{"id":"https://openalex.org/W3170936177","doi":"https://doi.org/10.1109/icme51207.2021.9428081","title":"Multimodal Transformer Networks with Latent Interaction for Audio-Visual Event Localization","display_name":"Multimodal Transformer Networks with Latent Interaction for Audio-Visual Event Localization","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3170936177","doi":"https://doi.org/10.1109/icme51207.2021.9428081","mag":"3170936177"},"language":"en","primary_location":{"id":"doi:10.1109/icme51207.2021.9428081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","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/A5088676221","display_name":"Yixuan He","orcid":"https://orcid.org/0000-0003-1865-1699"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixuan He","raw_affiliation_strings":["University of Electronic Science and Technology of China,Center for Future Media &amp; School of Computer Science and Engineering,China","Glasgow College, University of Electronic Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,Center for Future Media &amp; School of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Glasgow College, University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009074046","display_name":"Xing Xu","orcid":"https://orcid.org/0000-0001-5685-3123"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xu","raw_affiliation_strings":["University of Electronic Science and Technology of China,Center for Future Media &amp; School of Computer Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,Center for Future Media &amp; School of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352180","display_name":"Xin Liu","orcid":"https://orcid.org/0000-0002-0011-6260"},"institutions":[{"id":"https://openalex.org/I119045251","display_name":"Huaqiao University","ror":"https://ror.org/03frdh605","country_code":"CN","type":"education","lineage":["https://openalex.org/I119045251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Liu","raw_affiliation_strings":["Huaqiao University,Department of Computer Science","Department of Computer Science, Huaqiao University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huaqiao University,Department of Computer Science","institution_ids":["https://openalex.org/I119045251"]},{"raw_affiliation_string":"Department of Computer Science, Huaqiao University","institution_ids":["https://openalex.org/I119045251"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028245257","display_name":"Weihua Ou","orcid":"https://orcid.org/0000-0001-5241-7703"},"institutions":[{"id":"https://openalex.org/I154893126","display_name":"Guizhou Normal University","ror":"https://ror.org/02x1pa065","country_code":"CN","type":"education","lineage":["https://openalex.org/I154893126"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weihua Ou","raw_affiliation_strings":["Guizhou Normal University,School of Big Data and Computer Science,China","School of Big Data and Computer Science, Guizhou Normal University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guizhou Normal University,School of Big Data and Computer Science,China","institution_ids":["https://openalex.org/I154893126"]},{"raw_affiliation_string":"School of Big Data and Computer Science, Guizhou Normal University, China","institution_ids":["https://openalex.org/I154893126"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019035804","display_name":"Huimin Lu","orcid":"https://orcid.org/0000-0001-9794-3221"},"institutions":[{"id":"https://openalex.org/I207014233","display_name":"Kyushu Institute of Technology","ror":"https://ror.org/02278tr80","country_code":"JP","type":"education","lineage":["https://openalex.org/I207014233"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Huimin Lu","raw_affiliation_strings":["Kyushu Institute of Technology,Department of Mechanical and Control Engineering,Japan","Department of Mechanical and Control Engineering, Kyushu Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyushu Institute of Technology,Department of Mechanical and Control Engineering,Japan","institution_ids":["https://openalex.org/I207014233"]},{"raw_affiliation_string":"Department of Mechanical and Control Engineering, Kyushu Institute of Technology, Japan","institution_ids":["https://openalex.org/I207014233"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8129,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.87700166,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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":0.9955999851226807,"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":0.7686838507652283},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5637795329093933},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5587770938873291},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.553926408290863},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5423744916915894},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5133342146873474},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.4120728373527527},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3876579701900482},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35311293601989746},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.11091303825378418}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7686838507652283},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5637795329093933},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5587770938873291},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.553926408290863},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5423744916915894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5133342146873474},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.4120728373527527},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3876579701900482},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35311293601989746},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.11091303825378418},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme51207.2021.9428081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2157331557","https://openalex.org/W2194775991","https://openalex.org/W2511428026","https://openalex.org/W2896457183","https://openalex.org/W2931433835","https://openalex.org/W2962960500","https://openalex.org/W2964109005","https://openalex.org/W2990113535","https://openalex.org/W2997909293","https://openalex.org/W3014611590","https://openalex.org/W4293665662","https://openalex.org/W4385245566","https://openalex.org/W6637373629","https://openalex.org/W6729831399","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6761338195","https://openalex.org/W6772278063","https://openalex.org/W6775188310"],"related_works":["https://openalex.org/W2354322770","https://openalex.org/W3000097931","https://openalex.org/W1570848052","https://openalex.org/W2373192430","https://openalex.org/W4239268388","https://openalex.org/W1924837940","https://openalex.org/W2379407973","https://openalex.org/W4243305035","https://openalex.org/W2079488604","https://openalex.org/W2125195795"],"abstract_inverted_index":{"The":[0,92,137],"task":[1],"of":[2,127],"audio-visual":[3],"event":[4,14,69,179],"localization":[5,180],"(AVEL)":[6],"aims":[7],"to":[8,88,101,130,146],"localize":[9],"a":[10,16,22,38,54,62,77,97,124],"visible":[11],"and":[12,26,30,50,109,120,162],"audible":[13],"in":[15,53,112],"video.":[17],"Previous":[18],"methods":[19,43],"first":[20],"divide":[21],"video":[23,64],"into":[24,123],"segments":[25,52,122],"then":[27],"fuse":[28,147],"visual":[29,49,108,119],"acoustic":[31],"features":[32],"at":[33],"the":[34,103,118,141,171,178],"segment":[35,114],"level":[36],"via":[37],"co-attention":[39],"mechanism.":[40],"However,":[41],"existing":[42],"mostly":[44],"model":[45,79,95],"relations":[46],"between":[47,106,140,160],"individual":[48,134],"audio":[51,110,121],"limitedly":[55],"short":[56],"period,":[57],"which":[58,116,153],"may":[59],"not":[60],"cover":[61],"longer":[63],"duration":[65],"for":[66,177],"better":[67],"high-level":[68],"information":[70,139,149],"modeling.":[71],"In":[72],"this":[73,90],"paper,":[74],"we":[75],"proposed":[76,93],"novel":[78],"termed":[80],"Multimodal":[81],"Transformer":[82,99],"Network":[83],"with":[84],"Latent":[85],"Interaction":[86],"(MTNLI)":[87],"tackle":[89],"problem.":[91],"MTNLI":[94,165],"employs":[96],"multimodal":[98],"structure":[100],"learn":[102],"cross-modality":[104,138],"relationships":[105],"latent":[107,128,142],"summarizations":[111,143],"long":[113],"sequences,":[115],"summarize":[117],"small":[125],"number":[126],"representations":[129],"avoid":[131],"modeling":[132],"uninformative":[133],"visual-audio":[135],"relations.":[136],"is":[144],"propagated":[145],"valuable":[148],"from":[150],"both":[151],"modalities,":[152],"can":[154],"effectively":[155],"handle":[156],"large":[157],"temporal":[158],"inconsistent":[159],"vision":[161],"audio.":[163],"Our":[164],"method":[166],"achieves":[167],"state-of-the-art":[168],"performance":[169],"on":[170],"benchmark":[172],"AVE":[173],"(Audio-Visual":[174],"Event)":[175],"dataset":[176],"task.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
