{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/fots-fast-oriented-text-spotting-with-a","title":"FOTS: Fast Oriented Text Spotting with a Unified Network","arxiv_id":"1801.01671","date":"2018-01-05","proceeding":"CVPR 2018 6","authors":["Xuebo Liu","Ding Liang","Shi Yan","Dagui Chen","Yu Qiao","Junjie Yan"],"abstract":"Incidental scene text spotting is considered one of the most difficult and\nvaluable challenges in the document analysis community. Most existing methods\ntreat text detection and recognition as separate tasks. In this work, we\npropose a unified end-to-end trainable Fast Oriented Text Spotting (FOTS)\nnetwork for simultaneous detection and recognition, sharing computation and\nvisual information among the two complementary tasks. Specially, RoIRotate is\nintroduced to share convolutional features between detection and recognition.\nBenefiting from convolution sharing strategy, our FOTS has little computation\noverhead compared to baseline text detection network, and the joint training\nmethod learns more generic features to make our method perform better than\nthese two-stage methods. Experiments on ICDAR 2015, ICDAR 2017 MLT, and ICDAR\n2013 datasets demonstrate that the proposed method outperforms state-of-the-art\nmethods significantly, which further allows us to develop the first real-time\noriented text spotting system which surpasses all previous state-of-the-art\nresults by more than 5% on ICDAR 2015 text spotting task while keeping 22.6\nfps.","url_abs":"http://arxiv.org/abs/1801.01671v2","url_pdf":"http://arxiv.org/pdf/1801.01671v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"fots-fast-oriented-text-spotting-with-a","repo_url":"https://github.com/ArashJavan/FOTS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"fots-fast-oriented-text-spotting-with-a","repo_url":"https://github.com/Kaushal28/FOTS-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"fots-fast-oriented-text-spotting-with-a","repo_url":"https://github.com/Masao-Taketani/FOTS_OCR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"fots-fast-oriented-text-spotting-with-a","repo_url":"https://github.com/Pay20Y/FOTS_TF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"fots-fast-oriented-text-spotting-with-a","repo_url":"https://github.com/jiangxiluning/FOTS.PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"fots-fast-oriented-text-spotting-with-a","repo_url":"https://github.com/xieyufei1993/FOTS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"fots-fast-oriented-text-spotting-with-a","repo_url":"https://github.com/yu20103983/FOTS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"scene-text-detection","task_name":"Scene Text Detection"},{"task_slug":"scene-text-recognition","task_name":"Scene Text Recognition"},{"task_slug":"text-detection","task_name":"Text Detection"},{"task_slug":"text-spotting","task_name":"Text Spotting"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-text-detection-on-icdar-2015","task":"Scene Text Detection","dataset":"ICDAR 2015","model":"FOTS MS","rank_in_archive_order":7,"of":43,"metrics":{"F-Measure":"89.84","Precision":"91.85","Recall":"87.92"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-icdar-2015","task":"Scene Text Detection","dataset":"ICDAR 2015","model":"FOTS","rank_in_archive_order":12,"of":43,"metrics":{"F-Measure":"87.99","Precision":"91","Recall":"85.17"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-icdar-2017-mlt-1","task":"Scene Text Detection","dataset":"ICDAR 2017 MLT","model":"FOTS MS","rank_in_archive_order":4,"of":14,"metrics":{"F-Measure":"70.75%","Precision":"81.86","Recall":"62.3"},"uses_additional_data":false},{"leaderboard":"/sota/scene-text-detection-on-icdar-2017-mlt-1","task":"Scene Text Detection","dataset":"ICDAR 2017 MLT","model":"FOTS","rank_in_archive_order":6,"of":14,"metrics":{"F-Measure":"67.25%","Precision":"80.95","Recall":"57.51"},"uses_additional_data":false},{"leaderboard":"/sota/text-spotting-on-icdar-2015","task":"Text Spotting","dataset":"ICDAR 2015","model":"FOTS","rank_in_archive_order":10,"of":18,"metrics":{"F-measure (%) - Generic Lexicon":"62.2","F-measure (%) - Strong Lexicon":"83.6","F-measure (%) - Weak Lexicon":"74.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1801.01671","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}