{"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/visual-semantic-re-ranker-for-text-spotting","title":"Visual Semantic Re-ranker for Text Spotting","arxiv_id":"1810.09776","date":"2018-10-23","proceeding":null,"authors":["Ahmed Sabir","Francesc Moreno-Noguer","Lluís Padró"],"abstract":"Many current state-of-the-art methods for text recognition are based on\npurely local information and ignore the semantic correlation between text and\nits surrounding visual context. In this paper, we propose a post-processing\napproach to improve the accuracy of text spotting by using the semantic\nrelation between the text and the scene. We initially rely on an off-the-shelf\ndeep neural network that provides a series of text hypotheses for each input\nimage. These text hypotheses are then re-ranked using the semantic relatedness\nwith the object in the image. As a result of this combination, the performance\nof the original network is boosted with a very low computational cost. The\nproposed framework can be used as a drop-in complement for any text-spotting\nalgorithm that outputs a ranking of word hypotheses. We validate our approach\non ICDAR'17 shared task dataset.","url_abs":"http://arxiv.org/abs/1810.09776v2","url_pdf":"http://arxiv.org/pdf/1810.09776v2.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":"visual-semantic-re-ranker-for-text-spotting","repo_url":"https://github.com/ahmedssabir/Visual-Semantic-Relatedness-with-Word-Embedding","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"text-spotting","task_name":"Text Spotting"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}