{"id":"https://openalex.org/W4385750120","doi":"https://doi.org/10.1145/3581783.3612502","title":"Induction Network: Audio-Visual Modality Gap-Bridging for Self-Supervised Sound Source Localization","display_name":"Induction Network: Audio-Visual Modality Gap-Bridging for Self-Supervised Sound Source Localization","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4385750120","doi":"https://doi.org/10.1145/3581783.3612502"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612502","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612502","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2308.04767","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102771621","display_name":"Tianyu Liu","orcid":"https://orcid.org/0000-0002-9098-5944"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianyu Liu","raw_affiliation_strings":["Northwestern Polytechnical University &amp; Ningbo Institute of Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University &amp; Ningbo Institute of Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100364068","display_name":"Peng Zhang","orcid":"https://orcid.org/0000-0001-9690-7026"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Zhang","raw_affiliation_strings":["Northwestern Polytechnical University &amp; Ningbo Institute of Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University &amp; Ningbo Institute of Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004584268","display_name":"Wei Huang","orcid":"https://orcid.org/0000-0002-0541-8612"},"institutions":[{"id":"https://openalex.org/I141649914","display_name":"Nanchang University","ror":"https://ror.org/042v6xz23","country_code":"CN","type":"education","lineage":["https://openalex.org/I141649914"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Huang","raw_affiliation_strings":["Nanchang University, Nanchang, China"],"affiliations":[{"raw_affiliation_string":"Nanchang University, Nanchang, China","institution_ids":["https://openalex.org/I141649914"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014604035","display_name":"Yufei Zha","orcid":"https://orcid.org/0000-0001-5013-2501"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufei Zha","raw_affiliation_strings":["Northwestern Polytechnical University &amp; Ningbo Institute of Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University &amp; Ningbo Institute of Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006326110","display_name":"Tao You","orcid":"https://orcid.org/0000-0003-0023-7617"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao You","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028235866","display_name":"Yanning Zhang","orcid":"https://orcid.org/0000-0002-2977-8057"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanning Zhang","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102771621"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.5886,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.64510544,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4042","last_page":"4052"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.992900013923645,"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/computer-science","display_name":"Computer science","score":0.7914641499519348},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.645565390586853},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6289681792259216},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5885381102561951},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5636368989944458},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.561561644077301},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.5293691158294678},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5169536471366882},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5095694065093994},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4939008355140686},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4574403762817383},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3281984031200409},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.0931418240070343}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7914641499519348},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.645565390586853},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6289681792259216},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5885381102561951},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5636368989944458},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.561561644077301},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.5293691158294678},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5169536471366882},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5095694065093994},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4939008355140686},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4574403762817383},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3281984031200409},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0931418240070343},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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:10.1145/3581783.3612502","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612502","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2308.04767","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.04767","pdf_url":"https://arxiv.org/pdf/2308.04767","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2308.04767","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.04767","pdf_url":"https://arxiv.org/pdf/2308.04767","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7300000190734863,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G210655010","display_name":null,"funder_award_id":"2021J048","funder_id":"https://openalex.org/F4320332587","funder_display_name":"Natural Science Foundation of