{"id":"https://openalex.org/W4318148179","doi":"https://doi.org/10.1109/bigdata55660.2022.10020269","title":"Scene Text Recognition with Heuristic Local Attention","display_name":"Scene Text Recognition with Heuristic Local Attention","publication_year":2022,"publication_date":"2022-12-17","ids":{"openalex":"https://openalex.org/W4318148179","doi":"https://doi.org/10.1109/bigdata55660.2022.10020269"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata55660.2022.10020269","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata55660.2022.10020269","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103028836","display_name":"Tianlong Ma","orcid":"https://orcid.org/0000-0003-4079-7897"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianlong Ma","raw_affiliation_strings":["Fudan University,School of Computer Science,Shanghai,China","School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047942518","display_name":"Xiangcheng Du","orcid":"https://orcid.org/0000-0002-4268-6114"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangcheng Du","raw_affiliation_strings":["Fudan University,School of Computer Science,Shanghai,China","School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Computer Science,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101461644","display_name":"Yanlong Wang","orcid":"https://orcid.org/0000-0002-5857-2154"},"institutions":[{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanlong Wang","raw_affiliation_strings":["Shanxi University,Archives of Shanxi University,Shanxi,China","Archives of Shanxi University, Shanxi University, Shanxi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanxi University,Archives of Shanxi University,Shanxi,China","institution_ids":["https://openalex.org/I181877577"]},{"raw_affiliation_string":"Archives of Shanxi University, Shanxi University, Shanxi, China","institution_ids":["https://openalex.org/I181877577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078677016","display_name":"Xiu-Tao Cui","orcid":null},"institutions":[{"id":"https://openalex.org/I4210163926","display_name":"Zhejiang Medicine (China)","ror":"https://ror.org/05h86nk22","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210163926"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiutao Cui","raw_affiliation_strings":["Dewertokin Technology Group Co., Ltd.,Department of General Health,Zhejiang,China","Department of General Health, Dewertokin Technology Group Co., Ltd., Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dewertokin Technology Group Co., Ltd.,Department of General Health,Zhejiang,China","institution_ids":["https://openalex.org/I4210163926"]},{"raw_affiliation_string":"Department of General Health, Dewertokin Technology Group Co., Ltd., Zhejiang, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"4187","last_page":"4194"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":1.0,"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":1.0,"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":0.9973000288009644,"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":0.9965999722480774,"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":0.7657076716423035},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6526274681091309},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5851733684539795},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5495091080665588},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5468369126319885},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.5020215511322021},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.48846641182899475},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4831485152244568},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4772089123725891},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.45359107851982117},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44823944568634033},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.42954060435295105},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3506007194519043},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16983866691589355},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08513280749320984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7657076716423035},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6526274681091309},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5851733684539795},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5495091080665588},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5468369126319885},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.5020215511322021},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.48846641182899475},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4831485152244568},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4772089123725891},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.45359107851982117},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44823944568634033},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.42954060435295105},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3506007194519043},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16983866691589355},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08513280749320984},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata55660.2022.10020269","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata55660.2022.10020269","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W1902237438","https://openalex.org/W1922126009","https://openalex.org/W1971822075","https://openalex.org/W1981283549","https://openalex.org/W1998042868","https://openalex.org/W2008806374","https://openalex.org/W2105482032","https://openalex.org/W2127141656","https://openalex.org/W2140132917","https://openalex.org/W2144554289","https://openalex.org/W2146835493","https://openalex.org/W2194187530","https://openalex.org/W2294053032","https://openalex.org/W2343052201","https://openalex.org/W2593572697","https://openalex.org/W2745439869","https://openalex.org/W2750938222","https://openalex.org/W2752225195","https://openalex.org/W2785769188","https://openalex.org/W2788069964","https://openalex.org/W2795619303","https://openalex.org/W2810983211","https://openalex.org/W2896457183","https://openalex.org/W2963233387","https://openalex.org/W2963327605","https://openalex.org/W2963517393","https://openalex.org/W2963526661","https://openalex.org/W2963712589","https://openalex.org/W2965066169","https://openalex.org/W2972995428","https://openalex.org/W2978036638","https://openalex.org/W2998382406","https://openalex.org/W3003642782","https://openalex.org/W3004846386","https://openalex.org/W3013224334","https://openalex.org/W3015688946","https://openalex.org/W3034447740","https://openalex.org/W3043311956","https://openalex.org/W3096609285","https://openalex.org/W3106271744","https://openalex.org/W3106728613","https://openalex.org/W4287704453","https://openalex.org/W4295312788","https://openalex.org/W6618372016","https://openalex.org/W6744310024","https://openalex.org/W6755207826","https://openalex.org/W6766978945","https://openalex.org/W6771915120","https://openalex.org/W6781533629","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W3163712264","https://openalex.org/W4306707571","https://openalex.org/W3179897446","https://openalex.org/W2970150031","https://openalex.org/W4309224528","https://openalex.org/W1562999394","https://openalex.org/W4392445496","https://openalex.org/W4362605793","https://openalex.org/W2980285880","https://openalex.org/W3035903760"],"abstract_inverted_index":{"Scene":[0],"text":[1,12,20,25,112],"recognition":[2,13,113],"is":[3,26,107],"considered":[4],"as":[5],"a":[6,103],"sequence":[7],"labeling":[8],"problem.":[9],"For":[10],"the":[11,15,18,23,30,35,43,62,70,78,86,110,137,141,146],"task,":[14],"alignment":[16,56,131],"between":[17],"scene":[19,111],"image":[21,36],"and":[22,82,101,127],"output":[24],"coincident,":[27],"which":[28,53,106],"means":[29],"latter":[31],"characters":[32],"corresponding":[33],"to":[34,55,69,84,89],"region":[37],"will":[38],"also":[39],"be":[40],"behind.":[41],"However,":[42],"existing":[44,147],"global":[45,87,148],"attention-based":[46],"method":[47,144],"focuses":[48],"too":[49],"much":[50],"irrelevant":[51],"information":[52],"leads":[54],"drift.":[57],"Contrary,":[58],"local":[59,79,98,142],"attention":[60,80,88,99,143,149],"selects":[61],"subset":[63],"of":[64,97],"feature":[65],"representation":[66],"most":[67],"relevant":[68],"current":[71],"character.":[72],"In":[73],"this":[74],"paper,":[75],"we":[76,93,118],"explore":[77],"mechanism":[81],"attempt":[83],"replace":[85],"implement":[90],"decoding.":[91],"Therefore,":[92],"revise":[94],"several":[95],"variants":[96],"methods":[100],"provide":[102],"comprehensive":[104],"comparison,":[105],"missing":[108],"in":[109],"literature":[114],"so":[115],"far.":[116],"Specially,":[117],"introduce":[119],"two":[120],"Heuristic":[121],"approaches":[122],"for":[123],"Local":[124],"Attention":[125],"(HLA)":[126],"prove":[128],"that":[129,140],"monotonic":[130],"improves":[132],"performance":[133],"significantly.":[134],"Evaluations":[135],"on":[136],"benchmarks":[138],"show":[139],"outperforms":[145],"methods.":[150]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}