{"id":"https://openalex.org/W2990113535","doi":"https://doi.org/10.1109/iccv.2019.00639","title":"Dual Attention Matching for Audio-Visual Event Localization","display_name":"Dual Attention Matching for Audio-Visual Event Localization","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2990113535","doi":"https://doi.org/10.1109/iccv.2019.00639","mag":"2990113535"},"language":"en","primary_location":{"id":"doi:10.1109/iccv.2019.00639","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2019.00639","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10453/137951","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100324098","display_name":"Yu Wu","orcid":"https://orcid.org/0000-0002-1680-8253"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]},{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU","CN"],"is_corresponding":true,"raw_author_name":"Yu Wu","raw_affiliation_strings":["Baidu Research","ReLER, University of Technology Sydney"],"affiliations":[{"raw_affiliation_string":"Baidu Research","institution_ids":["https://openalex.org/I98301712"]},{"raw_affiliation_string":"ReLER, University of Technology Sydney","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043617790","display_name":"Linchao Zhu","orcid":"https://orcid.org/0000-0002-4093-7557"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Linchao Zhu","raw_affiliation_strings":["ReLER, University of Technology Sydney"],"affiliations":[{"raw_affiliation_string":"ReLER, University of Technology Sydney","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395035","display_name":"Yan Yan","orcid":"https://orcid.org/0000-0001-9108-6767"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Yan","raw_affiliation_strings":["Texas State University"],"affiliations":[{"raw_affiliation_string":"Texas State University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005421447","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0002-0512-880X"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["ReLER, University of Technology Sydney"],"affiliations":[{"raw_affiliation_string":"ReLER, University of Technology Sydney","institution_ids":["https://openalex.org/I114017466"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100324098"],"corresponding_institution_ids":["https://openalex.org/I114017466","https://openalex.org/I98301712"],"apc_list":null,"apc_paid":null,"fwci":18.6938,"has_fulltext":false,"cited_by_count":219,"citation_normalized_percentile":{"value":0.99622687,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6291","last_page":"6299"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983000159263611,"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":0.9965000152587891,"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":0.7712304592132568},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6687496900558472},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.6268003582954407},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6229762434959412},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6107869744300842},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.599396288394928},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5439299941062927},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5088024735450745},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4984772205352783},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.46446508169174194},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4365866184234619},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4332835078239441},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.41065749526023865},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38785651326179504},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0774875283241272},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.07446882128715515}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7712304592132568},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6687496900558472},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.6268003582954407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6229762434959412},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6107869744300842},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.599396288394928},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5439299941062927},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5088024735450745},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4984772205352783},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.46446508169174194},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4365866184234619},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4332835078239441},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.41065749526023865},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38785651326179504},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0774875283241272},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.07446882128715515},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iccv.2019.00639","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv.2019.00639","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:opus.lib.uts.edu.au:10453/137951","is_oa":true,"landing_page_url":"http://hdl.handle.net/10453/137951","pdf_url":null,"source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":{"id":"pmh:oai:opus.lib.uts.edu.au:10453/137951","is_oa":true,"landing_page_url":"http://hdl.handle.net/10453/137951","pdf_url":null,"source":{"id":"https://openalex.org/S4306401357","display_name":"UTS