Ningbo"},{"id":"https://openalex.org/G2263213080","display_name":null,"funder_award_id":"25522108","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2376276132","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2925634993","display_name":null,"funder_award_id":"61971352","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3444584140","display_name":null,"funder_award_id":"61971352","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G44360340","display_name":null,"funder_award_id":"2021J049","funder_id":"https://openalex.org/F4320332587","funder_display_name":"Natural Science Foundation of Ningbo"},{"id":"https://openalex.org/G4561077893","display_name":null,"funder_award_id":"D5000220190","funder_id":"https://openalex.org/F3516509085","funder_display_name":"Fundamental Research Funds for the Central Universities of Beijing University of Chemical Technology"},{"id":"https://openalex.org/G4841766026","display_name":null,"funder_award_id":"2021J048","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5293425300","display_name":null,"funder_award_id":"D5000220190","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G5789108345","display_name":null,"funder_award_id":"20232010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6058138561","display_name":null,"funder_award_id":", No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7029710954","display_name":null,"funder_award_id":"61971352, 62271239","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7291233177","display_name":null,"funder_award_id":"2021J049","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G827283038","display_name":null,"funder_award_id":"62271239","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F3516509085","display_name":"Fundamental Research Funds for the Central Universities of Beijing University of Chemical Technology","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320332587","display_name":"Natural Science Foundation of Ningbo","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385750120.pdf"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W2046753598","https://openalex.org/W2059447530","https://openalex.org/W2105582566","https://openalex.org/W2108598243","https://openalex.org/W2121947440","https://openalex.org/W2140000690","https://openalex.org/W2158131535","https://openalex.org/W2171819471","https://openalex.org/W2194775991","https://openalex.org/W2235381883","https://openalex.org/W2250384498","https://openalex.org/W2619697695","https://openalex.org/W2796992393","https://openalex.org/W2798991696","https://openalex.org/W2890052321","https://openalex.org/W2962960500","https://openalex.org/W2963680395","https://openalex.org/W2964109005","https://openalex.org/W2979579363","https://openalex.org/W2982619606","https://openalex.org/W2986131686","https://openalex.org/W2997685131","https://openalex.org/W2999905431","https://openalex.org/W3015371781","https://openalex.org/W3035060554","https://openalex.org/W3037195468","https://openalex.org/W3092603041","https://openalex.org/W3094502228","https://openalex.org/W3094550259","https://openalex.org/W3103455452","https://openalex.org/W3105352633","https://openalex.org/W3108367559","https://openalex.org/W3109212767","https://openalex.org/W3123318516","https://openalex.org/W3154807520","https://openalex.org/W3159481202","https://openalex.org/W3162293946","https://openalex.org/W3169318522","https://openalex.org/W3170088426","https://openalex.org/W3171007011","https://openalex.org/W3175300676","https://openalex.org/W3190580390","https://openalex.org/W3215253112","https://openalex.org/W4211090899","https://openalex.org/W4211123385","https://openalex.org/W4212847156","https://openalex.org/W4213271552","https://openalex.org/W4214601882","https://openalex.org/W4221161766","https://openalex.org/W4221161778","https://openalex.org/W4226314236","https://openalex.org/W4286421014","https://openalex.org/W4287240385","https://openalex.org/W4287592659","https://openalex.org/W4296594718","https://openalex.org/W4297808394","https://openalex.org/W4312205418","https://openalex.org/W4312926266","https://openalex.org/W4385245566","https://openalex.org/W4386075532"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W1482209366","https://openalex.org/W2110523656","https://openalex.org/W2521627374","https://openalex.org/W2981954115"],"abstract_inverted_index":{"Self-supervised":[0],"sound":[1,30,93],"source":[2],"localization":[3],"is":[4,70,134,169],"usually":[5],"challenged":[6],"by":[7],"the":[8,36,40,44,59,74,81,88,99,110,117,138,141],"modality":[9,46,75,112,119],"inconsistency.":[10],"In":[11,64,121],"recent":[12],"studies,":[13],"contrastive":[14,127],"learning":[15],"based":[16],"strategies":[17],"have":[18,153],"shown":[19],"promising":[20],"to":[21,39,52,72,113,123,136,159],"establish":[22],"such":[23],"a":[24,104,124,155],"consistent":[25],"correspondence":[26],"between":[27],"audio":[28,86,111],"and":[29,85,149],"sources":[31,94],"in":[32,43,103,163],"visual":[33,84,90,118,125],"scenarios.":[34,166],"Unfortunately,":[35],"insufficient":[37],"attention":[38],"heterogeneity":[41],"influence":[42],"different":[45,164],"features":[47],"still":[48],"limits":[49],"this":[50,65],"scheme":[51],"be":[53,96,114],"further":[54],"improved,":[55],"which":[56,107],"also":[57,108],"becomes":[58],"motivation":[60],"of":[61,83,92,140],"our":[62],"work.":[63],"study,":[66],"an":[67,129],"Induction":[68,101,142],"Network":[69],"proposed":[71],"bridge":[73],"gap":[76],"more":[77],"effectively.":[78],"By":[79],"decoupling":[80],"gradients":[82],"modalities,":[87],"discriminative":[89],"representations":[91],"can":[95],"learned":[97],"with":[98,116],"designed":[100],"Vector":[102],"bootstrap":[105],"manner,":[106],"enables":[109],"aligned":[115],"consistently.":[120],"addition":[122],"weighted":[126],"loss,":[128],"adaptive":[130],"threshold":[131],"selection":[132],"strategy":[133],"introduced":[135],"enhance":[137],"robustness":[139],"Network.":[143],"Substantial":[144],"experiments":[145],"conducted":[146],"on":[147],"SoundNet-Flickr":[148],"VGG-Sound":[150],"Source":[151],"datasets":[152],"demonstrated":[154],"superior":[156],"performance":[157],"compared":[158],"other":[160],"state-of-the-art":[161],"works":[162],"challenging":[165],"The":[167],"code":[168],"available":[170],"at":[171],"https://github.com/Tahy1/AVIN.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2023-08-11T00:00:00"}
