{"id":"https://openalex.org/W4312383651","doi":"https://doi.org/10.1109/tpami.2022.3226328","title":"Semantic and Relation Modulation for Audio-Visual Event Localization","display_name":"Semantic and Relation Modulation for Audio-Visual Event Localization","publication_year":2022,"publication_date":"2022-12-16","ids":{"openalex":"https://openalex.org/W4312383651","doi":"https://doi.org/10.1109/tpami.2022.3226328","pmid":"https://pubmed.ncbi.nlm.nih.gov/37015417"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2022.3226328","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3226328","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","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/A5029105574","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0002-3138-0734"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0002-3138-0734","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003217535","display_name":"Zheng-Jun Zha","orcid":"https://orcid.org/0000-0003-2510-8993"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng-Jun Zha","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-2510-8993","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034640518","display_name":"Liang Li","orcid":"https://orcid.org/0000-0001-8437-4824"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Li","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8437-4824","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088031350","display_name":"Xuejin Chen","orcid":"https://orcid.org/0000-0003-0478-7018"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuejin Chen","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-0478-7018","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055469774","display_name":"Jiebo Luo","orcid":"https://orcid.org/0000-0002-4516-9729"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiebo Luo","raw_affiliation_strings":["Department of Computer Science, University of Rochester, Rochester, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-4516-9729","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5219,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.9596714,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"45","issue":"6","first_page":"7711","last_page":"7725"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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/T10860","display_name":"Speech and Audio Processing","score":0.9976999759674072,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9959999918937683,"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":0.7351580262184143},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7205910682678223},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5941707491874695},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5406351685523987},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5380216836929321},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5245604515075684},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5236893892288208},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5001082420349121},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42903101444244385},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.4146222174167633},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3596417307853699},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.20488515496253967}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7351580262184143},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7205910682678223},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5941707491874695},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5406351685523987},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5380216836929321},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5245604515075684},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5236893892288208},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5001082420349121},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42903101444244385},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4146222174167633},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3596417307853699},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.20488515496253967},{"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2022.3226328","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2022.3226328","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:37015417","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37015417","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 pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3584809445","display_name":null,"funder_award_id":"U19B2038","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G575396328","display_name":null,"funder_award_id":"62225207","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6052960980","display_name":null,"funder_award_id":"2020AAA0105702","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program 