbone-search-for-scene-text","slug":"efficient-backbone-search-for-scene-text","title":"AutoSTR: Efficient Backbone Search for Scene Text Recognition","date":"2020-03-14","arxiv_id":"2003.06567","repositories_listed":2,"syntology":null},{"url":"/paper/a-feasible-framework-for-arbitrary-shaped","slug":"a-feasible-framework-for-arbitrary-shaped","title":"A Feasible Framework for Arbitrary-Shaped Scene Text Recognition","date":"2019-12-10","arxiv_id":"1912.04561","repositories_listed":2,"syntology":null},{"url":"/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","repositories_listed":2,"syntology":null},{"url":"/paper/pyramid-mask-text-detector","slug":"pyramid-mask-text-detector","title":"Pyramid Mask Text Detector","date":"2019-03-28","arxiv_id":"1903.11800","repositories_listed":2,"syntology":null},{"url":"/paper/pedestrian-synthesis-gan-generating","slug":"pedestrian-synthesis-gan-generating","title":"Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond","date":"2018-04-05","arxiv_id":"1804.02047","repositories_listed":2,"syntology":null},{"url":"/paper/see-towards-semi-supervised-end-to-end-scene","slug":"see-towards-semi-supervised-end-to-end-scene","title":"SEE: Towards Semi-Supervised End-to-End Scene Text Recognition","date":"2017-12-14","arxiv_id":"1712.05404","repositories_listed":2,"syntology":null},{"url":"/paper/linguistics-aware-masked-image-modeling-for","slug":"linguistics-aware-masked-image-modeling-for","title":"Linguistics-aware Masked Image Modeling for Self-supervised Scene Text Recognition","date":"2025-03-24","arxiv_id":"2503.18746","repositories_listed":1,"syntology":{"n":6,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"phrase":"1 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; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/linguistics-aware-masked-image-modeling-for#ran","syntology_url":"https://syntology.ai/paper/2503.18746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.18746"}},"official":{"repos":["zhangyifei01/LMIM"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/eventstr-a-benchmark-dataset-and-baselines","slug":"eventstr-a-benchmark-dataset-and-baselines","title":"EventSTR: A Benchmark Dataset and Baselines for Event Stream based Scene Text Recognition","date":"2025-02-13","arxiv_id":"2502.09020","repositories_listed":1,"syntology":null},{"url":"/paper/ocean-ocr-towards-general-ocr-application-via","slug":"ocean-ocr-towards-general-ocr-application-via","title":"Ocean-OCR: Towards General OCR Application via a Vision-Language Model","date":"2025-01-26","arxiv_id":"2501.15558","repositories_listed":1,"syntology":null},{"url":"/paper/textssr-diffusion-based-data-synthesis-for","slug":"textssr-diffusion-based-data-synthesis-for","title":"TextSSR: Diffusion-based Data Synthesis for Scene Text Recognition","date":"2024-12-02","arxiv_id":"2412.01137","repositories_listed":1,"syntology":null},{"url":"/paper/svtrv2-ctc-beats-encoder-decoder-models-in","slug":"svtrv2-ctc-beats-encoder-decoder-models-in","title":"SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition","date":"2024-11-24","arxiv_id":"2411.15858","repositories_listed":1,"syntology":null},{"url":"/paper/boosting-semi-supervised-scene-text","slug":"boosting-semi-supervised-scene-text","title":"Boosting Semi-Supervised Scene Text Recognition via Viewing and Summarizing","date":"2024-11-23","arxiv_id":"2411.15585","repositories_listed":1,"syntology":null},{"url":"/paper/relational-contrastive-learning-and-masked","slug":"relational-contrastive-learning-and-masked","title":"Relational Contrastive Learning and Masked Image Modeling for Scene Text Recognition","date":"2024-11-18","arxiv_id":"2411.11219","repositories_listed":1,"syntology":null},{"url":"/paper/mctbench-multimodal-cognition-towards-text","slug":"mctbench-multimodal-cognition-towards-text","title":"MCTBench: Multimodal Cognition towards Text-Rich Visual Scenes Benchmark","date":"2024-10-15","arxiv_id":"2410.11538","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mctbench-multimodal-cognition-towards-text#ran","syntology_url":"https://syntology.ai/paper/2410.11538","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.11538"}},"official":{"repos":["xfey/mctbench"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/stratified-domain-adaptation-a-progressive","slug":"stratified-domain-adaptation-a-progressive","title":"Stratified Domain Adaptation: A Progressive Self-Training Approach for Scene Text Recognition","date":"2024-10-13","arxiv_id":"2410.09913","repositories_listed":1,"syntology":null},{"url":"/paper/scene-text-grounding-for-text-based-video","slug":"scene-text-grounding-for-text-based-video","title":"Scene-Text Grounding for Text-Based Video Question Answering","date":"2024-09-22","arxiv_id":"2409.14319","repositories_listed":1,"syntology":null},{"url":"/paper/platypus-a-generalized-specialist-model-for","slug":"platypus-a-generalized-specialist-model-for","title":"Platypus: