{"id":"https://openalex.org/W4408361498","doi":"https://doi.org/10.1145/3721981","title":"Towards Energy-efficient Audio-visual Classification via Multimodal Interactive Spiking Neural Network","display_name":"Towards Energy-efficient Audio-visual Classification via Multimodal Interactive Spiking Neural Network","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408361498","doi":"https://doi.org/10.1145/3721981"},"language":"en","primary_location":{"id":"doi:10.1145/3721981","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3721981","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-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/A5101103928","display_name":"Xu Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xu Liu","raw_affiliation_strings":["Hefei University of Technology, Hefei, China","Hefei University of Technology, China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]},{"raw_affiliation_string":"Hefei University of Technology, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052281951","display_name":"Na Xia","orcid":"https://orcid.org/0000-0001-9502-5558"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Na Xia","raw_affiliation_strings":["Hefei University of Technology, Hefei, China","Hefei University of Technology, China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]},{"raw_affiliation_string":"Hefei University of Technology, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047303316","display_name":"Jinxing Zhou","orcid":"https://orcid.org/0000-0001-6402-7593"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Jinxing Zhou","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates","Mohamed bin Zayed University of Artificial Intelligence, United Arab Emirates"],"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I4210113480"]},{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence, United Arab Emirates","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051302689","display_name":"Zhangbin Li","orcid":"https://orcid.org/0009-0001-2227-8826"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhangbin Li","raw_affiliation_strings":["Hefei University of Technology, Hefei, China","Hefei University of Technology, China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]},{"raw_affiliation_string":"Hefei University of Technology, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059530979","display_name":"Dan Guo","orcid":"https://orcid.org/0000-0003-2594-254X"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]},{"id":"https://openalex.org/I39774598","display_name":"Hefei University","ror":"https://ror.org/01f5rdf64","country_code":"CN","type":"education","lineage":["https://openalex.org/I39774598"]},{"id":"https://openalex.org/I4210137491","display_name":"National Science Centre","ror":"https://ror.org/03ha2q922","country_code":"PL","type":"government","lineage":["https://openalex.org/I4210137491"]}],"countries":["CN","PL"],"is_corresponding":false,"raw_author_name":"Dan Guo","raw_affiliation_strings":["Hefei University of Technology, Hefei, China and Hefei Comprehensive National Science Center, Hefei, China","Hefei University of Technology, China and Hefei Comprehensive National Science Center, China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China and Hefei Comprehensive National Science Center, Hefei, China","institution_ids":["https://openalex.org/I16365422","https://openalex.org/I4210137491","https://openalex.org/I39774598"]},{"raw_affiliation_string":"Hefei University of Technology, China and Hefei Comprehensive National Science Center, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101103928"],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":2.8257,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.88706281,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"21","issue":"5","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.989799976348877,"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"}},{"id":"https://openalex.org/T12032","display_name":"Multisensory perception and integration","score":0.9894999861717224,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9190347194671631},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.564629316329956},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5281845331192017},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5222223997116089},{"id":"https://openalex.org/keywords/spiking-neural-network","display_name":"Spiking neural network","score":0.4451601505279541},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39538949728012085},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37771281599998474},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.35998088121414185}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9190347194671631},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.564629316329956},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5281845331192017},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5222223997116089},{"id":"https://openalex.org/C11731999","wikidata":"https://www.wikidata.org/wiki/Q9067355","display_name":"Spiking neural