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}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":75,"referenced_works":["https://openalex.org/W1900913856","https://openalex.org/W2014021126","https://openalex.org/W2089468765","https://openalex.org/W2117539524","https://openalex.org/W2123557418","https://openalex.org/W2131042978","https://openalex.org/W2511428026","https://openalex.org/W2526050071","https://openalex.org/W2529163075","https://openalex.org/W2550143307","https://openalex.org/W2593116425","https://openalex.org/W2619697695","https://openalex.org/W2738406145","https://openalex.org/W2755876276","https://openalex.org/W2766402183","https://openalex.org/W2780124704","https://openalex.org/W2809716557","https://openalex.org/W2884460600","https://openalex.org/W2890952074","https://openalex.org/W2893390896","https://openalex.org/W2897492344","https://openalex.org/W2931433835","https://openalex.org/W2944294033","https://openalex.org/W2952435096","https://openalex.org/W2962699416","https://openalex.org/W2962732076","https://openalex.org/W2962865004","https://openalex.org/W2962876901","https://openalex.org/W2963019222","https://openalex.org/W2963115079","https://openalex.org/W2963218389","https://openalex.org/W2963247196","https://openalex.org/W2963321993","https://openalex.org/W2963680395","https://openalex.org/W2963807156","https://openalex.org/W2964107628","https://openalex.org/W2964109005","https://openalex.org/W2964171275","https://openalex.org/W2964207404","https://openalex.org/W2964214371","https://openalex.org/W2964216549","https://openalex.org/W2964345931","https://openalex.org/W2981851635","https://openalex.org/W2982619606","https://openalex.org/W2983918066","https://openalex.org/W2986407524","https://openalex.org/W2990113535","https://openalex.org/W2997909293","https://openalex.org/W3015925607","https://openalex.org/W3093287838","https://openalex.org/W3100481960","https://openalex.org/W3102619627","https://openalex.org/W3108367559","https://openalex.org/W3116298410","https://openalex.org/W3118366136","https://openalex.org/W3168126734","https://openalex.org/W3170088426","https://openalex.org/W3175514052","https://openalex.org/W3214311327","https://openalex.org/W3214808272","https://openalex.org/W4200436929","https://openalex.org/W4213183958","https://openalex.org/W4221153068","https://openalex.org/W4226501520","https://openalex.org/W4289665794","https://openalex.org/W4312356258","https://openalex.org/W6631216910","https://openalex.org/W6637373629","https://openalex.org/W6724997344","https://openalex.org/W6729831399","https://openalex.org/W6729977899","https://openalex.org/W6739901393","https://openalex.org/W6751130187","https://openalex.org/W6753054903","https://openalex.org/W6810168380"],"related_works":["https://openalex.org/W2591697403","https://openalex.org/W2944728705","https://openalex.org/W2904022177","https://openalex.org/W2359348847","https://openalex.org/W2385859805","https://openalex.org/W3011538607","https://openalex.org/W4294432981","https://openalex.org/W4321441197","https://openalex.org/W2530972254","https://openalex.org/W627697492"],"abstract_inverted_index":{"We":[0,47],"study":[1],"the":[2,29,39,59,67,95,100,114,159,163,178,187],"problem":[3],"of":[4,38,90,99,107],"localizing":[5],"audio-visual":[6,167],"events":[7],"that":[8,183],"are":[9],"both":[10,191],"audible":[11],"and":[12,22,25,42,52,62,71,83,112,127,138,154,195],"visible":[13],"in":[14,190],"a":[15,49,91,122,128],"video.":[16],"Existing":[17],"works":[18],"focus":[19],"on":[20,177],"encoding":[21],"aligning":[23],"audio":[24],"visual":[26],"features":[27,89,106,160],"at":[28],"segment":[30,130],"level":[31],"while":[32],"neglecting":[33],"informative":[34],"correlation":[35,61,164],"between":[36,43,142,148,155],"segments":[37,150],"two":[40,108],"modalities":[41,109],"multi-scale":[44,123,135],"event":[45,136,172,193],"proposals.":[46],"propose":[48,80,121],"novel":[50],"Semantic":[51],"Relation":[53],"Modulation":[54],"Network":[55],"(SRMN)":[56],"to":[57,65,133],"learn":[58],"above":[60],"leverage":[63],"it":[64],"modulate":[66],"related":[68],"auditory,":[69],"visual,":[70],"fused":[72],"features.":[73],"In":[74],"particular,":[75],"for":[76],"semantic":[77,97],"modulation,":[78,119],"we":[79,120],"intra-modal":[81],"normalization":[82],"cross-modal":[84,115,143],"normalization.":[85],"The":[86,103],"former":[87],"modulates":[88,105],"single":[92],"modality":[93],"with":[94],"event-relevant":[96],"guidance":[98],"same":[101],"modality.":[102],"latter":[104],"by":[110,162],"establishing":[111],"exploiting":[113],"relationship.":[116],"For":[117],"relation":[118],"proposal":[124,153],"modulating":[125,131],"module":[126,132],"multi-alignment":[129],"introduce":[134],"proposals":[137],"enable":[139],"dense":[140],"matching":[141],"segments,":[144],"which":[145],"strengthen":[146],"correlations":[147],"successive":[149],"within":[151],"one":[152],"all":[156],"segments.":[157],"With":[158],"modulated":[161],"information":[165],"regarding":[166],"events,":[168],"SRMN":[169],"performs":[170],"accurate":[171],"localization.":[173],"Extensive":[174],"experiments":[175],"conducted":[176],"public":[179],"AVE":[180],"dataset":[181],"demonstrate":[182],"our":[184],"method":[185],"outperforms":[186],"state-of-the-art":[188],"methods":[189],"supervised":[192],"localization":[194,197],"cross-modality":[196],"tasks.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":8}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}