{"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-detection","name":"Scene Text Detection","slug":"scene-text-detection","description_markdown":"**Scene Text Detection** is a computer vision task that involves automatically identifying and localizing text within natural images or videos. The goal of scene text detection is to develop algorithms that can robustly detect and and label text with bounding boxes in uncontrolled and complex environments, such as street signs, billboards, or license plates.\r\n\r\n\r\n<span class=\"description-source\">Source: [ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection ](https://arxiv.org/abs/2004.04940)</span>","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":213,"papers_with_code":98,"benchmarks":9,"benchmark_tables_in_archive":9,"benchmark_tables_shown":9,"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":17,"subtasks":2,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/scene-text-detection-on-icdar-2015","slug":"scene-text-detection-on-icdar-2015","dataset":"ICDAR 2015","dataset_url":"/dataset/icdar-2015","rows_in_archive":43,"metrics":["F-Measure","Precision","Recall","Accuracy","FPS"],"first_row_in_archive_order":{"model":"TextFuseNet (ResNeXt-101)","paper_title":"TextFuseNet: Scene Text Detection with Richer Fused Features","paper_url":"/paper/textfusenet-scene-text-detection-with-richer","paper_date":"2020-05-17","arxiv_id":null,"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"}],"syntology":null}},{"leaderboard":"/sota/scene-text-detection-on-total-text","slug":"scene-text-detection-on-total-text","dataset":"Total-Text","dataset_url":"/dataset/total-text","rows_in_archive":27,"metrics":["F-Measure","Precision","Recall","FPS"],"first_row_in_archive_order":{"model":"MixNet","paper_title":"MixNet: Toward Accurate Detection of Challenging Scene Text in the Wild","paper_url":"/paper/mixnet-toward-accurate-detection-of","paper_date":"2023-08-23","arxiv_id":"2308.12817","code_links":[{"title":"D641593/MixNet","url":"https://github.com/D641593/MixNet"}],"syntology":null}},{"leaderboard":"/sota/scene-text-detection-on-msra-td500","slug":"scene-text-detection-on-msra-td500","dataset":"MSRA-TD500","dataset_url":"/dataset/msra-td500","rows_in_archive":18,"metrics":["F-Measure","Precision","Recall","FPS"],"first_row_in_archive_order":{"model":"MixNet","paper_title":"MixNet: Toward Accurate Detection of Challenging Scene Text in the Wild","paper_url":"/paper/mixnet-toward-accurate-detection-of","paper_date":"2023-08-23","arxiv_id":"2308.12817","code_links":[{"title":"D641593/MixNet","url":"https://github.com/D641593/MixNet"}],"syntology":null}},{"leaderboard":"/sota/scene-text-detection-on-scut-ctw1500","slug":"scene-text-detection-on-scut-ctw1500","dataset":"SCUT-CTW1500","dataset_url":"/dataset/scut-ctw1500","rows_in_archive":17,"metrics":["F-Measure","Precision","Recall","FPS"],"first_row_in_archive_order":{"model":"MixNet","paper_title":"MixNet: Toward Accurate Detection of Challenging Scene Text in the Wild","paper_url":"/paper/mixnet-toward-accurate-detection-of","paper_date":"2023-08-23","arxiv_id":"2308.12817","code_links":[{"title":"D641593/MixNet","url":"https://github.com/D641593/MixNet"}],"syntology":null}},{"leaderboard":"/sota/scene-text-detection-on-icdar-2013","slug":"scene-text-detection-on-icdar-2013","dataset":"ICDAR 2013","dataset_url":"/dataset/icdar-2013","rows_in_archive":16,"metrics":["F-Measure","Precision","Recall","H-Mean"],"first_row_in_archive_order":{"model":"TextFuseNet (ResNeXt-101)","paper_title":"TextFuseNet: Scene Text Detection with Richer Fused Features","paper_url":"/paper/textfusenet-scene-text-detection-with-richer","paper_date":"2020-05-17","arxiv_id":null,"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"}],"syntology":null}},{"leaderboard":"/sota/scene-text-detection-on-icdar-2017-mlt-1","slug":"scene-text-detection-on-icdar-2017-mlt-1","dataset":"ICDAR 2017 MLT","dataset_url":"/dataset/icdar-2017","rows_in_archive":14,"metrics":["Precision","Recall","F-Measure","H-Mean"],"first_row_in_archive_order":{"model":"PMTD*","paper_title":"Pyramid Mask Text Detector","paper_url":"/paper/pyramid-mask-text-detector","paper_date":"2019-03-28","arxiv_id":"1903.11800","code_links":[{"title":"jjprincess/PMTD","url":"https://github.com/jjprincess/PMTD"},{"title":"anhnguyen9a7/pyramid-mask-and-plane-clustering-visualization","url":"https://github.com/anhnguyen9a7/pyramid-mask-and-plane-clustering-visualization"}],"syntology":null}},{"leaderboard":"/sota/scene-text-detection-on-coco-text","slug":"scene-text-detection-on-coco-text","dataset":"COCO-Text","dataset_url":"/dataset/coco-text","rows_in_archive":6,"metrics":["F-Measure","Precision","Recall"],"first_row_in_archive_order":{"model":"Corner-based Region Proposals","paper_title":"Detecting Multi-Oriented Text with Corner-based Region