{"id":"https://openalex.org/W2912576923","doi":"https://doi.org/10.1109/bigdata.2018.8622129","title":"A unified scheme of text localization and structured data extraction for joint OCR and data mining","display_name":"A unified scheme of text localization and structured data extraction for joint OCR and data mining","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2912576923","doi":"https://doi.org/10.1109/bigdata.2018.8622129","mag":"2912576923"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2018.8622129","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big Data)","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/A5057969679","display_name":"Yibin Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123571","display_name":"Huawei Technologies (France)","ror":"https://ror.org/02rbzf697","country_code":"FR","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210123571"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yibin Ye","raw_affiliation_strings":["Cloud BU, Huawei Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cloud BU, Huawei Technologies","institution_ids":["https://openalex.org/I4210123571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003746644","display_name":"Shenggao Zhu","orcid":"https://orcid.org/0000-0002-3254-0058"},"institutions":[{"id":"https://openalex.org/I4210123571","display_name":"Huawei Technologies (France)","ror":"https://ror.org/02rbzf697","country_code":"FR","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210123571"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Shenggao Zhu","raw_affiliation_strings":["Cloud BU, Huawei Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cloud BU, Huawei Technologies","institution_ids":["https://openalex.org/I4210123571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100378720","display_name":"Jing Wang","orcid":"https://orcid.org/0000-0003-4567-3869"},"institutions":[{"id":"https://openalex.org/I4210123571","display_name":"Huawei Technologies (France)","ror":"https://ror.org/02rbzf697","country_code":"FR","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210123571"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jing Wang","raw_affiliation_strings":["Cloud BU, Huawei Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cloud BU, Huawei Technologies","institution_ids":["https://openalex.org/I4210123571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009176287","display_name":"Qi Du","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123571","display_name":"Huawei Technologies (France)","ror":"https://ror.org/02rbzf697","country_code":"FR","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210123571"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Qi Du","raw_affiliation_strings":["Cloud BU, Huawei Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cloud BU, Huawei Technologies","institution_ids":["https://openalex.org/I4210123571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001076452","display_name":"Yezhang Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123571","display_name":"Huawei Technologies (France)","ror":"https://ror.org/02rbzf697","country_code":"FR","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210123571"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yezhang Yang","raw_affiliation_strings":["Cloud BU, Huawei Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cloud BU, Huawei Technologies","institution_ids":["https://openalex.org/I4210123571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101645793","display_name":"Dandan Tu","orcid":"https://orcid.org/0000-0002-3560-124X"},"institutions":[{"id":"https://openalex.org/I4210123571","display_name":"Huawei Technologies (France)","ror":"https://ror.org/02rbzf697","country_code":"FR","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210123571"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Dandan Tu","raw_affiliation_strings":["Cloud BU, Huawei Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cloud BU, Huawei Technologies","institution_ids":["https://openalex.org/I4210123571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025153128","display_name":"Lanjun Wang","orcid":"https://orcid.org/0000-0002-7696-5330"},"institutions":[{"id":"https://openalex.org/I4210123571","display_name":"Huawei Technologies (France)","ror":"https://ror.org/02rbzf697","country_code":"FR","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210123571"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Lanjun Wang","raw_affiliation_strings":["Cloud BU, Huawei Technologies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cloud BU, Huawei Technologies","institution_ids":["https://openalex.org/I4210123571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055469774","display_name":"Jiebo Luo","orcid":"https://orcid.org/0000-0002-4516-9729"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiebo Luo","raw_affiliation_strings":["University of Rochester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6243,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.75114706,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2373","last_page":"2382"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9943000078201294,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8466128706932068},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7089327573776245},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.6098187565803528},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5678144693374634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5547717809677124},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5501320362091064},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.534747302532196},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4764585793018341},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4365033507347107},{"id":"https://openalex.org/keywords/text-processing","display_name":"Text