{"id":"https://openalex.org/W4225262244","doi":"https://doi.org/10.1109/icassp43922.2022.9746345","title":"MS-ROCANet: Multi-Scale Residual Orthogonal-Channel Attention Network for Scene Text Detection","display_name":"MS-ROCANet: Multi-Scale Residual Orthogonal-Channel Attention Network for Scene Text Detection","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225262244","doi":"https://doi.org/10.1109/icassp43922.2022.9746345"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746345","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100619673","display_name":"Jinpeng Liu","orcid":"https://orcid.org/0000-0002-3071-4499"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinpeng Liu","raw_affiliation_strings":["SouthWest University,College of Computer and Information Science,Chongqing,China","College of Computer and Information Science, SouthWest University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SouthWest University,College of Computer and Information Science,Chongqing,China","institution_ids":["https://openalex.org/I142108993"]},{"raw_affiliation_string":"College of Computer and Information Science, SouthWest University, Chongqing, China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101879872","display_name":"Song Wu","orcid":"https://orcid.org/0000-0002-1792-5216"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song Wu","raw_affiliation_strings":["SouthWest University,College of Computer and Information Science,Chongqing,China","College of Computer and Information Science, SouthWest University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SouthWest University,College of Computer and Information Science,Chongqing,China","institution_ids":["https://openalex.org/I142108993"]},{"raw_affiliation_string":"College of Computer and Information Science, SouthWest University, Chongqing, China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011501539","display_name":"Dehong He","orcid":null},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dehong He","raw_affiliation_strings":["SouthWest University,College of Computer and Information Science,Chongqing,China","College of Computer and Information Science, SouthWest University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SouthWest University,College of Computer and Information Science,Chongqing,China","institution_ids":["https://openalex.org/I142108993"]},{"raw_affiliation_string":"College of Computer and Information Science, SouthWest University, Chongqing, China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047341940","display_name":"Guoqiang Xiao","orcid":"https://orcid.org/0000-0003-2165-476X"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoqiang Xiao","raw_affiliation_strings":["SouthWest University,College of Computer and Information Science,Chongqing,China","College of Computer and Information Science, SouthWest University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SouthWest University,College of Computer and Information Science,Chongqing,China","institution_ids":["https://openalex.org/I142108993"]},{"raw_affiliation_string":"College of Computer and Information Science, SouthWest University, Chongqing, China","institution_ids":["https://openalex.org/I142108993"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I142108993"],"apc_list":null,"apc_paid":null,"fwci":0.3698,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.65638767,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2200","last_page":"2204"},"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9887999892234802,"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":0.986299991607666,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.8461794853210449},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8251416087150574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5511743426322937},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5368251204490662},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5306823253631592},{"id":"https://openalex.org/keywords/text-detection","display_name":"Text detection","score":0.492269903421402},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4794536828994751},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.47466471791267395},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4646645784378052},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.453653484582901},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.41192150115966797},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3951635956764221},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38274937868118286},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3714527487754822},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36954838037490845},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.20800462365150452},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19786477088928223},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07740595936775208}],"concepts":[{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.8461794853210449},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8251416087150574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5511743426322937},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5368251204490662},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5306823253631592},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.492269903421402},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4794536828994751},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.47466471791267395},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4646645784378052},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.453653484582901},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.41192150115966797},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3951635956764221},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38274937868118286},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3714527487754822},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36954838037490845},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.20800462365150452},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19786477088928223},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07740595936775208},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746345","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2144554289","https://openalex.org/W2565639579","https://openalex.org/W2810028092","https://openalex.org/W2914492226","https://openalex.org/W2953606406","https://openalex.org/W2953894958","https://openalex.org/W2963299604","https://openalex.org/W2963353821","https://openalex.org/W2963647456","https://openalex.org/W2967615747","https://openalex.org/W2991626090","https://openalex.org/W2997371611","https://openalex.org/W2998621280","https://openalex.org/W3034514377","https://openalex.org/W3034792612","https://openalex.org/W3035679705","https://openalex.org/W3093046205","https://openalex.org/W3181016597","https://openalex.org/W3190216403","https://openalex.org/W6745516741","https://openalex.org/W6781850746","https://openalex.org/W6800092589"],"related_works":["https://openalex.org/W2560215812","https://openalex.org/W2949601986","https://openalex.org/W2788972299","https://openalex.org/W2521347458","https://openalex.org/W2498789492","https://openalex.org/W2729981612","https://openalex.org/W4233449973","https://openalex.org/W2925692864","https://openalex.org/W2768526084","https://openalex.org/W3011293149"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks-based":[2],"scene":[3,16,48],"text":[4,17,27,49,132],"detection":[5,18],"has":[6],"obtained":[7],"increasing":[8],"attention":[9],"in":[10],"recent":[11],"years.":[12],"However,":[13],"the":[14,23,43,112],"existing":[15],"methods":[19],"cannot":[20],"effectively":[21],"solve":[22],"problem":[24],"of":[25,47,70,115,129],"unclear":[26],"features.":[28],"In":[29],"this":[30],"paper,":[31],"a":[32,52,63,71,78,93,97,127],"Multi-scale":[33],"Residual":[34,72,79],"Orthogonal-Channel":[35],"Attention":[36,66,74,81],"Network":[37],"(MS-ROCANet)":[38],"is":[39,55,84,102],"proposed":[40,103],"to":[41,57,104,111],"improve":[42],"recall":[44],"and":[45,77,136],"accuracy":[46],"detection.":[50,133],"Specifically,":[51],"Detail-aware":[53],"FPN":[54],"designed":[56],"capture":[58],"more":[59],"detailed":[60],"information.":[61],"Then,":[62],"Shared":[64],"Composite":[65],"Head":[67],"(SCAH)":[68],"consists":[69],"Orthogonal":[73],"Module":[75],"(ROAM),":[76],"Channel":[80],"Block":[82],"(RCAB)":[83],"proposed.":[85],"It":[86],"can":[87],"enhance":[88],"textual":[89],"region":[90],"features":[91],"at":[92,140],"multi-scale":[94],"level.":[95],"Finally,":[96],"global":[98,106],"context":[99],"extraction":[100],"module":[101],"obtain":[105],"contextual":[107],"information":[108],"after":[109],"referring":[110],"core":[113],"idea":[114],"Transformer.":[116],"Extensive":[117],"experiments":[118],"demonstrated":[119],"that":[120],"our":[121],"MS-ROCANet":[122],"achieved":[123],"competitive":[124],"results":[125],"on":[126],"variety":[128],"baselines":[130],"for":[131],"The":[134],"codes":[135],"models":[137],"are":[138],"available":[139],"https://github.com/ASentry/MS-ROCANet":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}