{"id":"https://openalex.org/W4414359809","doi":"https://doi.org/10.24963/ijcai.2025/465","title":"MHANet: Multi-scale Hybrid Attention Network for Auditory Attention Detection","display_name":"MHANet: Multi-scale Hybrid Attention Network for Auditory Attention Detection","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359809","doi":"https://doi.org/10.24963/ijcai.2025/465"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/465","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5100386342","display_name":"Lu Li","orcid":"https://orcid.org/0000-0003-0434-4284"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lu Li","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University"],"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037493212","display_name":"Cunhang Fan","orcid":"https://orcid.org/0000-0001-6318-8803"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cunhang Fan","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University"],"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412598","display_name":"Hongyu Zhang","orcid":"https://orcid.org/0000-0002-3063-9425"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyu Zhang","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University"],"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100369381","display_name":"Jingjing Zhang","orcid":"https://orcid.org/0000-0002-3430-6329"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Zhang","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University"],"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101869247","display_name":"Xiaoke Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoke Yang","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University"],"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100687249","display_name":"Jian Zhou","orcid":"https://orcid.org/0000-0003-4736-9457"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Zhou","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University"],"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101578581","display_name":"Zhao Lv","orcid":"https://orcid.org/0000-0001-9727-366X"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Lv","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University"],"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University","institution_ids":["https://openalex.org/I143868143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100386342"],"corresponding_institution_ids":["https://openalex.org/I143868143"],"apc_list":null,"apc_paid":null,"fwci":3.2089,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.92649815,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4173","last_page":"4181"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9692999720573425,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9692999720573425,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/electroencephalography","display_name":"Electroencephalography","score":0.620199978351593},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5985999703407288},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5361999869346619},{"id":"https://openalex.org/keywords/attention-network","display_name":"Attention network","score":0.4867999851703644},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4700999855995178},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.40400001406669617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.758899986743927},{"id":"https://openalex.org/C522805319","wikidata":"https://www.wikidata.org/wiki/Q179965","display_name":"Electroencephalography","level":2,"score":0.620199978351593},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5985999703407288},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5361999869346619},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.4867999851703644},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4700999855995178},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4530999958515167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44600000977516174},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.40400001406669617},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.387800008058548},{"id":"https://openalex.org/C2989146674","wikidata":"https://www.wikidata.org/wiki/Q4818236","display_name":"Selective attention","level":3,"score":0.37549999356269836},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.35839998722076416},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3452000021934509},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.271699994802475}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/465","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Auditory":[0],"attention":[1,32,64,75,88,94],"detection":[2],"(AAD)":[3],"aims":[4],"to":[5,47,125],"detect":[6],"the":[7,72,79,115,134,153],"target":[8],"speaker":[9],"in":[10],"a":[11,61],"multi-talker":[12],"environment":[13],"from":[14],"brain":[15],"signals,":[16,43],"such":[17],"as":[18],"electroencephalography":[19],"(EEG),":[20],"which":[21,69],"has":[22],"made":[23],"great":[24],"progress.":[25],"However,":[26],"most":[27,154],"AAD":[28],"methods":[29],"solely":[30],"utilize":[31],"mechanisms":[33],"sequentially":[34],"and":[35,78,89,92,105,122],"overlook":[36],"valuable":[37],"multi-scale":[38,62,73,90,99],"contextual":[39],"information":[40],"within":[41,102],"EEG":[42,103],"limiting":[44],"their":[45],"ability":[46],"capture":[48],"long-short":[49,107],"range":[50,108],"spatiotemporal":[51,80,109,128],"dependencies":[52,110],"simultaneously.":[53,111],"To":[54,112],"address":[55],"these":[56],"issues,":[57],"this":[58],"paper":[59],"proposes":[60],"hybrid":[63,74],"network":[65],"(MHANet)":[66],"for":[67],"AAD,":[68,118],"consists":[70],"of":[71,117,152],"(MHA)":[76],"module":[77],"convolution":[81],"(STC)":[82],"module.":[83],"Specifically,":[84],"MHA":[85],"combines":[86],"channel":[87],"temporal":[91,100,121],"global":[93],"mechanisms.":[95],"This":[96],"effectively":[97],"extracts":[98],"patterns":[101],"signals":[104],"captures":[106],"further":[113],"improve":[114],"performance":[116,139],"STC":[119],"utilizes":[120],"spatial":[123],"convolutions":[124],"aggregate":[126],"expressive":[127],"representations.":[129],"Experimental":[130],"results":[131],"show":[132],"that":[133,151],"proposed":[135],"MHANet":[136],"achieves":[137],"state-of-the-art":[138],"with":[140],"fewer":[141],"trainable":[142],"parameters":[143],"across":[144],"three":[145],"datasets,":[146],"3":[147],"times":[148],"lower":[149],"than":[150],"advanced":[155],"model.":[156],"Code":[157],"is":[158],"available":[159],"at:":[160],"https://github.com/fchest/MHANet.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}
