{"id":"https://openalex.org/W2886603769","doi":"https://doi.org/10.1109/tip.2018.2855399","title":"Multi-Oriented and Multi-Lingual Scene Text Detection With Direct Regression","display_name":"Multi-Oriented and Multi-Lingual Scene Text Detection With Direct Regression","publication_year":2018,"publication_date":"2018-07-12","ids":{"openalex":"https://openalex.org/W2886603769","doi":"https://doi.org/10.1109/tip.2018.2855399","mag":"2886603769","pmid":"https://pubmed.ncbi.nlm.nih.gov/30010560"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2018.2855399","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2018.2855399","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100736473","display_name":"Wenhao He","orcid":"https://orcid.org/0000-0002-3922-5720"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"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":true,"raw_author_name":"Wenhao He","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082548671","display_name":"Xu-Yao Zhang","orcid":"https://orcid.org/0000-0001-9260-188X"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"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":"Xu-Yao Zhang","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039310938","display_name":"Fei Yin","orcid":"https://orcid.org/0000-0002-6412-9140"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"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":"Fei Yin","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100714202","display_name":"Cheng\u2010Lin Liu","orcid":"https://orcid.org/0000-0002-6743-4175"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng-Lin Liu","raw_affiliation_strings":["Center for Excellence of Brain Science and Intelligence Technology, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Center for Excellence of Brain Science and Intelligence Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210097554","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100736473"],"corresponding_institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":7.4373,"has_fulltext":false,"cited_by_count":120,"citation_normalized_percentile":{"value":0.9791477,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"27","issue":"11","first_page":"5406","last_page":"5419"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9890999794006348,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.6283957958221436},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6249638795852661},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.5462710857391357},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5226376056671143},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4443775713443756},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.44002532958984375},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33065229654312134},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24966639280319214},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.23724859952926636},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23087438941001892}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6283957958221436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6249638795852661},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.5462710857391357},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5226376056671143},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4443775713443756},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.44002532958984375},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33065229654312134},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24966639280319214},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.23724859952926636},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23087438941001892}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2018.2855399","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2018.2855399","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:30010560","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30010560","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3418581704","display_name":null,"funder_award_id":"61733007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3601266531","display_name":null,"funder_award_id":"61411136002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6431871145","display_name":null,"funder_award_id":"61721004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7010190359","display_name":null,"funder_award_id":"61633021","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W7746136","https://openalex.org/W639708223","https://openalex.org/W1533861849","https://openalex.org/W1536680647","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1903029394","https://openalex.org/W1922126009","https://openalex.org/W1935817682","https://openalex.org/W1972065312","https://openalex.org/W2019478948","https://openalex.org/W2020964295","https://openalex.org/W2046836262","https://openalex.org/W2060822828","https://openalex.org/W2065613686","https://openalex.org/W2078997308","https://openalex.org/W2125556102","https://openalex.org/W2129987527","https://openalex.org/W2131163834","https://openalex.org/W2135231474","https://openalex.org/W2142159465","https://openalex.org/W2144554289","https://openalex.org/W2148214126","https://openalex.org/W2155893237","https://openalex.org/W2163352848","https://openalex.org/W2163605009","https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2217433794","https://openalex.org/W2239285313","https://openalex.org/W2339589954","https://openalex.org/W2343052201","https://openalex.org/W2395360388","https://openalex.org/W2464918637","https://openalex.org/W2468724597","https://openalex.org/W2519818067","https://openalex.org/W2550687635","https://openalex.org/W2565639579","https://openalex.org/W2604243686","https://openalex.org/W2604735854","https://openalex.org/W2605076167","https://openalex.org/W2605982830","https://openalex.org/W2613718673","https://openalex.org/W2785383245","https://openalex.org/W2785775823","https://openalex.org/W2911964244","https://openalex.org/W2950800384","https://openalex.org/W2962773189","https://openalex.org/W2962992847","https://openalex.org/W2963037989","https://openalex.org/W2963516811","https://openalex.org/W2964065044","https://openalex.org/W3106228955","https://openalex.org/W3106250896","https://openalex.org/W6600313631","https://openalex.org/W6620707391","https://openalex.org/W6631943919","https://openalex.org/W6637373629","https://openalex.org/W6638667902","https://openalex.org/W6642972425","https://openalex.org/W6684191040","https://openalex.org/W6714138976","https://openalex.org/W6729791593"],"related_works":["https://openalex.org/W31220157","https://openalex.org/W2312753042","https://openalex.org/W4289356671","https://openalex.org/W2389155397","https://openalex.org/W2165884543","https://openalex.org/W3186837933","https://openalex.org/W2368989808","https://openalex.org/W1969346022","https://openalex.org/W2034959125","https://openalex.org/W2355687852"],"abstract_inverted_index":{"Multi-oriented":[0],"and":[1,14,24,63,107,109,134,161,166],"multi-lingual":[2,162],"scene":[3,45,84,163,191],"text":[4,23,46,55,73,85,106,122,149,164,192],"detection":[5,42,86,127,137,193],"plays":[6],"an":[7],"important":[8],"role":[9],"in":[10,99,185],"computer":[11],"vision":[12],"area":[13],"is":[15,51,67,102,112,128],"challenging":[16],"due":[17],"to":[18,44,52,68,115,146,180],"the":[19,33,54,64,70,77,110,117,153],"wide":[20],"variety":[21],"of":[22,72,120,172],"background.":[25],"In":[26],"this":[27],"paper,":[28],"firstly":[29],"we":[30,81,138],"point":[31],"out":[32],"two":[34],"key":[35,183],"tasks":[36],"when":[37],"extending":[38],"CNN":[39,189],"based":[40,61,88,129,190],"object":[41],"frameworks":[43],"detection.":[47],"The":[48],"first":[49,78],"task":[50,66],"localize":[53,147],"region":[56,74],"by":[57,76],"a":[58,83,95,140],"down-sampled":[59],"segmentation":[60],"module,":[62],"second":[65],"regress":[69],"boundaries":[71],"determined":[75],"task.":[79],"Secondly,":[80],"propose":[82],"framework":[87,155],"on":[89,130,156,170],"fully":[90],"convolutional":[91],"network":[92],"(FCN)":[93],"with":[94],"bi-task":[96],"prediction":[97],"module":[98],"which":[100],"one":[101],"pixel-wise":[103,113],"classification":[104],"between":[105],"non-text,":[108],"other":[111],"regression":[114],"determine":[116],"vertex":[118],"coordinates":[119],"quadrilateral":[121],"boundaries.":[123],"Post-processing":[124],"for":[125,135],"word-level":[126],"Non-Maximum":[131],"Suppression":[132],"(NMS),":[133],"line-level":[136],"design":[139],"heuristic":[141],"line":[142],"segments":[143],"grouping":[144],"method":[145],"long":[148],"lines.":[150],"We":[151,174],"evaluated":[152],"proposed":[154],"various":[157],"benchmarks":[158],"including":[159],"multi-oriented":[160],"datasets,":[165],"achieved":[167],"state-of-the-art":[168],"performance":[169,188],"most":[171],"them.":[173],"also":[175],"provide":[176],"abundant":[177],"ablation":[178],"experiments":[179],"analyze":[181],"several":[182],"factors":[184],"building":[186],"high":[187],"systems.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":24},{"year":2020,"cited_by_count":28},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":3}],"updated_date":"2026-04-12T07:58:50.170612","created_date":"2025-10-10T00:00:00"}