{"id":"https://openalex.org/W3093287838","doi":"https://doi.org/10.1145/3394171.3413581","title":"Cross-Modal Relation-Aware Networks for Audio-Visual Event Localization","display_name":"Cross-Modal Relation-Aware Networks for Audio-Visual Event Localization","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3093287838","doi":"https://doi.org/10.1145/3394171.3413581","mag":"3093287838"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413581","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5019295371","display_name":"Haoming Xu","orcid":"https://orcid.org/0000-0002-8131-7477"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoming Xu","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018498977","display_name":"Runhao Zeng","orcid":"https://orcid.org/0000-0001-8694-4245"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runhao Zeng","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023130798","display_name":"Qingyao Wu","orcid":"https://orcid.org/0000-0002-6771-3932"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyao Wu","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032352025","display_name":"Mingkui Tan","orcid":"https://orcid.org/0000-0001-8856-756X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingkui Tan","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040877128","display_name":"Chuang Gan","orcid":"https://orcid.org/0000-0003-4031-5886"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chuang Gan","raw_affiliation_strings":["MIT-IBM Watson AI Lab, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT-IBM Watson AI Lab, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":94,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3893","last_page":"3901"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9972000122070312,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9919999837875366,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7806984186172485},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7666350603103638},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6919002532958984},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.671058714389801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5672562122344971},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5658140182495117},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.477710485458374},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4618827700614929},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.43208515644073486},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4317302107810974},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.42932164669036865},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3934958577156067},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3645181655883789},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.2951735854148865},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2014518678188324},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.14188745617866516},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.11671453714370728}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7806984186172485},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7666350603103638},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6919002532958984},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.671058714389801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5672562122344971},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5658140182495117},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.477710485458374},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4618827700614929},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.43208515644073486},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4317302107810974},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.42932164669036865},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3934958577156067},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3645181655883789},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2951735854148865},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2014518678188324},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.14188745617866516},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.11671453714370728},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3413581","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1900913856","https://openalex.org/W1938425378","https://openalex.org/W2123557418","https://openalex.org/W2163605009","https://openalex.org/W2184188583","https://openalex.org/W2194775991","https://openalex.org/W2511428026","https://openalex.org/W2526050071","https://openalex.org/W2550143307","https://openalex.org/W2550553598","https://openalex.org/W2593116425","https://openalex.org/W2619697695","https://openalex.org/W2931433835","https://openalex.org/W2950534130","https://openalex.org/W2962699416","https://openalex.org/W2962865004","https://openalex.org/W2963091558","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963420686","https://openalex.org/W2964080601","https://openalex.org/W2964109005","https://openalex.org/W2964110616","https://openalex.org/W2966683369","https://openalex.org/W2970355596","https://openalex.org/W2971680695","https://openalex.org/W2979157532","https://openalex.org/W2980088508","https://openalex.org/W2981586349","https://openalex.org/W2981851635","https://openalex.org/W2981998043","https://openalex.org/W2986407524","https://openalex.org/W2989980422","https://openalex.org/W2990113535","https://openalex.org/W2996173702","https://openalex.org/W2997344006","https://openalex.org/W3017343282","https://openalex.org/W3034655362","https://openalex.org/W3034658206","https://openalex.org/W3035640828","https://openalex.org/W3098204367","https://openalex.org/W3108240585","https://openalex.org/W6631231910"],"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/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"We":[0],"address":[1],"the":[2,10,28,60,67,72,79,90,94,121,125,136,163,174,179,185,194,210],"challenging":[3],"task":[4],"of":[5,31,82,165],"event":[6,15,48,56,116,190,195],"localization,":[7],"which":[8,85],"requires":[9],"machine":[11],"to":[12,74,88,107,119,134,138,147,178],"localize":[13],"an":[14,55,129],"and":[16,45,62,111,152,198,215],"recognize":[17,54],"its":[18,36],"category":[19],"in":[20,99,212],"unconstrained":[21],"videos.":[22],"Most":[23],"existing":[24],"methods":[25],"leverage":[26,108],"only":[27],"visual":[29,61,83,112,142,151],"information":[30,69,113,172],"a":[32,104,156],"video":[33,166],"while":[34],"neglecting":[35],"audio":[37,63,68,110,153,168],"information,":[38],"which,":[39],"however,":[40],"can":[41,70,86],"be":[42],"very":[43],"helpful":[44],"important":[46],"for":[47,114],"localization.":[49,117],"For":[50],"example,":[51],"humans":[52],"often":[53],"by":[57,93,97,124,170,192],"reasoning":[58],"with":[59,155],"content":[64],"simultaneously.":[65],"Moreover,":[66],"guide":[71,135],"model":[73,137],"pay":[75],"more":[76],"attention":[77,132],"on":[78,140,184],"informative":[80],"regions":[81],"scenes,":[84],"help":[87],"reduce":[89,120],"interference":[91,122],"brought":[92,123],"background.":[95],"Motivated":[96],"these,":[98],"this":[100],"paper,":[101],"we":[102,127,145,161,188],"propose":[103,128,146],"relation-aware":[105,157,186],"network":[106],"both":[109,213],"accurate":[115],"Specifically,":[118],"background,":[126],"audio-guided":[130],"spatial-channel":[131],"module":[133],"focus":[139],"event-relevant":[141],"regions.":[143],"Besides,":[144],"build":[148],"connections":[149],"between":[150],"modalities":[154],"module.":[158],"In":[159],"particular,":[160],"learn":[162],"representations":[164],"and/or":[167],"segments":[169],"aggregating":[171],"from":[173],"other":[175],"modality":[176],"according":[177],"cross-modal":[180],"relations.":[181],"Last,":[182],"relying":[183],"representations,":[187],"conduct":[189],"localization":[191],"predicting":[193],"relevant":[196],"score":[197],"classification":[199],"score.":[200],"Extensive":[201],"experimental":[202],"results":[203],"demonstrate":[204],"that":[205],"our":[206],"method":[207],"significantly":[208],"outperforms":[209],"state-of-the-arts":[211],"supervised":[214],"weakly-supervised":[216],"AVE":[217],"settings.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":11}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}