Proposals","paper_url":"/paper/detecting-multi-oriented-text-with-corner","paper_date":"2018-04-08","arxiv_id":"1804.02690","code_links":[{"title":"xhzdeng/crpn","url":"https://github.com/xhzdeng/crpn"}],"syntology":null}},{"leaderboard":"/sota/scene-text-detection-on-ic19-art","slug":"scene-text-detection-on-ic19-art","dataset":"IC19-Art","dataset_url":null,"rows_in_archive":4,"metrics":["H-Mean"],"first_row_in_archive_order":{"model":"MixNet","paper_title":"MixNet: Toward Accurate Detection of Challenging Scene Text in the Wild","paper_url":"/paper/mixnet-toward-accurate-detection-of","paper_date":"2023-08-23","arxiv_id":"2308.12817","code_links":[{"title":"D641593/MixNet","url":"https://github.com/D641593/MixNet"}],"syntology":null}},{"leaderboard":"/sota/scene-text-detection-on-ic19-rects","slug":"scene-text-detection-on-ic19-rects","dataset":"IC19-ReCTs","dataset_url":null,"rows_in_archive":1,"metrics":["F-Measure"],"first_row_in_archive_order":{"model":"BDN","paper_title":"Omnidirectional Scene Text Detection with Sequential-free Box Discretization","paper_url":"/paper/omnidirectional-scene-text-detection-with","paper_date":"2019-06-06","arxiv_id":"1906.02371","code_links":[{"title":"Yuliang-Liu/Box_Discretization_Network","url":"https://github.com/Yuliang-Liu/Box_Discretization_Network"}],"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"1 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/omnidirectional-scene-text-detection-with#ran","syntology_url":"https://syntology.ai/paper/1906.02371","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.02371"}},"official":{"repos":["Yuliang-Liu/Box_Discretization_Network"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}}}],"datasets":[{"url":"/dataset/icdar-2013","name":"ICDAR 2013","full_name":"","num_papers_in_archive":246},{"url":"/dataset/total-text","name":"Total-Text","full_name":"","num_papers_in_archive":156},{"url":"/dataset/msra-td500","name":"MSRA-TD500","full_name":"MSRA Text Detection 500 Database","num_papers_in_archive":124},{"url":"/dataset/coco-text","name":"COCO-Text","full_name":"COCO-Text","num_papers_in_archive":89},{"url":"/dataset/icdar-2015","name":"ICDAR 2015","full_name":"","num_papers_in_archive":52},{"url":"/dataset/scut-ctw1500","name":"SCUT-CTW1500","full_name":"","num_papers_in_archive":44},{"url":"/dataset/textocr","name":"TextOCR","full_name":"","num_papers_in_archive":37},{"url":"/dataset/rctw-17","name":"RCTW-17","full_name":"Reading Chinese Text in the Wild","num_papers_in_archive":20},{"url":"/dataset/icdar-2017","name":"ICDAR 2017","full_name":"ICDAR 2017","num_papers_in_archive":18},{"url":"/dataset/chinese-text-in-the-wild","name":"Chinese Text in the Wild","full_name":"","num_papers_in_archive":5},{"url":"/dataset/pku-license-plate-detection","name":"PKU (License Plate Detection)","full_name":"","num_papers_in_archive":2},{"url":"/dataset/shopsign","name":"ShopSign","full_name":"","num_papers_in_archive":2},{"url":"/dataset/urdudoc","name":"UrduDoc","full_name":"","num_papers_in_archive":1},{"url":"/dataset/cntd","name":"CNTD","full_name":"Chinese and Naxi text detection","num_papers_in_archive":0},{"url":"/dataset/indian-number-plates-dataset-vehicle-number","name":"Indian Number Plates Dataset | Vehicle Number Plates | English OCR Detection","full_name":"","num_papers_in_archive":0},{"url":"/dataset/media-text","name":"Media-Text","full_name":"MediaText: a media industry-based dataset for scene text detetcion","num_papers_in_archive":0},{"url":"/dataset/thanh","name":"SignboardText","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/curved-text-detection","name":"Curved Text Detection"},{"url":"/task/multi-oriented-scene-text-detection","name":"Multi-Oriented Scene Text Detection"}],"parent_tasks":[],"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":213,"of_with_code":98,"tagged_in_all":213,"counts":{"archive_papers_tagged":213,"with_a_code_link":98,"where_syntology_ran_a_sample":20,"not_listed_spam_title":0,"listed":213,"listed_where_code_ran":20,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":17,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":17,"listed_every_run_a_failure_of_syntologys_instrument":3,"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/east-an-efficient-and-accurate-scene-text","slug":"east-an-efficient-and-accurate-scene-text","title":"EAST: An Efficient and Accurate Scene Text Detector","date":"2017-04-11","arxiv_id":"1704.03155","repositories_listed":31,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"5 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; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/east-an-efficient-and-accurate-scene-text#ran","syntology_url":"https://syntology.ai/paper/1704.03155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.03155"}},"official":null}},{"url":"/paper/detecting-text-in-natural-image-with","slug":"detecting-text-in-natural-image-with","title":"Detecting Text in Natural Image with Connectionist Text Proposal Network","date":"2016-09-12","arxiv_id":"1609.03605","repositories_listed":27,"syntology":{"n":35,"n_ran":30,"n_constructed":0,"n_ran_checked":27,"n_instrument":3,"n_unverified":5,"n_honours":3,"n_violates":1,"n_no_contract":23,"n_pointer_only":2,"phrase":"30 