{"id":"https://openalex.org/W2525090041","doi":"https://doi.org/10.1145/2964284.2967282","title":"Detecting Arbitrary Oriented Text in the Wild with a Visual Attention Model","display_name":"Detecting Arbitrary Oriented Text in the Wild with a Visual Attention Model","publication_year":2016,"publication_date":"2016-09-29","ids":{"openalex":"https://openalex.org/W2525090041","doi":"https://doi.org/10.1145/2964284.2967282","mag":"2525090041"},"language":"en","primary_location":{"id":"doi:10.1145/2964284.2967282","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2964284.2967282","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2967282&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=2967282&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069048388","display_name":"Wenyi Huang","orcid":"https://orcid.org/0000-0002-3526-6314"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wenyi Huang","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087598861","display_name":"Dafang He","orcid":"https://orcid.org/0000-0002-4049-9729"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dafang He","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055756196","display_name":"Xiao Yang","orcid":"https://orcid.org/0000-0003-4558-8947"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao Yang","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001762730","display_name":"Zihan Zhou","orcid":"https://orcid.org/0000-0002-1697-2168"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zihan Zhou","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005431144","display_name":"Daniel Kifer","orcid":"https://orcid.org/0000-0002-4611-7066"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Kifer","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001294898","display_name":"C. Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Lee Giles","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5069048388"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":2.3381,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.9253025,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"551","last_page":"555"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8300998210906982},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6089197397232056},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6008844971656799},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5018320083618164},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4696368873119354},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.42045480012893677},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.39722758531570435},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3463381230831146}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8300998210906982},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6089197397232056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6008844971656799},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5018320083618164},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4696368873119354},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.42045480012893677},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.39722758531570435},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3463381230831146},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2964284.2967282","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2964284.2967282","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2967282&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2964284.2967282","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2964284.2967282","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2967282&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM international conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6193076742","display_name":null,"funder_award_id":"1317560","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2525090041.pdf","grobid_xml":"https://content.openalex.org/works/W2525090041.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W70975097","https://openalex.org/W984976173","https://openalex.org/W1026856040","https://openalex.org/W1488125194","https://openalex.org/W1491389626","https://openalex.org/W1514535095","https://openalex.org/W1607307044","https://openalex.org/W1935817682","https://openalex.org/W1971822075","https://openalex.org/W1972065312","https://openalex.org/W1998042868","https://openalex.org/W2001999290","https://openalex.org/W2019370496","https://openalex.org/W2019478948","https://openalex.org/W2020905429","https://openalex.org/W2023415694","https://openalex.org/W2056518953","https://openalex.org/W2061802763","https://openalex.org/W2065613686","https://openalex.org/W2083868436","https://openalex.org/W2086478842","https://openalex.org/W2112796928","https://openalex.org/W2122710056","https://openalex.org/W2131673214","https://openalex.org/W2135440260","https://openalex.org/W2142159465","https://openalex.org/W2144554289","https://openalex.org/W2147527908","https://openalex.org/W2183231851","https://openalex.org/W2239285313","https://openalex.org/W2296073425","https://openalex.org/W2310919327","https://openalex.org/W2487919169","https://openalex.org/W2964036520","https://openalex.org/W4249401242","https://openalex.org/W6678398238"],"related_works":["https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W1847088711","https://openalex.org/W4225394202","https://openalex.org/W3036642985","https://openalex.org/W3032952384","https://openalex.org/W3017902212","https://openalex.org/W2964335273","https://openalex.org/W2982145560","https://openalex.org/W2969450769"],"abstract_inverted_index":{"Text":[0],"embedded":[1],"in":[2,16,55],"images":[3],"provides":[4],"important":[5],"semantic":[6],"information":[7,81],"about":[8],"a":[9,21,38,63,74],"scene":[10,48],"and":[11,31,46,72,109],"its":[12],"content.":[13],"Detecting":[14],"text":[15],"an":[17,92],"unconstrained":[18],"environment":[19],"is":[20],"challenging":[22],"task":[23],"because":[24],"of":[25,33],"the":[26,34,52,56,69,80,86,97,100,104,110],"many":[27],"fonts,":[28],"sizes,":[29],"backgrounds,":[30],"alignments":[32],"characters.":[35],"We":[36],"present":[37],"novel":[39],"attention":[40,53,87],"model":[41,61,98],"for":[42],"detecting":[43],"arbitrary":[44,115],"oriented":[45,116],"curved":[47],"text.":[49,117],"Inspired":[50],"by":[51],"mechanisms":[54],"human":[57],"visual":[58],"system,":[59],"our":[60],"utilizes":[62],"spatial":[64],"glimpse":[65],"network":[66,77],"to":[67,84],"processes":[68],"attended":[70],"area":[71],"deploys":[73],"recurrent":[75],"neural":[76],"that":[78],"aggregates":[79],"over":[82],"time":[83],"determine":[85],"movement.":[88],"Combining":[89],"this":[90],"with":[91],"off-the-shelf":[93],"region":[94],"proposal":[95],"method,":[96],"achieves":[99],"state-of-the-art":[101],"performance":[102],"on":[103],"highly":[105],"cited":[106],"ICDAR2013":[107],"dataset,":[108],"MSRA-TD500":[111],"dataset":[112],"which":[113],"contains":[114]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":10}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}