{"id":"https://openalex.org/W4211154280","doi":"https://doi.org/10.1109/tmm.2022.3150469","title":"Dense Modality Interaction Network for Audio-Visual Event Localization","display_name":"Dense Modality Interaction Network for Audio-Visual Event Localization","publication_year":2022,"publication_date":"2022-02-12","ids":{"openalex":"https://openalex.org/W4211154280","doi":"https://doi.org/10.1109/tmm.2022.3150469"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3150469","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3150469","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Multimedia","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/A5100435115","display_name":"Shuo Liu","orcid":"https://orcid.org/0000-0002-9707-5572"},"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/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Liu","raw_affiliation_strings":["NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","National Laboratory of Pattern Recognition, Institude of Automation Chinese Academy of Sciences, Beijing, China, 100190"],"raw_orcid":"https://orcid.org/0000-0002-9707-5572","affiliations":[{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institude of Automation Chinese Academy of Sciences, Beijing, China, 100190","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045242540","display_name":"Weize Quan","orcid":"https://orcid.org/0000-0003-0892-581X"},"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/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weize Quan","raw_affiliation_strings":["NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","NLPR, Chinese Academy of Sciences Institute of Automation, 74522 Beijing, China, 100080"],"raw_orcid":"https://orcid.org/0000-0003-0892-581X","affiliations":[{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"NLPR, Chinese Academy of Sciences Institute of Automation, 74522 Beijing, China, 100080","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115594845","display_name":"Chaoqun Wang","orcid":"https://orcid.org/0000-0002-4649-5518"},"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/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoqun Wang","raw_affiliation_strings":["NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390906","display_name":"Yuan Liu","orcid":"https://orcid.org/0000-0002-8880-3451"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Liu","raw_affiliation_strings":["Speech Lab, Alibaba Group, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab, Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395562","display_name":"Bin Liu","orcid":"https://orcid.org/0000-0003-1529-1552"},"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/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Liu","raw_affiliation_strings":["NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Institute of Automation, Chinese Academy of Sciences, 12381 Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1529-1552","affiliations":[{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, 12381 Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003969300","display_name":"Dong\u2010Ming Yan","orcid":"https://orcid.org/0000-0003-2209-2404"},"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/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong-Ming Yan","raw_affiliation_strings":["NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, 74522 Beijing, Beijing, China, 100190"],"raw_orcid":"https://orcid.org/0000-0003-2209-2404","affiliations":[{"raw_affiliation_string":"NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, 74522 Beijing, Beijing, China, 100190","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6764,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.93949269,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"25","issue":null,"first_page":"2734","last_page":"2748"},"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":0.9965999722480774,"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":0.9890000224113464,"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":0.816399097442627},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7816369533538818},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7237310409545898},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6619454622268677},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6287627220153809},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5733872652053833},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5731896758079529},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5136165022850037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4570688009262085},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.4518274664878845},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.42542946338653564},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1444387435913086}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.816399097442627},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7816369533538818},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7237310409545898},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6619454622268677},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6287627220153809},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5733872652053833},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5731896758079529},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5136165022850037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4570688009262085},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.4518274664878845},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.42542946338653564},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1444387435913086},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2022.3150469","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3150469","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5099999904632568},{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