ran (of which 0 constructed an object rather than computing a result; 27 with no instrument failure: 3 honoured, 1 violated, 23 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/detecting-text-in-natural-image-with#ran","syntology_url":"https://syntology.ai/paper/1609.03605","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1609.03605"}},"official":null}},{"url":"/paper/shape-robust-text-detection-with-progressive-1","slug":"shape-robust-text-detection-with-progressive-1","title":"Shape Robust Text Detection with Progressive Scale Expansion Network","date":"2019-03-28","arxiv_id":"1903.12473","repositories_listed":19,"syntology":null},{"url":"/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","repositories_listed":18,"syntology":{"n":40,"n_ran":25,"n_constructed":0,"n_ran_checked":20,"n_instrument":5,"n_unverified":15,"n_honours":1,"n_violates":0,"n_no_contract":19,"n_pointer_only":4,"phrase":"25 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 5 where Syntology's instrument failed) · 15 unverified","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"}},"official":null}},{"url":"/paper/abcnet-real-time-scene-text-spotting-with","slug":"abcnet-real-time-scene-text-spotting-with","title":"ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network","date":"2020-02-24","arxiv_id":"2002.10200","repositories_listed":16,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/abcnet-real-time-scene-text-spotting-with#ran","syntology_url":"https://syntology.ai/paper/2002.10200","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.10200"}},"official":{"repos":["aim-uofa/AdelaiDet"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/real-time-scene-text-detection-with","slug":"real-time-scene-text-detection-with","title":"Real-time Scene Text Detection with Differentiable Binarization","date":"2019-11-20","arxiv_id":"1911.08947","repositories_listed":15,"syntology":{"n":25,"n_ran":20,"n_constructed":0,"n_ran_checked":17,"n_instrument":3,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":17,"n_pointer_only":1,"phrase":"20 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; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/real-time-scene-text-detection-with#ran","syntology_url":"https://syntology.ai/paper/1911.08947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08947"}},"official":{"repos":["MhLiao/DB"],"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/fourier-contour-embedding-for-arbitrary","slug":"fourier-contour-embedding-for-arbitrary","title":"Fourier Contour Embedding for Arbitrary-Shaped Text Detection","date":"2021-04-21","arxiv_id":"2104.10442","repositories_listed":12,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/fourier-contour-embedding-for-arbitrary#ran","syntology_url":"https://syntology.ai/paper/2104.10442","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.10442"}},"official":null}},{"url":"/paper/shape-robust-text-detection-with-progressive","slug":"shape-robust-text-detection-with-progressive","title":"Shape Robust Text Detection with Progressive Scale Expansion Network","date":"2018-06-07","arxiv_id":"1806.02559","repositories_listed":9,"syntology":{"n":24,"n_ran":17,"n_constructed":0,"n_ran_checked":15,"n_instrument":2,"n_unverified":7,"n_honours":0,"n_violates":3,"n_no_contract":12,"n_pointer_only":3,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 3 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/shape-robust-text-detection-with-progressive#ran","syntology_url":"https://syntology.ai/paper/1806.02559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.02559"}},"official":{"repos":["whai362/PSENet"],"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/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/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,"repositories_listed":6,"syntology":null},{"url":"/paper/efficient-and-accurate-arbitrary-shaped-text","slug":"efficient-and-accurate-arbitrary-shaped-text","title":"Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network","date":"2019-08-16","arxiv_id":"1908.05900","repositories_listed":6,"syntology":{"n":28,"n_ran":17,"n_constructed":0,"n_ran_checked":13,"n_instrument":4,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":2,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 4 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/efficient-and-accurate-arbitrary-shaped-text#ran","syntology_url":"https://syntology.ai/paper/1908.05900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.05900"}},"official":{"repos":["whai362/pan_pp.pytorch"],"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/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","repositories_listed":6,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 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; 1 where Syntology's instrument failed) · 0 