A Generalized Specialist Model for Reading Text in Various Forms","date":"2024-08-27","arxiv_id":"2408.14805","repositories_listed":1,"syntology":null},{"url":"/paper/decoder-pre-training-with-only-text-for-scene","slug":"decoder-pre-training-with-only-text-for-scene","title":"Decoder Pre-Training with only Text for Scene Text Recognition","date":"2024-08-11","arxiv_id":"2408.05706","repositories_listed":1,"syntology":null},{"url":"/paper/moose-multi-orientation-sharing-experts-for","slug":"moose-multi-orientation-sharing-experts-for","title":"MOoSE: Multi-Orientation Sharing Experts for Open-set Scene Text Recognition","date":"2024-07-26","arxiv_id":"2407.18616","repositories_listed":1,"syntology":null},{"url":"/paper/out-of-length-text-recognition-with-sub","slug":"out-of-length-text-recognition-with-sub","title":"Out of Length Text Recognition with Sub-String Matching","date":"2024-07-17","arxiv_id":"2407.12317","repositories_listed":1,"syntology":null},{"url":"/paper/focus-on-the-whole-character-discriminative","slug":"focus-on-the-whole-character-discriminative","title":"Focus on the Whole Character: Discriminative Character Modeling for Scene Text Recognition","date":"2024-07-08","arxiv_id":"2407.05562","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/focus-on-the-whole-character-discriminative#ran","syntology_url":"https://syntology.ai/paper/2407.05562","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.05562"}},"official":{"repos":["bang123-box/cfe"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/a-general-framework-for-jersey-number","slug":"a-general-framework-for-jersey-number","title":"A General Framework for Jersey Number Recognition in Sports Video","date":"2024-05-22","arxiv_id":"2405.13896","repositories_listed":1,"syntology":null},{"url":"/paper/the-first-swahili-language-scene-text","slug":"the-first-swahili-language-scene-text","title":"The First Swahili Language Scene Text Detection and Recognition Dataset","date":"2024-05-19","arxiv_id":"2405.11437","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-pre-training-with-symmetric","slug":"self-supervised-pre-training-with-symmetric","title":"Self-Supervised Pre-training with Symmetric Superimposition Modeling for Scene Text Recognition","date":"2024-05-09","arxiv_id":"2405.05841","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":5,"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/self-supervised-pre-training-with-symmetric#ran","syntology_url":"https://syntology.ai/paper/2405.05841","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.05841"}},"official":{"repos":["faltingsa/ssm"],"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/efficient-scene-text-image-super-resolution","slug":"efficient-scene-text-image-super-resolution","title":"Efficient scene text image super-resolution with semantic guidance","date":"2024-03-20","arxiv_id":"2403.13330","repositories_listed":1,"syntology":null},{"url":"/paper/instruction-guided-scene-text-recognition","slug":"instruction-guided-scene-text-recognition","title":"Instruction-Guided Scene Text Recognition","date":"2024-01-31","arxiv_id":"2401.17851","repositories_listed":1,"syntology":null},{"url":"/paper/viptr-a-vision-permutable-extractor-for-fast","slug":"viptr-a-vision-permutable-extractor-for-fast","title":"SVIPTR: Fast and Efficient Scene Text Recognition with Vision Permutable Extractor","date":"2024-01-18","arxiv_id":"2401.10110","repositories_listed":1,"syntology":null},{"url":"/paper/an-empirical-study-of-scaling-law-for-scene","slug":"an-empirical-study-of-scaling-law-for-scene","title":"An Empirical Study of Scaling Law for Scene Text Recognition","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/ipad-iterative-parallel-and-diffusion-based","slug":"ipad-iterative-parallel-and-diffusion-based","title":"IPAD: Iterative, Parallel, and Diffusion-based Network for Scene Text Recognition","date":"2023-12-19","arxiv_id":"2312.11923","repositories_listed":1,"syntology":null},{"url":"/paper/cross-lingual-learning-in-multilingual-scene","slug":"cross-lingual-learning-in-multilingual-scene","title":"Cross-Lingual Learning in Multilingual Scene Text Recognition","date":"2023-12-17","arxiv_id":"2312.10806","repositories_listed":1,"syntology":null},{"url":"/paper/multi-modal-in-context-learning-makes-an-ego","slug":"multi-modal-in-context-learning-makes-an-ego","title":"Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer","date":"2023-11-22","arxiv_id":"2311.13120","repositories_listed":1,"syntology":null},{"url":"/paper/scene-text-image-super-resolution-based-on","slug":"scene-text-image-super-resolution-based-on","title":"Scene Text Image Super-resolution based on Text-conditional Diffusion