.46000000834465027}],"awards":[{"id":"https://openalex.org/G5408962470","display_name":null,"funder_award_id":"62102418","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G835646299","display_name":null,"funder_award_id":"62172415","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1938425378","https://openalex.org/W2103104224","https://openalex.org/W2117539524","https://openalex.org/W2121486117","https://openalex.org/W2134867751","https://openalex.org/W2161226030","https://openalex.org/W2190656909","https://openalex.org/W2474638510","https://openalex.org/W2526050071","https://openalex.org/W2546919788","https://openalex.org/W2550553598","https://openalex.org/W2593116425","https://openalex.org/W2752782242","https://openalex.org/W2783457476","https://openalex.org/W2788241093","https://openalex.org/W2844030168","https://openalex.org/W2884585870","https://openalex.org/W2888471892","https://openalex.org/W2896457183","https://openalex.org/W2901907199","https://openalex.org/W2918609062","https://openalex.org/W2931433835","https://openalex.org/W2953037339","https://openalex.org/W2962850006","https://openalex.org/W2963091558","https://openalex.org/W2963150162","https://openalex.org/W2963383024","https://openalex.org/W2963654155","https://openalex.org/W2963807156","https://openalex.org/W2964109005","https://openalex.org/W2964207404","https://openalex.org/W2964260444","https://openalex.org/W2964345931","https://openalex.org/W2970231061","https://openalex.org/W2981851635","https://openalex.org/W2985076077","https://openalex.org/W2990113535","https://openalex.org/W2990387939","https://openalex.org/W2997909293","https://openalex.org/W3007589762","https://openalex.org/W3007605881","https://openalex.org/W3015925607","https://openalex.org/W3021321555","https://openalex.org/W3035323656","https://openalex.org/W3035333188","https://openalex.org/W3093287838","https://openalex.org/W3105017218","https://openalex.org/W3108240585","https://openalex.org/W3110606395","https://openalex.org/W3118120400","https://openalex.org/W3118548710","https://openalex.org/W3154807520","https://openalex.org/W3175514052","https://openalex.org/W3176649666","https://openalex.org/W4288281388","https://openalex.org/W6631190155","https://openalex.org/W6631216910","https://openalex.org/W6637373629","https://openalex.org/W6683033130","https://openalex.org/W6687239747","https://openalex.org/W6728881024","https://openalex.org/W6739901393","https://openalex.org/W6754416387","https://openalex.org/W6760307120","https://openalex.org/W6765843572","https://openalex.org/W6768454739"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2004831463","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935"],"abstract_inverted_index":{"Human":[0],"perception":[1],"systems":[2],"can":[3,52,278],"integrate":[4],"audio":[5,20,40,82,109,157,173],"and":[6,21,41,83,98,131,140,158,174,208,233,270],"visual":[7,22,42,84,121,159,175],"information":[8,85,110,167],"automatically":[9],"to":[10,26,44,59,79,111,115,119,143,177,186,204,227,243,256],"obtain":[11],"a":[12,73,196,249,264,268],"profound":[13],"understanding":[14],"of":[15,64,147,168,172,267],"real-world":[16],"events.":[17],"Accordingly,":[18],"fusing":[19],"contents":[23],"is":[24,125,184,202,224,263,287],"important":[25],"solve":[27,257],"the":[28,61,65,92,99,113,128,145,150,154,162,166,179,187,206,228,240,258,271,283],"audio-visual":[29,245],"event":[30],"(AVE)":[31],"localization":[32,260],"problem.":[33],"Although":[34],"most":[35],"existing":[36],"works":[37],"have":[38],"fused":[39,209],"modalities":[43],"explore":[45,279],"their":[46,55],"relationship":[47,56],"with":[48],"attention-based":[49],"networks,":[50],"we":[51,71,247],"delve":[53],"into":[54],"more":[57,117,213],"deeply":[58],"improve":[60],"fusion":[62],"capability":[63],"two":[66,88,284],"modalities.":[67,160,285],"In":[68],"this":[69],"paper,":[70],"propose":[72],"dense":[74,100,250],"modality":[75,252],"interaction":[76],"network":[77,114,254],"(DMIN)":[78],"elegantly":[80],"leverage":[81],"by":[86],"integrating":[87],"novel":[89,197],"modules,":[90],"namely,":[91],"audio-guided":[93],"triplet":[94],"attention":[95,102,118,181,189],"(AGTA)":[96],"module":[97,107,152,164,190],"inter-modality":[101],"(DIMA)":[103],"module.":[104],"The":[105,217],"AGTA":[106],"enables":[108],"guide":[112],"pay":[116],"event-relevant":[120],"regions.":[122],"This":[123],"guidance":[124],"conducted":[126],"in":[127,231],"channel,":[129],"temporal,":[130],"spatial":[132,141],"dimensions,":[133],"which":[134,183],"emphasize":[135],"informative":[136],"features,":[137],"temporal":[138],"relationships":[139,281],"regions,":[142],"boost":[144],"capacity":[146],"representations.":[148],"Furthermore,":[149],"DIMA":[151,163,277],"establishes":[153],"dense-relationship":[155],"between":[156,282],"Specifically,":[161],"leverages":[165],"all":[169],"channel":[170],"pairs":[171],"features":[176,210],"formulate":[178],"cross-modality":[180,259],"weight,":[182],"superior":[185,226],"multi-head":[188],"that":[191,221,276],"uses":[192],"limited":[193],"information.":[194],"Moreover,":[195],"unimodal":[198,207],"discrimination":[199],"loss":[200],"(UDL)":[201],"introduced":[203],"exploit":[205],"together":[211],"for":[212],"exact":[214],"AVE":[215,235],"localization.":[216],"experimental":[218,272],"results":[219,273],"show":[220],"our":[222],"method":[223],"remarkably":[225],"state-of-the-art":[229],"methods":[230],"fully-":[232],"weakly-supervised":[234],"settings.":[236],"To":[237],"further":[238,274],"evaluate":[239],"model's":[241],"ability":[242],"build":[244],"connections,":[246],"design":[248],"cross":[251],"relation":[253],"(DCMR)":[255],"task.":[261],"DCMR":[262],"simple":[265],"deformation":[266],"DMIN,":[269],"illustrate":[275],"denser":[280],"Code":[286],"available":[288],"at":[289],"https://github.com/weizequan/DMIN.git.":[290]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}