unverified","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"}},"official":null}},{"url":"/paper/real-time-scene-text-detection-with-1","slug":"real-time-scene-text-detection-with-1","title":"Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion","date":"2022-02-21","arxiv_id":"2202.10304","repositories_listed":5,"syntology":null},{"url":"/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","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/arbitrary-oriented-scene-text-detection-via","slug":"arbitrary-oriented-scene-text-detection-via","title":"Arbitrary-Oriented Scene Text Detection via Rotation Proposals","date":"2017-03-03","arxiv_id":"1703.01086","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/arbitrary-oriented-scene-text-detection-via#ran","syntology_url":"https://syntology.ai/paper/1703.01086","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.01086"}},"official":{"repos":["mjq11302010044/RRPN"],"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/coco-text-dataset-and-benchmark-for-text","slug":"coco-text-dataset-and-benchmark-for-text","title":"COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images","date":"2016-01-26","arxiv_id":"1601.07140","repositories_listed":4,"syntology":null},{"url":"/paper/towards-end-to-end-unified-scene-text","slug":"towards-end-to-end-unified-scene-text","title":"Towards End-to-End Unified Scene Text Detection and Layout Analysis","date":"2022-03-28","arxiv_id":"2203.15143","repositories_listed":3,"syntology":{"n":15,"n_ran":8,"n_constructed":7,"n_ran_checked":8,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":15,"phrase":"8 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/towards-end-to-end-unified-scene-text#ran","syntology_url":"https://syntology.ai/paper/2203.15143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15143"}},"official":{"repos":["google-research-datasets/hiertext","tensorflow/models"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"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/textsnake-a-flexible-representation-for","slug":"textsnake-a-flexible-representation-for","title":"TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes","date":"2018-07-04","arxiv_id":"1807.01544","repositories_listed":3,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/textsnake-a-flexible-representation-for#ran","syntology_url":"https://syntology.ai/paper/1807.01544","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.01544"}},"official":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/srformer-empowering-regression-based-text","slug":"srformer-empowering-regression-based-text","title":"SRFormer: Text Detection Transformer with Incorporated Segmentation and Regression","date":"2023-08-21","arxiv_id":"2308.10531","repositories_listed":2,"syntology":null},{"url":"/paper/efficient-and-accurate-scene-text-detection","slug":"efficient-and-accurate-scene-text-detection","title":"LRANet: Towards Accurate and Efficient Scene Text Detection with Low-Rank Approximation Network","date":"2023-06-27","arxiv_id":"2306.15142","repositories_listed":2,"syntology":{"n":19,"n_ran":19,"n_constructed":0,"n_ran_checked":19,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":19,"n_pointer_only":0,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/efficient-and-accurate-scene-text-detection#ran","syntology_url":"https://syntology.ai/paper/2306.15142","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.15142"}},"official":{"repos":["ychensu/lranet"],"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":["listed","official"]}}},{"url":"/paper/vision-language-pre-training-for-boosting","slug":"vision-language-pre-training-for-boosting","title":"Vision-Language Pre-Training for Boosting Scene Text Detectors","date":"2022-04-29","arxiv_id":"2204.13867","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":4,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/vision-language-pre-training-for-boosting#ran","syntology_url":"https://syntology.ai/paper/2204.13867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.13867"}},"official":{"repos":["AlibabaResearch/AdvancedLiterateMachinery"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/swintextspotter-scene-text-spotting-via","slug":"swintextspotter-scene-text-spotting-via","title":"SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition","date":"2022-03-19","arxiv_id":"2203.10209","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":2,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/swintextspotter-scene-text-spotting-via#ran","syntology_url":"https://syntology.ai/paper/2203.10209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.10209"}},"official":{"repos":["mxin262/swintextspotter"],"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/fast-searching-for-a-faster-arbitrarily","slug":"fast-searching-for-a-faster-arbitrarily","title":"FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation","date":"2021-11-03","arxiv_id":"2111.02394","repositories_listed":2,"syntology":null},{"url":"/paper/pgnet-real-time-arbitrarily-shaped-text","slug":"pgnet-real-time-arbitrarily-shaped-text","title":"PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network","date":"2021-04-12","arxiv_id":"2104.05458","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/shopsign-a-diverse-scene-text-dataset-of","slug":"shopsign-a-diverse-scene-text-dataset-of","title":"ShopSign: a Diverse Scene Text Dataset of Chinese Shop Signs in Street Views","date":"2019-03-25","arxiv_id":"1903.10412","repositories_listed":2,"syntology":null},{"url":"/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","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/the-devil-is-in-fine-tuning-and-long-tailed","slug":"the-devil-is-in-fine-tuning-and-long-tailed","title":"The Devil is in Fine-tuning and Long-tailed Problems:A New Benchmark for Scene Text Detection","date":"2025-05-21","arxiv_id":"2505.15649","repositories_listed":1,"syntology":null},{"url":"/paper/generalized-tampered-scene-text-detection-in","slug":"generalized-tampered-scene-text-detection-in","title":"Revisiting Tampered Scene Text Detection in the Era of Generative AI","date":"2024-07-31","arxiv_id":"2407.21422","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generalized-tampered-scene-text-detection-in#ran","syntology_url":"https://syntology.ai/paper/2407.21422","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.21422"}},"official":{"repos":["qcf-568/ostf"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dataset-and-benchmark-for-urdu-natural-scenes","slug":"dataset-and-benchmark-for-urdu-natural-scenes","title":"Dataset and Benchmark for Urdu Natural Scenes Text Detection, Recognition and Visual Question Answering","date":"2024-05-21","arxiv_id":"2405.12533","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/text-in-the-dark-extremely-low-light-text","slug":"text-in-the-dark-extremely-low-light-text","title":"Text in the Dark: Extremely Low-Light Text Image Enhancement","date":"2024-04-22","arxiv_id":"2404.14135","repositories_listed":1,"syntology":null},{"url":"/paper/odm-a-text-image-further-alignment-pre","slug":"odm-a-text-image-further-alignment-pre","title":"ODM: A Text-Image Further Alignment Pre-training Approach for Scene Text Detection and Spotting","date":"2024-03-01","arxiv_id":"2403.00303","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-synthetic-and-real-worlds-for-pre","slug":"bridging-synthetic-and-real-worlds-for-pre","title":"Bridging Synthetic and Real Worlds for Pre-training Scene Text Detectors","date":"2023-12-08","arxiv_id":"2312.05286","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-scene-text-detectors-with-realistic","slug":"enhancing-scene-text-detectors-with-realistic","title":"Enhancing Scene Text Detectors with Realistic Text Image Synthesis Using Diffusion Models","date":"2023-11-28","arxiv_id":"2311.16555","repositories_listed":1,"syntology":null},{"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/harnessing-the-power-of-multi-lingual","slug":"harnessing-the-power-of-multi-lingual","title":"Harnessing the Power of Multi-Lingual Datasets for Pre-training: Towards Enhancing Text Spotting Performance","date":"2023-10-02","arxiv_id":"2310.00917","repositories_listed":1,"syntology":null},{"url":"/paper/step-towards-structured-scene-text-spotting","slug":"step-towards-structured-scene-text-spotting","title":"STEP -- Towards Structured Scene-Text Spotting","date":"2023-09-05","arxiv_id":"2309.02356","repositories_listed":1,"syntology":null},{"url":"/paper/mixnet-toward-accurate-detection-of","slug":"mixnet-toward-accurate-detection-of","title":"MixNet: Toward Accurate Detection of Challenging Scene Text in the Wild","date":"2023-08-23","arxiv_id":"2308.12817","repositories_listed":1,"syntology":null},{"url":"/paper/turning-a-clip-model-into-a-scene-text-1","slug":"turning-a-clip-model-into-a-scene-text-1","title":"Turning a CLIP Model into a Scene Text Spotter","date":"2023-08-21","arxiv_id":"2308.10408","repositories_listed":1,"syntology":null},{"url":"/paper/viteraser-harnessing-the-power-of-vision","slug":"viteraser-harnessing-the-power-of-vision","title":"ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretraining","date":"2023-06-21","arxiv_id":"2306.12106","repositories_listed":1,"syntology":null},{"url":"/paper/deepsolo-let-transformer-decoder-with-1","slug":"deepsolo-let-transformer-decoder-with-1","title":"DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting","date":"2023-05-31","arxiv_id":"2305.19957","repositories_listed":1,"syntology":null},{"url":"/paper/turning-a-clip-model-into-a-scene-text","slug":"turning-a-clip-model-into-a-scene-text","title":"Turning a CLIP Model into a Scene Text Detector","date":"2023-02-28","arxiv_id":"2302.14338","repositories_listed":1,"syntology":null},{"url":"/paper/recurrent-contour-based-instance-segmentation","slug":"recurrent-contour-based-instance-segmentation","title":"Recurrent Generic Contour-based Instance Segmentation with Progressive