{"url":"/task/text-detection","name":"Text Detection","slug":"text-detection","description_markdown":"Detecting the text in the image and localise it using a bounding box. The text can be in any shape and size. We need to localise all such instances of text in the entire image along with bounding box for each word.","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":595,"papers_with_code":253,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":3,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/text-detection-on-urdudoc","slug":"text-detection-on-urdudoc","dataset":"UrduDoc","dataset_url":"/dataset/urdudoc","rows_in_archive":5,"metrics":["Precision","Recall"],"first_row_in_archive_order":{"model":"ContourNet [69]","paper_title":"UTRNet: High-Resolution Urdu Text Recognition In Printed Documents","paper_url":"/paper/utrnet-high-resolution-urdu-text-recognition","paper_date":"2023-06-27","arxiv_id":"2306.15782","code_links":[{"title":"abdur75648/UTRNet-High-Resolution-Urdu-Text-Recognition","url":"https://github.com/abdur75648/UTRNet-High-Resolution-Urdu-Text-Recognition"}],"syntology":null}}],"datasets":[{"url":"/dataset/bfrd","name":"BFRD","full_name":"Bengali Fake Review Dataset","num_papers_in_archive":1},{"url":"/dataset/urdudoc","name":"UrduDoc","full_name":"","num_papers_in_archive":1},{"url":"/dataset/media-text","name":"Media-Text","full_name":"MediaText: a media industry-based dataset for scene text detetcion","num_papers_in_archive":0}],"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":253,"tagged_in_all":595,"items":[{"url":"/paper/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_unverified":1,"n_pointer_only":1}},{"url":"/paper/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","title":"Character Region Awareness for Text Detection","date":"2019-04-03","arxiv_id":"1904.01941","repositories_listed":18,"syntology":{"n":40,"n_ran":6,"n_unverified":34,"n_pointer_only":4}},{"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/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":3,"n_unverified":22,"n_pointer_only":0}},{"url":"/paper/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":2,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/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":5,"n_unverified":19,"n_pointer_only":2}},{"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/word-level-human-interpretable-scoring","title":"Word-level Human Interpretable Scoring Mechanism for Novel Text Detection Using Tsetlin Machines","date":"2021-05-10","arxiv_id":"2105.04708","repositories_listed":6,"syntology":null},{"url":"/paper/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","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":4,"n_unverified":24,"n_pointer_only":0}},{"url":"/paper/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_unverified":0,"n_pointer_only":1}},{"url":"/paper/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","title":"PixelLink: Detecting Scene Text via Instance Segmentation","date":"2018-01-04","arxiv_id":"1801.01315","repositories_listed":5,"syntology":null},{"url":"/paper/deeptext-a-unified-framework-for-text","title":"DeepText: A Unified Framework for Text Proposal Generation and Text Detection in Natural Images","date":"2016-05-24","arxiv_id":"1605.07314","repositories_listed":5,"syntology":null},{"url":"/paper/mgtbench-benchmarking-machine-generated-text","title":"MGTBench: Benchmarking Machine-Generated Text Detection","date":"2023-03-26","arxiv_id":"2303.14822","repositories_listed":4,"syntology":{"n":26,"n_ran":5,"n_unverified":21,"n_pointer_only":0}},{"url":"/paper/detectgpt-zero-shot-machine-generated-text","title":"DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature","date":"2023-01-26","arxiv_id":"2301.11305","repositories_listed":4,"syntology":{"n":9,"n_ran":3,"n_unverified":6,"n_pointer_only":2}},{"url":"/paper/dit-self-supervised-pre-training-for-document","title":"DiT: Self-supervised Pre-training for Document Image Transformer","date":"2022-03-04","arxiv_id":"2203.02378","repositories_listed":4,"syntology":{"n":11,"n_ran":0,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/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":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/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/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/multiscale-positive-unlabeled-detection-of-ai","title":"Multiscale Positive-Unlabeled Detection of AI-Generated Texts","date":"2023-05-29","arxiv_id":"2305.18149","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"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/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_unverified":7,"n_pointer_only":15}},{"url":"/paper/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":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/190513538","title":"FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents","date":"2019-05-27","arxiv_id":"1905.13538","repositories_listed":3,"syntology":null},{"url":"/paper/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":1,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/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","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/synthetic-data-for-text-localisation-in","title":"Synthetic Data for Text Localisation in Natural Images","date":"2016-04-22","arxiv_id":"1604.06646","repositories_listed":3,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}}],"syntology_records":18,"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"}}