network","level":3,"score":0.4451601505279541},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39538949728012085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37771281599998474},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.35998088121414185}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3721981","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3721981","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2762492958","display_name":null,"funder_award_id":"2024YFB3311602","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8109548062","display_name":null,"funder_award_id":"JZ2024HGTG0309 and JZ2024AHST0337","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8219533030","display_name":null,"funder_award_id":"61971178, 62272144, and U20A20183","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W2006370340","https://openalex.org/W2030931454","https://openalex.org/W2186222003","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2604292070","https://openalex.org/W2892077605","https://openalex.org/W2964109005","https://openalex.org/W2990793844","https://openalex.org/W3093388624","https://openalex.org/W3170540448","https://openalex.org/W3174906557","https://openalex.org/W3175514052","https://openalex.org/W3214982345","https://openalex.org/W4205811793","https://openalex.org/W4205817612","https://openalex.org/W4214819138","https://openalex.org/W4223904523","https://openalex.org/W4280579728","https://openalex.org/W4283688199","https://openalex.org/W4285239306","https://openalex.org/W4306408041","https://openalex.org/W4309660795","https://openalex.org/W4312383651","https://openalex.org/W4313181051","https://openalex.org/W4319866562","https://openalex.org/W4360612554","https://openalex.org/W4383469171","https://openalex.org/W4383503740","https://openalex.org/W4386076642","https://openalex.org/W4387409844","https://openalex.org/W4387917764","https://openalex.org/W4391216149","https://openalex.org/W4391791458","https://openalex.org/W4392623241","https://openalex.org/W4393159599","https://openalex.org/W4393159836","https://openalex.org/W4399055279","https://openalex.org/W4399399741","https://openalex.org/W4399474077","https://openalex.org/W4400905856","https://openalex.org/W4402874874","https://openalex.org/W4403386295","https://openalex.org/W4403791730"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2393726419"],"abstract_inverted_index":{"The":[0],"Audio-visual":[1],"Classification":[2],"(AVC)":[3],"task":[4],"aims":[5],"to":[6,95,125,144,203,217],"determine":[7],"video":[8],"categories":[9],"by":[10,115],"integrating":[11],"audio":[12,205],"and":[13,34,75,149,170,206,253],"visual":[14,207],"signals.":[15],"Traditional":[16],"methods":[17],"for":[18,58,151,228,236],"AVC":[19,104,153],"leverage":[20],"Artificial":[21],"Neural":[22,45],"Networks":[23,46],"(ANNs)":[24],"that":[25,190],"operate":[26],"on":[27,86,192,243],"floating-point":[28],"features,":[29],"affording":[30],"large":[31],"parameter":[32],"counts":[33],"consuming":[35],"extensive":[36],"energy.":[37],"Recent":[38],"research":[39],"has":[40],"shifted":[41],"towards":[42],"brain-inspired":[43],"Spiking":[44,139],"(SNNs),":[47],"which":[48,168],"transmit":[49],"audiovisual":[50,176],"information":[51],"through":[52],"sparser":[53],"0/1":[54],"spike":[55,78,82,92,173],"features":[56,209,227],"allowing":[57],"better":[59],"energy":[60,254],"efficiency.":[61],"However,":[62],"a":[63,135,162,179,198],"byproduct":[64],"of":[65,99,158,175,188],"such":[66],"sparsity":[67],"is":[68,112],"the":[69,81,96,103,142,152,156,172,185,224],"increased":[70],"difficulty":[71],"in":[72,102,107,120,250],"effectively":[73],"encoding":[74],"utilizing":[76],"these":[77,131],"features.":[79],"Moreover,":[80],"firing":[83],"characteristics":[84],"based":[85],"neuron":[87],"membrane":[88],"potential":[89],"cause":[90],"asynchronous":[91],"activations":[93,174],"due":[94],"heterogeneous":[97],"distributions":[98],"different":[100],"modalities":[101],"task,":[105],"resulting":[106,119],"cross-modal":[108,212],"asynchronization.":[109],"This":[110],"issue":[111],"often":[113],"overlooked":[114],"prior":[116,186],"SNN":[117],"models,":[118],"lower":[121],"classification":[122],"accuracy":[123,148,252],"compared":[124],"traditional":[126],"ANN":[127],"models.":[128],"To":[129],"address":[130],"challenges,":[132],"we":[133,160,215],"present":[134],"new":[136],"Multimodal":[137,163],"Interaction":[138],"Network":[140],"(MISNet),":[141],"first":[143],"successfully":[145],"balance":[146],"both":[147,251],"efficiency":[150],"task.":[154],"As":[155,197],"core":[157],"MISNet,":[159],"propose":[161,216],"Leaky":[164],"Integrate-and-fire":[165],"(MLIF)":[166],"neuron,":[167,181],"coordinates":[169],"synchronizes":[171],"signals":[177],"within":[178],"single":[180],"distinguishing":[182],"it":[183],"from":[184],"paradigm":[187],"SNNs":[189],"relies":[191],"multiple":[193],"separate":[194],"processing":[195],"neurons.":[196],"result,":[199],"our":[200,241],"MISNet":[201],"enables":[202],"generate":[204],"spiking":[208,234],"with":[210],"effective":[211],"fusion.":[213],"Additionally,":[214],"add":[218],"extra":[219],"loss":[220],"regularizations":[221],"before":[222],"fusing":[223],"obtained":[225],"audio-visual":[226,245],"final":[229],"classification,":[230],"thereby":[231],"benefiting":[232],"unimodal":[233],"learning":[235],"multimodal":[237],"interaction.":[238],"We":[239],"evaluate":[240],"method":[242],"five":[244],"datasets,":[246],"demonstrating":[247],"advanced":[248],"performance":[249],"consumption.":[255]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