Learning","date":"2023-01-21","arxiv_id":"2301.08898","repositories_listed":1,"syntology":null},{"url":"/paper/cbnet-a-plug-and-play-network-for","slug":"cbnet-a-plug-and-play-network-for","title":"CBNet: A Plug-and-Play Network for Segmentation-Based Scene Text Detection","date":"2022-12-05","arxiv_id":"2212.02340","repositories_listed":1,"syntology":null},{"url":"/paper/deepsolo-let-transformer-decoder-with","slug":"deepsolo-let-transformer-decoder-with","title":"DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting","date":"2022-11-19","arxiv_id":"2211.10772","repositories_listed":1,"syntology":null},{"url":"/paper/arbitrary-shape-text-detection-via","slug":"arbitrary-shape-text-detection-via","title":"Arbitrary Shape Text Detection via Segmentation with Probability Maps","date":"2022-08-26","arxiv_id":"2208.12419","repositories_listed":1,"syntology":null},{"url":"/paper/dptext-detr-towards-better-scene-text","slug":"dptext-detr-towards-better-scene-text","title":"DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer","date":"2022-07-10","arxiv_id":"2207.04491","repositories_listed":1,"syntology":null},{"url":"/paper/traffsign-multilingual-traffic-signboard-text","slug":"traffsign-multilingual-traffic-signboard-text","title":"TraffSign: Multilingual Traffic Signboard Text Detection and Recognition for Urdu and English","date":"2022-05-18","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/weakly-supervised-scene-text-detection-using","slug":"weakly-supervised-scene-text-detection-using","title":"Weakly Supervised Scene Text Detection using Deep Reinforcement Learning","date":"2022-01-13","arxiv_id":"2201.04866","repositories_listed":1,"syntology":null},{"url":"/paper/core-text-improving-scene-text-detection-with","slug":"core-text-improving-scene-text-detection-with","title":"CORE-Text: Improving Scene Text Detection with Contrastive Relational Reasoning","date":"2021-12-14","arxiv_id":"2112.07513","repositories_listed":1,"syntology":null},{"url":"/paper/industrial-scene-text-detection-with-refined","slug":"industrial-scene-text-detection-with-refined","title":"Industrial Scene Text Detection with Refined Feature-attentive Network","date":"2021-10-25","arxiv_id":"2110.12663","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/industrial-scene-text-detection-with-refined#ran","syntology_url":"https://syntology.ai/paper/2110.12663","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.12663"}},"official":{"repos":["tongkunguan/rfn"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/tpsnet-thin-plate-spline-representation-for","slug":"tpsnet-thin-plate-spline-representation-for","title":"TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representation","date":"2021-10-25","arxiv_id":"2110.12826","repositories_listed":1,"syntology":null},{"url":"/paper/on-exploring-and-improving-robustness-of","slug":"on-exploring-and-improving-robustness-of","title":"On Exploring and Improving Robustness of Scene Text Detection Models","date":"2021-10-12","arxiv_id":"2110.05700","repositories_listed":1,"syntology":null},{"url":"/paper/i3cl-intra-and-inter-instance-collaborative","slug":"i3cl-intra-and-inter-instance-collaborative","title":"I3CL:Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detection","date":"2021-08-03","arxiv_id":"2108.01343","repositories_listed":1,"syntology":null},{"url":"/paper/centripetaltext-an-efficient-text-instance","slug":"centripetaltext-an-efficient-text-instance","title":"CentripetalText: An Efficient Text Instance Representation for Scene Text Detection","date":"2021-07-13","arxiv_id":"2107.05945","repositories_listed":1,"syntology":null},{"url":"/paper/dictionary-guided-scene-text-recognition","slug":"dictionary-guided-scene-text-recognition","title":"Dictionary-Guided Scene Text Recognition","date":"2021-06-19","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/pan-towards-efficient-and-accurate-end-to-end","slug":"pan-towards-efficient-and-accurate-end-to-end","title":"PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text","date":"2021-05-02","arxiv_id":"2105.00405","repositories_listed":1,"syntology":null},{"url":"/paper/scene-text-retrieval-via-joint-text-detection","slug":"scene-text-retrieval-via-joint-text-detection","title":"Scene Text Retrieval via Joint Text Detection and Similarity Learning","date":"2021-04-04","arxiv_id":"2104.01552","repositories_listed":1,"syntology":null},{"url":"/paper/selftext-beyond-polygon-unconstrained-text","slug":"selftext-beyond-polygon-unconstrained-text","title":"Polygon-free: Unconstrained Scene Text Detection with Box Annotations","date":"2020-11-26","arxiv_id":"2011.13307","repositories_listed":1,"syntology":null},{"url":"/paper/rrpn-guidance-towards-more-accurate-scene","slug":"rrpn-guidance-towards-more-accurate-scene","title":"RRPN++: Guidance Towards More Accurate Scene Text Detection","date":"2020-09-28","arxiv_id":"2009.13118","repositories_listed":1,"syntology":null},{"url":"/paper/synthetic-to-real-unsupervised-domain-1","slug":"synthetic-to-real-unsupervised-domain-1","title":"Synthetic-to-Real