{"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/e2e-mlt-an-unconstrained-end-to-end-method","title":"E2E-MLT - an Unconstrained End-to-End Method for Multi-Language Scene Text","arxiv_id":"1801.09919","date":"2018-01-30","proceeding":null,"authors":["Michal Bušta","Yash Patel","Jiri Matas"],"abstract":"An end-to-end trainable (fully differentiable) method for multi-language\nscene text localization and recognition is proposed. The approach is based on a\nsingle fully convolutional network (FCN) with shared layers for both tasks.\n  E2E-MLT is the first published multi-language OCR for scene text. While\ntrained in multi-language setup, E2E-MLT demonstrates competitive performance\nwhen compared to other methods trained for English scene text alone. The\nexperiments show that obtaining accurate multi-language multi-script\nannotations is a challenging problem.","url_abs":"http://arxiv.org/abs/1801.09919v2","url_pdf":"http://arxiv.org/pdf/1801.09919v2.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":"e2e-mlt-an-unconstrained-end-to-end-method","repo_url":"https://github.com/yash0307/E2E-MLT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"e2e-mlt-an-unconstrained-end-to-end-method","repo_url":"https://github.com/MichalBusta/E2E-MLT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"e2e-mlt-an-unconstrained-end-to-end-method","repo_url":"https://github.com/nhh1501/E2E_MLT_VN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1801.09919","atlas_url":"https://app.syntology.ai/?focus=1801.09919","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}