{"url":"/sota/text-spotting-on-icdar-2015","task":{"name":"Text Spotting","url":"/task/text-spotting","note":null},"dataset":{"name":"ICDAR 2015","url":"/dataset/icdar-2015"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Scene Text Spotting is the combination of Scene Text Detection and Scene Text Recognition in an end-to-end manner.\r\nIt is the ability to read natural text in the wild.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["F-measure (%) - Strong Lexicon","F-measure (%) - Weak Lexicon","F-measure (%) - Generic Lexicon"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"F-measure (%) - Strong Lexicon":null,"F-measure (%) - Weak Lexicon":null,"F-measure (%) - Generic Lexicon":null}},"counts":{"rows":18,"rows_with_code":16,"rows_with_paper_page":18,"rows_dated":18,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"UNITS","metrics":{"F-measure (%) - Generic Lexicon":"80.3","F-measure (%) - Strong Lexicon":"89.0","F-measure (%) - Weak Lexicon":"84.1"},"uses_additional_data":false,"paper_date":"2023-04-07","paper":"/paper/towards-unified-scene-text-spotting-based-on","paper_url":"https://arxiv.org/abs/2304.03435v1","paper_title":"Towards Unified Scene Text Spotting based on Sequence Generation","code":"https://github.com/clovaai/units","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":1,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"DeepSolo (ViTAEv2-S, TextOCR)","metrics":{"F-measure (%) - Generic Lexicon":"79.5","F-measure (%) - Strong Lexicon":"88.1","F-measure (%) - Weak Lexicon":"83.9"},"uses_additional_data":false,"paper_date":"2022-11-19","paper":"/paper/deepsolo-let-transformer-decoder-with","paper_url":"https://arxiv.org/abs/2211.10772v4","paper_title":"DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting","code":"https://github.com/vitae-transformer/deepsolo","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"DeepSolo(ResNet-50, TextOCR)","metrics":{"F-measure (%) - Generic Lexicon":"79.1","F-measure (%) - Strong Lexicon":"88.0","F-measure (%) - Weak Lexicon":"83.5"},"uses_additional_data":false,"paper_date":"2022-11-19","paper":"/paper/deepsolo-let-transformer-decoder-with","paper_url":"https://arxiv.org/abs/2211.10772v4","paper_title":"DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting","code":"https://github.com/vitae-transformer/deepsolo","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"DeepSolo(ResNet-50)","metrics":{"F-measure (%) - Generic Lexicon":"76.9","F-measure (%) - Strong Lexicon":"86.8","F-measure (%) - Weak Lexicon":"81.9"},"uses_additional_data":false,"paper_date":"2022-11-19","paper":"/paper/deepsolo-let-transformer-decoder-with","paper_url":"https://arxiv.org/abs/2211.10772v4","paper_title":"DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting","code":"https://github.com/vitae-transformer/deepsolo","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"SRTS","metrics":{"F-measure (%) - Generic Lexicon":"74.5","F-measure (%) - Strong Lexicon":"85.6","F-measure (%) - Weak Lexicon":"81.7"},"uses_additional_data":false,"paper_date":"2022-07-15","paper":"/paper/decoupling-recognition-from-detection-single","paper_url":"https://arxiv.org/abs/2207.07253v4","paper_title":"Single Shot Self-Reliant Scene Text Spotter by Decoupled yet Collaborative Detection and Recognition","code":"https://github.com/wjj1106/SRSTS","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"TESTR","metrics":{"F-measure (%) - Generic Lexicon":"73.6","F-measure (%) - Strong Lexicon":"85.2","F-measure (%) - Weak Lexicon":"79.4"},"uses_additional_data":false,"paper_date":"2022-04-05","paper":"/paper/text-spotting-transformers","paper_url":"https://arxiv.org/abs/2204.01918v1","paper_title":"Text Spotting Transformers","code":"https://github.com/mlpc-ucsd/testr","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":5,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"A3S","metrics":{"F-measure (%) - Generic Lexicon":"79.6","F-measure (%) - Strong Lexicon":"84.8","F-measure (%) - Weak Lexicon":"83.7"},"uses_additional_data":false,"paper_date":"2023-02-21","paper":"/paper/a3s-adversarial-learning-of-semantic","paper_url":"https://arxiv.org/abs/2302.10641v1","paper_title":"A3S: Adversarial learning of semantic representations for Scene-Text Spotting","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"GLASS","metrics":{"F-measure (%) - Generic Lexicon":"76.3","F-measure (%) - Strong Lexicon":"84.7","F-measure (%) - Weak Lexicon":"80.1"},"uses_additional_data":false,"paper_date":"2022-08-05","paper":"/paper/glass-global-to-local-attention-for-scene","paper_url":"https://arxiv.org/abs/2208.03364v1","paper_title":"GLASS: Global to Local Attention for Scene-Text Spotting","code":"https://github.com/amazon-science/glass-text-spotting","n_code_links":2,"syntology":null},{"rank_in_archive_order":9,"model":"SwinTextSpotter","metrics":{"F-measure (%) - Generic Lexicon":"70.5","F-measure (%) - Strong Lexicon":"83.9","F-measure (%) - Weak