ePRESS (University of Technology Sydney)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114017466","host_organization_name":"University of Technology Sydney","host_organization_lineage":["https://openalex.org/I114017466"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1523385540","https://openalex.org/W1686810756","https://openalex.org/W2064675550","https://openalex.org/W2105582566","https://openalex.org/W2117539524","https://openalex.org/W2123843894","https://openalex.org/W2131774270","https://openalex.org/W2157331557","https://openalex.org/W2164899449","https://openalex.org/W2341412280","https://openalex.org/W2511428026","https://openalex.org/W2526050071","https://openalex.org/W2550143307","https://openalex.org/W2556930864","https://openalex.org/W2558649592","https://openalex.org/W2593116425","https://openalex.org/W2597655663","https://openalex.org/W2619697695","https://openalex.org/W2626778328","https://openalex.org/W2735159761","https://openalex.org/W2792330714","https://openalex.org/W2796992393","https://openalex.org/W2797733588","https://openalex.org/W2890052321","https://openalex.org/W2905139236","https://openalex.org/W2911400095","https://openalex.org/W2931433835","https://openalex.org/W2952558884","https://openalex.org/W2962756039","https://openalex.org/W2962835968","https://openalex.org/W2962865004","https://openalex.org/W2962960500","https://openalex.org/W2963115079","https://openalex.org/W2963218389","https://openalex.org/W2963386218","https://openalex.org/W2963680395","https://openalex.org/W2964048159","https://openalex.org/W2964109005","https://openalex.org/W2964213933","https://openalex.org/W2964345931","https://openalex.org/W3100115227","https://openalex.org/W3100166939","https://openalex.org/W4293665662","https://openalex.org/W4294576248","https://openalex.org/W4385245566","https://openalex.org/W6631216910","https://openalex.org/W6637373629","https://openalex.org/W6684193366","https://openalex.org/W6725104640","https://openalex.org/W6729831399","https://openalex.org/W6729977899","https://openalex.org/W6735377749","https://openalex.org/W6738806211","https://openalex.org/W6739901393","https://openalex.org/W6747045456","https://openalex.org/W6750591037","https://openalex.org/W6750599028","https://openalex.org/W6754048563","https://openalex.org/W6757408916","https://openalex.org/W6785580342"],"related_works":["https://openalex.org/W2373577936","https://openalex.org/W4221148444","https://openalex.org/W4387678054","https://openalex.org/W2389596151","https://openalex.org/W3095575180","https://openalex.org/W4306784355","https://openalex.org/W2169308097","https://openalex.org/W3091984855","https://openalex.org/W2150768546","https://openalex.org/W2570112143"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"investigate":[4],"the":[5,40,52,67,71,83,107,114,125,130,144,151,155,190,197],"audio-visual":[6,178],"event":[7,19,103,179,186],"localization":[8,180],"problem.":[9],"This":[10],"task":[11],"is":[12,48,111,120],"to":[13,77,94,128],"localize":[14],"a":[15,21,27,78,88,96,159,200],"visible":[16],"and":[17,32,36,54,168],"audible":[18],"in":[20,139,154,158,176],"video.":[22],"Previous":[23],"methods":[24],"first":[25],"divide":[26],"video":[28,98,127],"into":[29],"short":[30],"segments,":[31],"then":[33],"fuse":[34],"visual":[35,53,169],"acoustic":[37,55],"features":[38,69],"at":[39,70],"segment":[41,59,72],"level.":[42],"The":[43],"duration":[44,99],"of":[45,57,66,82,147],"these":[46],"segments":[47,135],"usually":[49],"short,":[50],"making":[51],"feature":[56,146,153],"each":[58],"possibly":[60],"not":[61],"well":[62],"aligned.":[63],"Direct":[64],"concatenation":[65],"two":[68,84],"level":[73],"can":[74,172],"be":[75,137,173],"vulnerable":[76],"minor":[79],"temporal":[80,109,163],"misalignment":[81],"signals.":[85],"We":[86],"propose":[87],"Dual":[89],"Attention":[90],"Matching":[91],"(DAM)":[92],"module":[93],"cover":[95],"longer":[97],"for":[100,141],"better":[101],"high-level":[102,131],"information":[104,110],"modeling,":[105],"while":[106,133],"local":[108,152],"attained":[112],"by":[113,199],"global":[115,145],"cross-check":[116],"mechanism.":[117],"Our":[118],"premise":[119],"that":[121],"one":[122,148],"should":[123,136],"watch":[124],"whole":[126],"understand":[129],"event,":[132],"shorter":[134],"checked":[138],"detail":[140],"localization.":[142,187],"Specifically,":[143],"modality":[149,157],"queries":[150],"other":[156],"bi-directional":[160],"way.":[161],"With":[162],"co-occurrence":[164],"encoded":[165],"between":[166],"auditory":[167],"signals,":[170],"DAM":[171],"readily":[174],"applied":[175],"various":[177],"tasks,":[181],"e.g.,":[182],"cross-modality":[183],"localization,":[184],"supervised":[185],"Experiments":[188],"on":[189],"AVE":[191],"dataset":[192],"show":[193],"our":[194],"method":[195],"outperforms":[196],"state-of-the-art":[198],"large":[201],"margin.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":29},{"year":2024,"cited_by_count":37},{"year":2023,"cited_by_count":39},{"year":2022,"cited_by_count":40},{"year":2021,"cited_by_count":55},{"year":2020,"cited_by_count":17}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