Unsupervised Domain Adaptation for Scene Text Detection in the Wild","date":"2020-09-03","arxiv_id":"2009.01766","repositories_listed":1,"syntology":null},{"url":"/paper/textray-contour-based-geometric-modeling-for","slug":"textray-contour-based-geometric-modeling-for","title":"TextRay: Contour-based Geometric Modeling for Arbitrary-shaped Scene Text Detection","date":"2020-08-11","arxiv_id":"2008.04851","repositories_listed":1,"syntology":null},{"url":"/paper/text-detection-and-recognition-in-the-wild-a","slug":"text-detection-and-recognition-in-the-wild-a","title":"Text Detection and Recognition in the Wild: A Review","date":"2020-06-08","arxiv_id":"2006.04305","repositories_listed":1,"syntology":null},{"url":"/paper/r-3-reverse-retrieve-and-rank-for-sarcasm","slug":"r-3-reverse-retrieve-and-rank-for-sarcasm","title":"$R^3$: Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense Knowledge","date":"2020-04-28","arxiv_id":"2004.13248","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"7 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; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/r-3-reverse-retrieve-and-rank-for-sarcasm#ran","syntology_url":"https://syntology.ai/paper/2004.13248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.13248"}},"official":null}},{"url":"/paper/contournet-taking-a-further-step-toward","slug":"contournet-taking-a-further-step-toward","title":"ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection","date":"2020-04-10","arxiv_id":"2004.04940","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/contournet-taking-a-further-step-toward#ran","syntology_url":"https://syntology.ai/paper/2004.04940","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04940"}},"official":{"repos":["wangyuxin87/ContourNet"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/191209629","slug":"191209629","title":"Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text Detection","date":"2019-12-20","arxiv_id":"1912.09629","repositories_listed":1,"syntology":null},{"url":"/paper/gliding-vertex-on-the-horizontal-bounding-box","slug":"gliding-vertex-on-the-horizontal-bounding-box","title":"Gliding vertex on the horizontal bounding box for multi-oriented object detection","date":"2019-11-21","arxiv_id":"1911.09358","repositories_listed":1,"syntology":null},{"url":"/paper/convolutional-character-networks","slug":"convolutional-character-networks","title":"Convolutional Character Networks","date":"2019-10-17","arxiv_id":"1910.07954","repositories_listed":1,"syntology":null},{"url":"/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,"repositories_listed":1,"syntology":null},{"url":"/paper/stela-a-real-time-scene-text-detector-with","slug":"stela-a-real-time-scene-text-detector-with","title":"STELA: A Real-Time Scene Text Detector with Learned Anchor","date":"2019-09-17","arxiv_id":"1909.07549","repositories_listed":1,"syntology":null},{"url":"/paper/icdar2019-robust-reading-challenge-on","slug":"icdar2019-robust-reading-challenge-on","title":"ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT)","date":"2019-09-16","arxiv_id":"1909.07145","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/icdar2019-robust-reading-challenge-on#ran","syntology_url":"https://syntology.ai/paper/1909.07145","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.07145"}},"official":{"repos":["cs-chan/Total-Text-Dataset"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/geometry-normalization-networks-for-accurate","slug":"geometry-normalization-networks-for-accurate","title":"Geometry Normalization Networks for Accurate Scene Text Detection","date":"2019-09-02","arxiv_id":"1909.00794","repositories_listed":1,"syntology":null},{"url":"/paper/alchemy-techniques-for-rectification-based","slug":"alchemy-techniques-for-rectification-based","title":"Rethinking Irregular Scene Text Recognition","date":"2019-08-30","arxiv_id":"1908.11834","repositories_listed":1,"syntology":null},{"url":"/paper/a-single-shot-arbitrarily-shaped-text","slug":"a-single-shot-arbitrarily-shaped-text","title":"A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning","date":"2019-08-15","arxiv_id":"1908.05498","repositories_listed":1,"syntology":null},{"url":"/paper/synthtext3d-synthesizing-scene-text-images","slug":"synthtext3d-synthesizing-scene-text-images","title":"SynthText3D: Synthesizing Scene Text Images from 3D Virtual Worlds","date":"2019-07-13","arxiv_id":"1907.06007","repositories_listed":1,"syntology":null},{"url":"/paper/tedeval-a-fair-evaluation-metric-for-scene","slug":"tedeval-a-fair-evaluation-metric-for-scene","title":"TedEval: A Fair Evaluation Metric for Scene Text Detectors","date":"2019-07-02","arxiv_id":"1907.01227","repositories_listed":1,"syntology":null},{"url":"/paper/omnidirectional-scene-text-detection-with","slug":"omnidirectional-scene-text-detection-with","title":"Omnidirectional Scene Text Detection with Sequential-free Box