Lexicon":"77.3"},"uses_additional_data":false,"paper_date":"2022-03-19","paper":"/paper/swintextspotter-scene-text-spotting-via","paper_url":"https://arxiv.org/abs/2203.10209v1","paper_title":"SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition","code":"https://github.com/mxin262/swintextspotter","n_code_links":2,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":10,"model":"FOTS","metrics":{"F-measure (%) - Generic Lexicon":"62.2","F-measure (%) - Strong Lexicon":"83.6","F-measure (%) - Weak Lexicon":"74.5"},"uses_additional_data":false,"paper_date":"2018-01-05","paper":"/paper/fots-fast-oriented-text-spotting-with-a","paper_url":"http://arxiv.org/abs/1801.01671v2","paper_title":"FOTS: Fast Oriented Text Spotting with a Unified Network","code":"https://github.com/jiangxiluning/FOTS.PyTorch","n_code_links":7,"syntology":null},{"rank_in_archive_order":11,"model":"PGNet","metrics":{"F-measure (%) - Generic Lexicon":"63.5","F-measure (%) - Strong Lexicon":"83.3","F-measure (%) - Weak Lexicon":"78.3"},"uses_additional_data":false,"paper_date":"2021-04-12","paper":"/paper/pgnet-real-time-arbitrarily-shaped-text","paper_url":"https://arxiv.org/abs/2104.05458v1","paper_title":"PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network","code":"https://github.com/PaddlePaddle/PaddleOCR","n_code_links":2,"syntology":null},{"rank_in_archive_order":12,"model":"MaskTextSpotter v3","metrics":{"F-measure (%) - Generic Lexicon":"74.2","F-measure (%) - Strong Lexicon":"83.3","F-measure (%) - Weak Lexicon":"78.1"},"uses_additional_data":false,"paper_date":"2020-07-18","paper":"/paper/mask-textspotter-v3-segmentation-proposal","paper_url":"https://arxiv.org/abs/2007.09482v1","paper_title":"Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting","code":"https://github.com/MhLiao/MaskTextSpotterV3","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"ABCNet v2","metrics":{"F-measure (%) - Generic Lexicon":"73.0","F-measure (%) - Strong Lexicon":"82.7","F-measure (%) - Weak Lexicon":"78.5"},"uses_additional_data":false,"paper_date":"2021-05-08","paper":"/paper/abcnet-v2-adaptive-bezier-curve-network-for","paper_url":"https://arxiv.org/abs/2105.03620v3","paper_title":"ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting","code":"https://github.com/Yuliang-Liu/ABCNet_Chinese","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"TextDragon","metrics":{"F-measure (%) - Generic Lexicon":"65.2","F-measure (%) - Strong Lexicon":"82.5","F-measure (%) - Weak Lexicon":"78.3"},"uses_additional_data":false,"paper_date":"2019-10-01","paper":"/paper/textdragon-an-end-to-end-framework-for","paper_url":"http://openaccess.thecvf.com/content_ICCV_2019/html/Feng_TextDragon_An_End-to-End_Framework_for_Arbitrary_Shaped_Text_Spotting_ICCV_2019_paper.html","paper_title":"TextDragon: An End-to-End Framework for Arbitrary Shaped Text Spotting","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":15,"model":"SPTS v2","metrics":{"F-measure (%) - Generic Lexicon":"72.6","F-measure (%) - Strong Lexicon":"82.3","F-measure (%) - Weak Lexicon":"77.7"},"uses_additional_data":false,"paper_date":"2023-01-04","paper":"/paper/spts-v2-single-point-scene-text-spotting","paper_url":"https://arxiv.org/abs/2301.01635v4","paper_title":"SPTS v2: Single-Point Scene Text Spotting","code":"https://github.com/shannanyinxiang/spts","n_code_links":3,"syntology":{"n_ran":5,"n_unverified":11,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"MANGO","metrics":{"F-measure (%) - Generic Lexicon":"67.3","F-measure (%) - Strong Lexicon":"81.8","F-measure (%) - Weak Lexicon":"78.9"},"uses_additional_data":false,"paper_date":"2020-12-08","paper":"/paper/mango-a-mask-attention-guided-one-stage-scene","paper_url":"https://arxiv.org/abs/2012.04350v2","paper_title":"MANGO: A Mask Attention Guided One-Stage Scene Text Spotter","code":"https://github.com/hikopensource/davar-lab-ocr","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"TextPerceptron","metrics":{"F-measure (%) - Generic Lexicon":"65.1","F-measure (%) - Strong Lexicon":"80.5","F-measure (%) - Weak Lexicon":"76.6"},"uses_additional_data":false,"paper_date":"2020-02-17","paper":"/paper/text-perceptron-towards-end-to-end-arbitrary","paper_url":"https://arxiv.org/abs/2002.06820v2","paper_title":"Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting","code":"https://github.com/hikopensource/davar-lab-ocr","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"SPTS","metrics":{"F-measure (%) - Generic Lexicon":"65.8","F-measure (%) - Strong Lexicon":"77.5","F-measure (%) - Weak Lexicon":"70.2"},"uses_additional_data":false,"paper_date":"2021-12-15","paper":"/paper/spts-single-point-text-spotting","paper_url":"https://arxiv.org/abs/2112.07917v6","paper_title":"SPTS: Single-Point Text Spotting","code":"https://github.com/shannanyinxiang/spts","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":4,"rows_with_any_sample_ran":4,"distinct_papers_with_graph_line":4,"distinct_papers_with_any_sample_ran":4,"samples_over_distinct_papers":{"n_ran":23,"n_unverified":18,"n_samples":41,"n_pointer_only_licence":5,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":23,"n_unverified":18,"n_samples":41,"n_pointer_only_licence":5,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}