Models","date":"2023-11-16","arxiv_id":"2311.09759","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/scene-text-image-super-resolution-based-on#ran","syntology_url":"https://syntology.ai/paper/2311.09759","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09759"}},"official":{"repos":["toyotainfotech/stisr-tcdm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/exploring-ocr-capabilities-of-gpt-4v-ision-a","slug":"exploring-ocr-capabilities-of-gpt-4v-ision-a","title":"Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth Evaluation","date":"2023-10-25","arxiv_id":"2310.16809","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/exploring-ocr-capabilities-of-gpt-4v-ision-a#ran","syntology_url":"https://syntology.ai/paper/2310.16809","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.16809"}},"official":{"repos":["scut-dlvclab/gpt-4v_ocr"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/docxchain-a-powerful-open-source-toolchain","slug":"docxchain-a-powerful-open-source-toolchain","title":"DocXChain: A Powerful Open-Source Toolchain for Document Parsing and Beyond","date":"2023-10-19","arxiv_id":"2310.12430","repositories_listed":1,"syntology":null},{"url":"/paper/scene-text-recognition-models-explainability","slug":"scene-text-recognition-models-explainability","title":"Scene Text Recognition Models Explainability Using Local Features","date":"2023-10-14","arxiv_id":"2310.09549","repositories_listed":1,"syntology":null},{"url":"/paper/symmetrical-linguistic-feature-distillation","slug":"symmetrical-linguistic-feature-distillation","title":"Symmetrical Linguistic Feature Distillation with CLIP for Scene Text Recognition","date":"2023-10-08","arxiv_id":"2310.04999","repositories_listed":1,"syntology":null},{"url":"/paper/towards-large-scale-building-attribute","slug":"towards-large-scale-building-attribute","title":"Towards Large-scale Building Attribute Mapping using Crowdsourced Images: Scene Text Recognition on Flickr and Problems to be Solved","date":"2023-09-14","arxiv_id":"2309.08042","repositories_listed":1,"syntology":null},{"url":"/paper/chinese-text-recognition-with-a-pre-trained","slug":"chinese-text-recognition-with-a-pre-trained","title":"Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning","date":"2023-09-03","arxiv_id":"2309.01083","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/chinese-text-recognition-with-a-pre-trained#ran","syntology_url":"https://syntology.ai/paper/2309.01083","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.01083"}},"official":{"repos":["fudanvi/fudanocr"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/orientation-independent-chinese-text","slug":"orientation-independent-chinese-text","title":"Orientation-Independent Chinese Text Recognition in Scene Images","date":"2023-09-03","arxiv_id":"2309.01081","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/lister-neighbor-decoding-for-length","slug":"lister-neighbor-decoding-for-length","title":"LISTER: Neighbor Decoding for Length-Insensitive Scene Text Recognition","date":"2023-08-24","arxiv_id":"2308.12774","repositories_listed":1,"syntology":null},{"url":"/paper/towards-scene-text-to-scene-text-translation","slug":"towards-scene-text-to-scene-text-translation","title":"Show Me the World in My Language: Establishing the First Baseline for Scene-Text to Scene-Text Translation","date":"2023-08-06","arxiv_id":"2308.03024","repositories_listed":1,"syntology":null},{"url":"/paper/relational-contrastive-learning-for-scene","slug":"relational-contrastive-learning-for-scene","title":"Relational Contrastive Learning for Scene Text Recognition","date":"2023-08-01","arxiv_id":"2308.00508","repositories_listed":1,"syntology":null},{"url":"/paper/towards-robust-scene-text-image-super","slug":"towards-robust-scene-text-image-super","title":"Towards Robust Scene Text Image Super-resolution via Explicit Location Enhancement","date":"2023-07-19","arxiv_id":"2307.09749","repositories_listed":1,"syntology":{"n":16,"n_ran":14,"n_constructed":0,"n_ran_checked":7,"n_instrument":7,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":6,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/towards-robust-scene-text-image-super#ran","syntology_url":"https://syntology.ai/paper/2307.09749","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09749"}},"official":{"repos":["csguoh/lemma"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/reading-between-the-lanes-text-videoqa-on-the","slug":"reading-between-the-lanes-text-videoqa-on-the","title":"Reading Between the Lanes: Text VideoQA on the Road","date":"2023-07-08","arxiv_id":"2307.03948","repositories_listed":1,"syntology":null},{"url":"/paper/looking-and-listening-audio-guided-text","slug":"looking-and-listening-audio-guided-text","title":"Looking and Listening: Audio Guided Text