{"id":"https://openalex.org/W2807732175","doi":"https://doi.org/10.1145/3206025.3206043","title":"A Multi-Oriented Scene Text Detector with Position-Sensitive Segmentation","display_name":"A Multi-Oriented Scene Text Detector with Position-Sensitive Segmentation","publication_year":2018,"publication_date":"2018-06-05","ids":{"openalex":"https://openalex.org/W2807732175","doi":"https://doi.org/10.1145/3206025.3206043","mag":"2807732175"},"language":"en","primary_location":{"id":"doi:10.1145/3206025.3206043","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3206025.3206043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007124311","display_name":"Peirui Cheng","orcid":"https://orcid.org/0000-0002-4993-6753"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peirui Cheng","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100721601","display_name":"Weiqiang Wang","orcid":"https://orcid.org/0000-0002-7185-2804"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiqiang Wang","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.318,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.61708235,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"12","issue":null,"first_page":"152","last_page":"159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.9916999936103821,"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/segmentation","display_name":"Segmentation","score":0.8238842487335205},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7999262809753418},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7694078087806702},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.6594424247741699},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6589342355728149},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5776875615119934},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5568543076515198},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5498131513595581},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5394718050956726},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5287192463874817},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5211318135261536},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.4297254681587219},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3668583929538727}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8238842487335205},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7999262809753418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7694078087806702},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.6594424247741699},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6589342355728149},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5776875615119934},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5568543076515198},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5498131513595581},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5394718050956726},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5287192463874817},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5211318135261536},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.4297254681587219},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3668583929538727},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3206025.3206043","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3206025.3206043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W70975097","https://openalex.org/W101496726","https://openalex.org/W117491841","https://openalex.org/W639708223","https://openalex.org/W1488125194","https://openalex.org/W1861492603","https://openalex.org/W1903029394","https://openalex.org/W1922126009","https://openalex.org/W1935817682","https://openalex.org/W2008806374","https://openalex.org/W2061802763","https://openalex.org/W2108598243","https://openalex.org/W2124592697","https://openalex.org/W2129987527","https://openalex.org/W2142159465","https://openalex.org/W2144554289","https://openalex.org/W2148214126","https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2317851288","https://openalex.org/W2339589954","https://openalex.org/W2343052201","https://openalex.org/W2395360388","https://openalex.org/W2504335775","https://openalex.org/W2519818067","https://openalex.org/W2550687635","https://openalex.org/W2555182955","https://openalex.org/W2565639579","https://openalex.org/W2599765304","https://openalex.org/W2604243686","https://openalex.org/W2605076167","https://openalex.org/W2605982830","https://openalex.org/W2607075434","https://openalex.org/W2734349601","https://openalex.org/W2962773189","https://openalex.org/W2963037989","https://openalex.org/W2963977642","https://openalex.org/W3098090606","https://openalex.org/W3104370314","https://openalex.org/W3106250896","https://openalex.org/W6819060087"],"related_works":["https://openalex.org/W2095705906","https://openalex.org/W2383464976","https://openalex.org/W2975200075","https://openalex.org/W2004370856","https://openalex.org/W1967061043","https://openalex.org/W2739874619","https://openalex.org/W2019566805","https://openalex.org/W2021186063","https://openalex.org/W1963494852","https://openalex.org/W2965422042"],"abstract_inverted_index":{"Scene":[0],"text":[1,21,40,63,93,102,125],"detection":[2,33,64,70,94,103,126],"has":[3],"been":[4],"studied":[5],"for":[6,107,116,135],"a":[7,23,77,84,201],"long":[8],"time":[9],"and":[10,26,51,96,110,178,200],"lots":[11],"of":[12,31,48,143,150,198,204],"approaches":[13,19],"have":[14],"achieved":[15],"promising":[16],"performances.":[17],"Most":[18],"regard":[20],"as":[22,167],"specific":[24],"object":[25,32,69],"utilize":[27],"the":[28,68,73,121,131,141,148,151,155,164,171,182,192],"popular":[29],"frameworks":[30],"to":[34,146,161,168],"detect":[35],"scene":[36,39,62],"text.":[37],"However,":[38],"is":[41,105,114],"different":[42],"from":[43],"general":[44],"objects":[45],"in":[46],"terms":[47],"orientations,":[49],"sizes":[50],"aspect":[52],"ratios.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57],"present":[58],"an":[59,196],"end-to-end":[60],"multi-oriented":[61],"approach,":[65],"which":[66],"combines":[67],"framework":[71],"with":[72],"position-sensitive":[74,97,111,132,144,158],"segmentation.":[75],"For":[76,189],"given":[78],"image,":[79],"features":[80],"are":[81,90,128],"extracted":[82],"through":[83],"fully":[85],"convolutional":[86],"network.":[87,153],"Then":[88],"they":[89],"input":[91],"into":[92],"branch":[95,99,104,113,127],"segmentation":[98,112,118,133,145,159],"simultaneously,":[100],"where":[101],"used":[106,115],"generating":[108,117],"candidates":[109,122,165],"maps.":[119],"Finally":[120],"generated":[123],"by":[124],"projected":[129],"onto":[130],"maps":[134,160],"filtering.":[136],"The":[137],"proposed":[138,152,183,193],"approach":[139,156],"utilizes":[140],"merits":[142],"improve":[147,170],"expressiveness":[149],"Additionally,":[154],"uses":[157],"further":[162],"filter":[163],"so":[166],"highly":[169],"precision":[172,202],"rate.":[173],"Experiments":[174],"on":[175],"datasets":[176],"ICDAR2015":[177,190],"COCO-Text":[179],"demonstrate":[180],"that":[181],"method":[184,194],"outperforms":[185],"previous":[186],"state-of-the-art":[187],"methods.":[188],"dataset,":[191],"achieves":[195],"F-score":[197],"0.83":[199],"rate":[203],"0.87.":[205]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}