processing","score":0.42355093359947205},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4137963652610779},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4073951244354248},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35945987701416016},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3031412363052368}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8466128706932068},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7089327573776245},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.6098187565803528},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5678144693374634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5547717809677124},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5501320362091064},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.534747302532196},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4764585793018341},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4365033507347107},{"id":"https://openalex.org/C2779500292","wikidata":"https://www.wikidata.org/wiki/Q14802672","display_name":"Text processing","level":2,"score":0.42355093359947205},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4137963652610779},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4073951244354248},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35945987701416016},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3031412363052368},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2018.8622129","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W70975097","https://openalex.org/W117491841","https://openalex.org/W160318044","https://openalex.org/W756138690","https://openalex.org/W1512387364","https://openalex.org/W1573714593","https://openalex.org/W1585780903","https://openalex.org/W1614298861","https://openalex.org/W1922126009","https://openalex.org/W2012179495","https://openalex.org/W2019478948","https://openalex.org/W2056435187","https://openalex.org/W2069816967","https://openalex.org/W2104086170","https://openalex.org/W2128854450","https://openalex.org/W2135231474","https://openalex.org/W2137235842","https://openalex.org/W2137718414","https://openalex.org/W2138806976","https://openalex.org/W2140018062","https://openalex.org/W2150721933","https://openalex.org/W2153182373","https://openalex.org/W2160196229","https://openalex.org/W2161969291","https://openalex.org/W2162262658","https://openalex.org/W2165310684","https://openalex.org/W2194187530","https://openalex.org/W2204328893","https://openalex.org/W2239285313","https://openalex.org/W2294053032","https://openalex.org/W2333563142","https://openalex.org/W2339589954","https://openalex.org/W2343052201","https://openalex.org/W2519818067","https://openalex.org/W2520168073","https://openalex.org/W2550687635","https://openalex.org/W2569262305","https://openalex.org/W2593539516","https://openalex.org/W2604735854","https://openalex.org/W2605076167","https://openalex.org/W2605982830","https://openalex.org/W2613718673","https://openalex.org/W2884561390","https://openalex.org/W2950577311","https://openalex.org/W2953106684","https://openalex.org/W2962773189","https://openalex.org/W2962790387","https://openalex.org/W2963351448","https://openalex.org/W2963517393","https://openalex.org/W2964309167","https://openalex.org/W2964312704","https://openalex.org/W3023802502","https://openalex.org/W3106228955","https://openalex.org/W3106250896","https://openalex.org/W4231979413","https://openalex.org/W6602936574","https://openalex.org/W6604768502","https://openalex.org/W6620707391","https://openalex.org/W6630579473","https://openalex.org/W6634457518","https://openalex.org/W6636510571","https://openalex.org/W6640226783","https://openalex.org/W6675573929","https://openalex.org/W6682488149","https://openalex.org/W6683411478","https://openalex.org/W6684408796","https://openalex.org/W6702842988","https://openalex.org/W6726857151","https://openalex.org/W6729791593","https://openalex.org/W6742348326","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W4226047649","https://openalex.org/W159132833","https://openalex.org/W2577861415","https://openalex.org/W1560771748","https://openalex.org/W2918969764","https://openalex.org/W2963742859","https://openalex.org/W2113064181","https://openalex.org/W4292862793","https://openalex.org/W3174953199","https://openalex.org/W3202766839"],"abstract_inverted_index":{"Both":[0],"text":[1,24,101,131],"detection":[2,102],"and":[3,36,81,103,124,129,141,158],"structured":[4,53,104],"data":[5,49,54,75,105],"extraction":[6,106],"are":[7,45],"imperative":[8],"in":[9,33,48,68,132,153],"an":[10,120],"optical":[11],"character":[12],"recognition":[13],"(OCR)":[14],"processing":[15,84],"pipeline.":[16],"Text":[17,113],"detection,":[18],"especially":[19],"for":[20,73],"indistinct,":[21],"diverse,":[22],"multi-language":[23],"regions,":[25],"is":[26,119],"one":[27,64],"of":[28,65,149,155],"the":[29,147,150],"most":[30],"challenging":[31],"tasks":[32],"computer":[34],"vision":[35],"has":[37,57],"attracted":[38],"increasing":[39],"attention":[40,62],"recently.":[41],"Moreover,":[42],"although":[43],"there":[44],"some":[46],"studies":[47],"mining":[50],"related":[51],"to":[52,89,126],"extraction,":[55,76],"it":[56],"not":[58],"received":[59],"its":[60],"deserved":[61],"as":[63],"important":[66],"steps":[67],"OCR.":[69],"The":[70],"previous":[71],"methods":[72],"structural":[74],"including":[77],"layout":[78],"template-based,":[79],"rule-based,":[80],"natural":[82],"language":[83],"(NLP)-based":[85],"methods,":[86],"usually":[87],"leads":[88],"either":[90],"inaccurate":[91],"results":[92],"or":[93],"complex":[94],"modules.":[95],"In":[96],"this":[97],"paper,":[98],"we":[99],"integrate":[100],"into":[107],"a":[108,133],"unified":[109],"deep":[110],"learning-based":[111],"Image":[112],"Extraction":[114],"(ITE)":[115],"scheme.":[116],"Our":[117],"ITE":[118],"end-to-end":[121],"trainable":[122],"model":[123],"able":[125],"handle":[127],"multi-scale":[128],"multi-lingual":[130],"single":[134],"process.":[135],"Experiments":[136],"on":[137],"large-scale":[138],"real-world":[139],"passport":[140],"medical":[142],"receipt":[143],"datasets":[144],"have":[145],"demonstrated":[146],"superiority":[148],"proposed":[151],"method":[152],"terms":[154],"both":[156],"effectiveness":[157],"efficiency.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}