Recognition","date":"2023-06-06","arxiv_id":"2306.03482","repositories_listed":1,"syntology":null},{"url":"/paper/masked-and-permuted-implicit-context-learning","slug":"masked-and-permuted-implicit-context-learning","title":"Masked and Permuted Implicit Context Learning for Scene Text Recognition","date":"2023-05-25","arxiv_id":"2305.16172","repositories_listed":1,"syntology":null},{"url":"/paper/mrn-multiplexed-routing-network-for","slug":"mrn-multiplexed-routing-network-for","title":"MRN: Multiplexed Routing Network for Incremental Multilingual Text Recognition","date":"2023-05-24","arxiv_id":"2305.14758","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"6 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; 3 where Syntology's instrument failed) · 4 unverified","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"}},"official":null}},{"url":"/paper/tps-attention-enhanced-thin-plate-spline-for","slug":"tps-attention-enhanced-thin-plate-spline-for","title":"TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition","date":"2023-05-09","arxiv_id":"2305.05322","repositories_listed":1,"syntology":null},{"url":"/paper/geometric-perception-based-efficient-text","slug":"geometric-perception-based-efficient-text","title":"Geometric Perception based Efficient Text Recognition","date":"2023-02-08","arxiv_id":"2302.03873","repositories_listed":1,"syntology":null},{"url":"/paper/b-spline-texture-coefficients-estimator-for","slug":"b-spline-texture-coefficients-estimator-for","title":"B-Spline Texture Coefficients Estimator for Screen Content Image Super-Resolution","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/abinet-autonomous-bidirectional-and-iterative","slug":"abinet-autonomous-bidirectional-and-iterative","title":"ABINet++: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Spotting","date":"2022-11-19","arxiv_id":"2211.10578","repositories_listed":1,"syntology":null},{"url":"/paper/masked-vision-language-transformers-for-scene","slug":"masked-vision-language-transformers-for-scene","title":"Masked Vision-Language Transformers for Scene Text Recognition","date":"2022-11-09","arxiv_id":"2211.04785","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/toward-understanding-wordart-corner-guided","slug":"toward-understanding-wordart-corner-guided","title":"Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition","date":"2022-07-31","arxiv_id":"2208.00438","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/toward-understanding-wordart-corner-guided#ran","syntology_url":"https://syntology.ai/paper/2208.00438","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.00438"}},"official":{"repos":["xdxie/wordart"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/reading-and-writing-discriminative-and","slug":"reading-and-writing-discriminative-and","title":"Reading and Writing: Discriminative and Generative Modeling for Self-Supervised Text Recognition","date":"2022-07-01","arxiv_id":"2207.00193","repositories_listed":1,"syntology":null},{"url":"/paper/git-a-generative-image-to-text-transformer","slug":"git-a-generative-image-to-text-transformer","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","date":"2022-05-27","arxiv_id":"2205.14100","repositories_listed":1,"syntology":{"n":21,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/git-a-generative-image-to-text-transformer#ran","syntology_url":"https://syntology.ai/paper/2205.14100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14100"}},"official":{"repos":["microsoft/GenerativeImage2Text"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":7,"ran_from_kinds":["official"]}}}],"syntology_records":24,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"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)"},"since_archive_judged":{"papers":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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":[{"leaderboard":"/sota/scene-text-recognition-on-svt","since_archive":"/sota/scene-text-recognition-on-svt#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":27,"papers_where_code_ran_first_page":"/task/scene-text-recognition/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":3,"url":"/task/scene-text-recognition/papers/2","json":"/task/scene-text-recognition/papers/2.json","rows":100},{"order":"archive","page":3,"of":3,"url":"/task/scene-text-recognition/papers/3","json":"/task/scene-text-recognition/papers/3.json","rows":69},{"order":"ran","page":1,"of":1,"url":"/task/scene-text-recognition/papers/ran/1","json":"/task/scene-text-recognition/papers/ran/1.json","rows":27}],"description_links":{"kept":1,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper 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"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"8c779769a06cf5dac70c71e9f9e671e6cf216b6b1971c54c305dc6747ca27798","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}