{"id":"https://openalex.org/W4406258852","doi":"https://doi.org/10.1109/tip.2024.3523799","title":"Attention Guidance by Cross-Domain Supervision Signals for Scene Text Recognition","display_name":"Attention Guidance by Cross-Domain Supervision Signals for Scene Text Recognition","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406258852","doi":"https://doi.org/10.1109/tip.2024.3523799","pmid":"https://pubmed.ncbi.nlm.nih.gov/40030992"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2024.3523799","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3523799","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/A5030044809","display_name":"Fanfu Xue","orcid":"https://orcid.org/0000-0002-6821-2697"},"institutions":[{"id":"https://openalex.org/I28006308","display_name":"Shandong Normal University","ror":"https://ror.org/01wy3h363","country_code":"CN","type":"education","lineage":["https://openalex.org/I28006308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fanfu Xue","raw_affiliation_strings":["School of Information Science and Engineering, Shandong Normal University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-6821-2697","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Shandong Normal University, Jinan, China","institution_ids":["https://openalex.org/I28006308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080244427","display_name":"Jiande Sun","orcid":"https://orcid.org/0000-0001-6157-2051"},"institutions":[{"id":"https://openalex.org/I28006308","display_name":"Shandong Normal University","ror":"https://ror.org/01wy3h363","country_code":"CN","type":"education","lineage":["https://openalex.org/I28006308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiande Sun","raw_affiliation_strings":["School of Information Science and Engineering, Shandong Normal University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0001-6157-2051","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Shandong Normal University, Jinan, China","institution_ids":["https://openalex.org/I28006308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033588228","display_name":"Yaru Xue","orcid":"https://orcid.org/0000-0002-3873-964X"},"institutions":[{"id":"https://openalex.org/I134738993","display_name":"Shandong University of Traditional Chinese Medicine","ror":"https://ror.org/0523y5c19","country_code":"CN","type":"education","lineage":["https://openalex.org/I134738993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaqi Xue","raw_affiliation_strings":["College of Intelligence and Information Engineering, Shandong University of Traditional Chinese Medicine, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Information Engineering, Shandong University of Traditional Chinese Medicine, Jinan, China","institution_ids":["https://openalex.org/I134738993"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100694041","display_name":"Qiang Wu","orcid":"https://orcid.org/0000-0002-6362-5169"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Wu","raw_affiliation_strings":["School of Information Science and Engineering, Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0002-6362-5169","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108048954","display_name":"Lei Zhu","orcid":"https://orcid.org/0000-0002-2993-7142"},"institutions":[{"id":"https://openalex.org/I28006308","display_name":"Shandong Normal University","ror":"https://ror.org/01wy3h363","country_code":"CN","type":"education","lineage":["https://openalex.org/I28006308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhu","raw_affiliation_strings":["School of Information Science and Engineering, Shandong Normal University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-2993-7142","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Shandong Normal University, Jinan, China","institution_ids":["https://openalex.org/I28006308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034967388","display_name":"Xiaojun Chang","orcid":"https://orcid.org/0000-0002-7778-8807"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiaojun Chang","raw_affiliation_strings":["Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-7778-8807","affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022090297","display_name":"Sen-ching S. Cheung","orcid":"https://orcid.org/0000-0002-9207-5514"},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sen-Ching Cheung","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Kentucky, Lexington, KY, USA"],"raw_orcid":"https://orcid.org/0000-0002-9207-5514","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Kentucky, Lexington, KY, USA","institution_ids":["https://openalex.org/I143302722"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5932,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.944028,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"34","issue":null,"first_page":"717","last_page":"728"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9965000152587891,"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":0.9947999715805054,"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":0.7934742569923401},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7205491662025452},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6630089282989502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.556442379951477},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48166096210479736},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48119527101516724},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47101104259490967},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4464496970176697},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4458872079849243},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4269489049911499},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40253064036369324},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1343103051185608}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7934742569923401},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7205491662025452},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