Discretization","date":"2019-06-06","arxiv_id":"1906.02371","repositories_listed":1,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"1 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/omnidirectional-scene-text-detection-with#ran","syntology_url":"https://syntology.ai/paper/1906.02371","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.02371"}},"official":{"repos":["Yuliang-Liu/Box_Discretization_Network"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/selective-style-transfer-for-text","slug":"selective-style-transfer-for-text","title":"Selective Style Transfer for Text","date":"2019-06-04","arxiv_id":"1906.01466","repositories_listed":1,"syntology":null},{"url":"/paper/tightness-aware-evaluation-protocol-for-scene","slug":"tightness-aware-evaluation-protocol-for-scene","title":"Tightness-aware Evaluation Protocol for Scene Text Detection","date":"2019-03-27","arxiv_id":"1904.00813","repositories_listed":1,"syntology":null},{"url":"/paper/textfield-learning-a-deep-direction-field-for","slug":"textfield-learning-a-deep-direction-field-for","title":"TextField: Learning A Deep Direction Field for Irregular Scene Text Detection","date":"2018-12-04","arxiv_id":"1812.01393","repositories_listed":1,"syntology":null},{"url":"/paper/derpn-taking-a-further-step-toward-more","slug":"derpn-taking-a-further-step-toward-more","title":"DeRPN: Taking a further step toward more general object detection","date":"2018-11-16","arxiv_id":"1811.06700","repositories_listed":1,"syntology":null},{"url":"/paper/scene-text-detection-and-recognition-the-deep","slug":"scene-text-detection-and-recognition-the-deep","title":"Scene Text Detection and Recognition: The Deep Learning Era","date":"2018-11-10","arxiv_id":"1811.04256","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":"/paper/sliding-line-point-regression-for-shape","slug":"sliding-line-point-regression-for-shape","title":"Sliding Line Point Regression for Shape Robust Scene Text Detection","date":"2018-01-30","arxiv_id":"1801.09969","repositories_listed":1,"syntology":null},{"url":"/paper/detecting-curve-text-in-the-wild-new-dataset","slug":"detecting-curve-text-in-the-wild-new-dataset","title":"Detecting Curve Text in the Wild: New Dataset and New Solution","date":"2017-12-06","arxiv_id":"1712.02170","repositories_listed":1,"syntology":null},{"url":"/paper/total-text-a-comprehensive-dataset-for-scene","slug":"total-text-a-comprehensive-dataset-for-scene","title":"Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition","date":"2017-10-28","arxiv_id":"1710.10400","repositories_listed":1,"syntology":null},{"url":"/paper/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","repositories_listed":1,"syntology":null},{"url":"/paper/r2cnn-rotational-region-cnn-for-orientation","slug":"r2cnn-rotational-region-cnn-for-orientation","title":"R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection","date":"2017-06-29","arxiv_id":"1706.09579","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/r2cnn-rotational-region-cnn-for-orientation#ran","syntology_url":"https://syntology.ai/paper/1706.09579","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.09579"}},"official":null}},{"url":"/paper/multi-oriented-text-detection-with-fully","slug":"multi-oriented-text-detection-with-fully","title":"Multi-Oriented Text Detection with Fully Convolutional Networks","date":"2016-04-14","arxiv_id":"1604.04018","repositories_listed":1,"syntology":null},{"url":"/paper/accurate-text-localization-in-natural-image","slug":"accurate-text-localization-in-natural-image","title":"Accurate Text Localization in Natural Image with Cascaded Convolutional Text Network","date":"2016-03-31","arxiv_id":"1603.09423","repositories_listed":1,"syntology":null},{"url":null,"slug":"explicit-relational-reasoning-network-for","title":"Explicit Relational Reasoning Network for Scene Text Detection","date":"2024-12-19","arxiv_id":"2412.14692","repositories_listed":0,"syntology":null},{"url":null,"slug":"khmerst-a-low-resource-khmer-scene-text","title":"KhmerST: A Low-Resource Khmer Scene Text Detection and Recognition Benchmark","date":"2024-10-23","arxiv_id":"2410.18277","repositories_listed":0,"syntology":null}],"syntology_records":23,"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":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_where_code_ran":20,"papers_where_code_ran_first_page":"/task/scene-text-detection/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-detection/papers/2","json":"/task/scene-text-detection/papers/2.json","rows":100},{"order":"archive","page":3,"of":3,"url":"/task/scene-text-detection/papers/3","json":"/task/scene-text-detection/papers/3.json","rows":13},{"order":"ran","page":1,"of":1,"url":"/task/scene-text-detection/papers/ran/1","json":"/task/scene-text-detection/papers/ran/1.json","rows":20}],"description_links":{"kept":0,"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":"00019e01073f1c4e15dc4d4ccdca782b0fc1820034be0b5bb4d18a42c34dec5b","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}