{"url":"/task/text-spotting","name":"Text Spotting","slug":"text-spotting","description_markdown":"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.","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":112,"papers_with_code":64,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"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":6,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/text-spotting-on-icdar-2015","slug":"text-spotting-on-icdar-2015","dataset":"ICDAR 2015","dataset_url":"/dataset/icdar-2015","rows_in_archive":18,"metrics":["F-measure (%) - Strong Lexicon","F-measure (%) - Weak Lexicon","F-measure (%) - Generic Lexicon"],"first_row_in_archive_order":{"model":"UNITS","paper_title":"Towards Unified Scene Text Spotting based on Sequence Generation","paper_url":"/paper/towards-unified-scene-text-spotting-based-on","paper_date":"2023-04-07","arxiv_id":"2304.03435","code_links":[{"title":"clovaai/units","url":"https://github.com/clovaai/units"}],"syntology":{"n":8,"n_ran":7,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/text-spotting-on-total-text","slug":"text-spotting-on-total-text","dataset":"Total-Text","dataset_url":"/dataset/total-text","rows_in_archive":12,"metrics":["F-measure (%) - No Lexicon","F-measure (%) - Full Lexicon"],"first_row_in_archive_order":{"model":"DeepSolo (ViTAEv2-S, TextOCR)","paper_title":"DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting","paper_url":"/paper/deepsolo-let-transformer-decoder-with","paper_date":"2022-11-19","arxiv_id":"2211.10772","code_links":[{"title":"vitae-transformer/deepsolo","url":"https://github.com/vitae-transformer/deepsolo"}],"syntology":null}},{"leaderboard":"/sota/text-spotting-on-scut-ctw1500","slug":"text-spotting-on-scut-ctw1500","dataset":"SCUT-CTW1500","dataset_url":"/dataset/scut-ctw1500","rows_in_archive":11,"metrics":["F-measure (%) - No Lexicon","F-Measure (%) - Full Lexicon"],"first_row_in_archive_order":{"model":"A3S","paper_title":"A3S: Adversarial learning of semantic representations for Scene-Text Spotting","paper_url":"/paper/a3s-adversarial-learning-of-semantic","paper_date":"2023-02-21","arxiv_id":"2302.10641","code_links":[],"syntology":null}},{"leaderboard":"/sota/text-spotting-on-inverse-text","slug":"text-spotting-on-inverse-text","dataset":"Inverse-Text","dataset_url":null,"rows_in_archive":9,"metrics":["F-measure (%) - No Lexicon","F-measure (%) - Full Lexicon"],"first_row_in_archive_order":{"model":"DeepSolo (ViTAEv2-S, TextOCR)","paper_title":"DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting","paper_url":"/paper/deepsolo-let-transformer-decoder-with-1","paper_date":"2023-05-31","arxiv_id":"2305.19957","code_links":[{"title":"vitae-transformer/deepsolo","url":"https://github.com/vitae-transformer/deepsolo"}],"syntology":null}}],"datasets":[{"url":"/dataset/total-text","name":"Total-Text","full_name":"","num_papers_in_archive":156},{"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/lsvtd","name":"LSVTD","full_name":"","num_papers_in_archive":7},{"url":"/dataset/ucla-protest-image","name":"UCLA Protest Image","full_name":"","num_papers_in_archive":2},{"url":"/dataset/textual-visual-semantic-dataset","name":"Textual Visual Semantic Dataset","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":64,"tagged_in_all":112,"items":[{"url":"/paper/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_unverified":1,"n_pointer_only":1}},{"url":"/paper/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/bridging-the-gap-between-end-to-end-and-two","title":"Bridging the Gap Between End-to-End and Two-Step Text Spotting","date":"2024-04-06","arxiv_id":"2404.04624","repositories_listed":4,"syntology":{"n":37,"n_ran":26,"n_unverified":11,"n_pointer_only":23}},{"url":"/paper/estextspotter-towards-better-scene-text","title":"ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer","date":"2023-08-20","arxiv_id":"2308.10147","repositories_listed":3,"syntology":null},{"url":"/paper/spts-v2-single-point-scene-text-spotting","title":"SPTS v2: Single-Point Scene Text Spotting","date":"2023-01-04","arxiv_id":"2301.01635","repositories_listed":3,"syntology":{"n":16,"n_ran":5,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/a-bilingual-openworld-video-text-dataset-and","title":"A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer","date":"2021-12-09","arxiv_id":"2112.04888","repositories_listed":3,"syntology":{"n":19,"n_ran":16,"n_unverified":3,"n_pointer_only":19}},{"url":"/paper/semantic-relatedness-based-re-ranker-for-text","title":"Semantic Relatedness Based Re-ranker for Text Spotting","date":"2019-09-17","arxiv_id":"1909.07950","repositories_listed":3,"syntology":null},{"url":"/paper/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/glass-global-to-local-attention-for-scene","title":"GLASS: Global to Local Attention for Scene-Text Spotting","date":"2022-08-05","arxiv_id":"2208.03364","repositories_listed":2,"syntology":null},{"url":"/paper/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_unverified":1,"n_pointer_only":5}},{"url":"/paper/open-images-v5-text-annotation-and-yet","title":"Open Images V5 Text Annotation and Yet Another Mask Text Spotter","date":"2021-06-23","arxiv_id":"2106.12326","repositories_listed":2,"syntology":null},{"url":"/paper/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/ae-textspotter-learning-visual-and-linguistic","title":"AE TextSpotter: Learning Visual and Linguistic Representation for Ambiguous Text Spotting","date":"2020-08-03","arxiv_id":"2008.00714","repositories_listed":2,"syntology":null},{"url":"/paper/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/gomatching-parameter-and-data-efficient","title":"GoMatching++: Parameter- and Data-Efficient Arbitrary-Shaped Video Text Spotting and Benchmarking","date":"2025-05-28","arxiv_id":"2505.22228","repositories_listed":1,"syntology":null},{"url":"/paper/semiets-integrating-spatial-and-content-1","title":"SemiETS: Integrating Spatial and Content Consistencies for Semi-Supervised End-to-end Text Spotting","date":"2025-04-14","arxiv_id":"2504.09966","repositories_listed":1,"syntology":null},{"url":"/paper/textinplace-indoor-visual-place-recognition","title":"TextInPlace: Indoor Visual Place Recognition in Repetitive Structures with Scene Text Spotting and Verification","date":"2025-03-09","arxiv_id":"2503.06501","repositories_listed":1,"syntology":null},{"url":"/paper/omniparser-v2-structured-points-of-thought","title":"OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Models","date":"2025-02-22","arxiv_id":"2502.16161","repositories_listed":1,"syntology":null},{"url":"/paper/instructocr-instruction-boosting-scene-text","title":"InstructOCR: Instruction Boosting Scene Text Spotting","date":"2024-12-20","arxiv_id":"2412.15523","repositories_listed":1,"syntology":null},{"url":"/paper/fasttextspotter-a-high-efficiency-transformer","title":"FastTextSpotter: A High-Efficiency Transformer for Multilingual Scene Text Spotting","date":"2024-08-27","arxiv_id":"2408.14998","repositories_listed":1,"syntology":null},{"url":"/paper/dntextspotter-arbitrary-shaped-scene-text","title":"DNTextSpotter: Arbitrary-Shaped Scene Text Spotting via Improved Denoising Training","date":"2024-08-01","arxiv_id":"2408.00355","repositories_listed":1,"syntology":null},{"url":"/paper/wecromcl-weakly-supervised-cross-modality","title":"WeCromCL: Weakly Supervised Cross-Modality Contrastive Learning for Transcription-only Supervised Text Spotting","date":"2024-07-28","arxiv_id":"2407.19507","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_unverified":3,"n_pointer_only":11}},{"url":"/paper/vimts-a-unified-video-and-image-text-spotter","title":"VimTS: A Unified Video and Image Text Spotter for Enhancing the Cross-domain Generalization","date":"2024-04-30","arxiv_id":"2404.19652","repositories_listed":1,"syntology":null},{"url":"/paper/omniparser-a-unified-framework-for-text","title":"OmniParser: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognition","date":"2024-03-28","arxiv_id":"2403.19128","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/textmonkey-an-ocr-free-large-multimodal-model","title":"TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document","date":"2024-03-07","arxiv_id":"2403.04473","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/swintextspotter-v2-towards-better-synergy-for","title":"SwinTextSpotter v2: Towards Better Synergy for Scene Text Spotting","date":"2024-01-15","arxiv_id":"2401.07641","repositories_listed":1,"syntology":null},{"url":"/paper/gomatching-a-simple-baseline-for-video-text","title":"GoMatching: A Simple Baseline for Video Text Spotting via Long and Short Term Matching","date":"2024-01-13","arxiv_id":"2401.07080","repositories_listed":1,"syntology":null},{"url":"/paper/glotsformer-global-video-text-spotting","title":"GloTSFormer: Global Video Text Spotting Transformer","date":"2024-01-08","arxiv_id":"2401.03694","repositories_listed":1,"syntology":null},{"url":"/paper/omniparser-a-unified-framework-for-text-1","title":"OmniParser: A Unified Framework for Text Spotting Key Information Extraction and Table Recognition","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/parrot-captions-teach-clip-to-spot-text","title":"Parrot Captions Teach CLIP to Spot Text","date":"2023-12-21","arxiv_id":"2312.14232","repositories_listed":1,"syntology":null}],"syntology_records":8,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}