6630089282989502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.556442379951477},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48166096210479736},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48119527101516724},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47101104259490967},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4464496970176697},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4458872079849243},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4269489049911499},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40253064036369324},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1343103051185608},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2024.3523799","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3523799","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:40030992","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40030992","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":[{"id":"https://metadata.un.org/sdg/4","score":0.800000011920929,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G8844733660","display_name":null,"funder_award_id":"2023YFE0208800","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1491389626","https://openalex.org/W1971822075","https://openalex.org/W1981283549","https://openalex.org/W1998042868","https://openalex.org/W2008806374","https://openalex.org/W2144554289","https://openalex.org/W2146835493","https://openalex.org/W2194187530","https://openalex.org/W2194775991","https://openalex.org/W2343052201","https://openalex.org/W2750938222","https://openalex.org/W2810983211","https://openalex.org/W2939140832","https://openalex.org/W2952285877","https://openalex.org/W2963233387","https://openalex.org/W2963263347","https://openalex.org/W2963327605","https://openalex.org/W2965066169","https://openalex.org/W2978036638","https://openalex.org/W2997749585","https://openalex.org/W2998382406","https://openalex.org/W3034414401","https://openalex.org/W3035106683","https://openalex.org/W3035449864","https://openalex.org/W3035682985","https://openalex.org/W3083321694","https://openalex.org/W3106271744","https://openalex.org/W3110267192","https://openalex.org/W3160053372","https://openalex.org/W3181186176","https://openalex.org/W3200439183","https://openalex.org/W3202415716","https://openalex.org/W3203616741","https://openalex.org/W3204479434","https://openalex.org/W3206651063","https://openalex.org/W4225562651","https://openalex.org/W4226329156","https://openalex.org/W4229030834","https://openalex.org/W4283821822","https://openalex.org/W4285146136","https://openalex.org/W4295308312","https://openalex.org/W4312298799","https://openalex.org/W4312331087","https://openalex.org/W4312787220","https://openalex.org/W4312843595","https://openalex.org/W4312993511","https://openalex.org/W4319777850","https://openalex.org/W4382202677","https://openalex.org/W4385485738","https://openalex.org/W4385767840","https://openalex.org/W4386065575","https://openalex.org/W4386410320","https://openalex.org/W4390871832","https://openalex.org/W4390872592","https://openalex.org/W6600284362","https://openalex.org/W6629590909","https://openalex.org/W6726497184","https://openalex.org/W6764306230","https://openalex.org/W6788135285"],"related_works":["https://openalex.org/W2161474341","https://openalex.org/W2368824897","https://openalex.org/W1508050556","https://openalex.org/W1910862367","https://openalex.org/W2379365082","https://openalex.org/W2370747590","https://openalex.org/W2030109976","https://openalex.org/W2369260257","https://openalex.org/W2389120450","https://openalex.org/W55249799"],"abstract_inverted_index":{"Despite":[0],"recent":[1],"advances,":[2],"scene":[3],"text":[4,19],"recognition":[5,50,183],"remains":[6],"a":[7,76,147],"challenging":[8],"problem":[9],"due":[10,29],"to":[11,30,42,48,128,132,153,172],"the":[12,27,64,68,80,95,99,104,107,111,123,135,162,174,182,186,196],"significant":[13],"variability,":[14],"irregularity":[15],"and":[16,21,35,115,157,169,194],"distortion":[17],"in":[18,59,134],"appearance":[20],"localization.":[22],"Attention-based":[23],"methods":[24],"have":[25],"become":[26],"mainstream":[28],"their":[31],"superior":[32],"vocabulary":[33],"learning":[34,171],"observation":[36],"ability.":[37],"Nonetheless,":[38],"they":[39],"are":[40,189],"susceptible":[41],"attention":[43,57,96,113,131,140],"drift":[44,58,97],"which":[45,92,179],"can":[46,93],"lead":[47],"word":[49],"errors.":[51],"Most":[52],"works":[53],"focus":[54],"on":[55,191],"correcting":[56],"decoding":[60,155,159],"but":[61],"completely":[62],"ignore":[63],"error":[65],"accumulated":[66],"during":[67],"encoding":[69,101,117,136],"process.":[70,137],"In":[71,161],"this":[72],"paper,":[73],"we":[74,145,165],"propose":[75,146],"novel":[77],"scheme,":[78],"called":[79],"Attention":[81],"Guidance":[82],"by":[83],"Cross-Domain":[84],"Supervision":[85],"Signals":[86],"for":[87],"Scene":[88],"Text":[89],"Recognition":[90],"(ACDS-STR),":[91],"mitigate":[94],"at":[98,204],"feature":[100,116],"stage.":[102],"At":[103],"heart":[105],"of":[106,126,177,185],"proposed":[108],"scheme":[109],"is":[110],"cross-domain":[112],"guidance":[114,168],"fusion":[118],"module":[119],"(CAFM)":[120],"that":[121],"uses":[122],"core":[124,175],"areas":[125,176],"characters":[127],"recursively":[129],"guide":[130],"learn":[133,173],"With":[138],"precise":[139],"information":[141],"sourced":[142],"from":[143],"CAFM,":[144],"non-attention-based":[148],"adaptive":[149],"transformation":[150],"decoder":[151],"(ATD)":[152],"guarantee":[154],"performance":[156,184],"improve":[158],"speed.":[160],"training":[163],"stage,":[164],"fuse":[166],"manual":[167],"subjective":[170],"characters,":[178],"notably":[180],"augments":[181],"model.":[187],"Experiments":[188],"conducted":[190],"public":[192],"benchmarks":[193],"show":[195],"state-of-the-art":[197],"performance.":[198],"The":[199],"source":[200],"will":[201],"be":[202],"available":[203],"https://github.com/xuefanfu/ACDS-STR.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
