{"id":"https://openalex.org/W3214311327","doi":"https://doi.org/10.1109/tmm.2021.3127029","title":"Audio-Visual Event Localization by Learning Spatial and Semantic Co-Attention","display_name":"Audio-Visual Event Localization by Learning Spatial and Semantic Co-Attention","publication_year":2021,"publication_date":"2021-11-15","ids":{"openalex":"https://openalex.org/W3214311327","doi":"https://doi.org/10.1109/tmm.2021.3127029","mag":"3214311327"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2021.3127029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3127029","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/A5082078673","display_name":"Cheng Xue","orcid":"https://orcid.org/0000-0001-9667-623X"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Xue","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100681425","display_name":"Xionghu Zhong","orcid":"https://orcid.org/0000-0002-7533-2347"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xionghu Zhong","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-7533-2347","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076011239","display_name":"Minjie Cai","orcid":"https://orcid.org/0000-0002-6688-3710"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minjie Cai","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-6688-3710","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353508","display_name":"Hao Chen","orcid":"https://orcid.org/0000-0001-9857-6283"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Chen","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-9857-6283","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["Center for Vision Speech and Signal Processing, Department of Electrical and Electronic Engineering, University of Surrey, Guildford, U.K"],"raw_orcid":"https://orcid.org/0000-0002-8393-5703","affiliations":[{"raw_affiliation_string":"Center for Vision Speech and Signal Processing, Department of Electrical and Electronic Engineering, University of Surrey, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4435,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.93591437,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"25","issue":null,"first_page":"418","last_page":"429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.9993000030517578,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9909999966621399,"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":0.8618500828742981},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6960331797599792},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6872953772544861},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6195303797721863},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4635113775730133},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.41286855936050415},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37721776962280273},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3528371751308441},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.10552093386650085}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8618500828742981},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6960331797599792},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6872953772544861},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6195303797721863},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4635113775730133},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.41286855936050415},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37721776962280273},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3528371751308441},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.10552093386650085},{"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":2,"locations":[{"id":"doi:10.1109/tmm.2021.3127029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3127029","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"},{"id":"pmh:oai:alma.44SUR_INST:11155590370002346","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7300000190734863,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1556733010","display_name":null,"funder_award_id":"2020JJ5082","funder_id":"https://openalex.org/F4320322843","funder_display_name":"Natural Science Foundation of\u00a0Hunan Province"},{"id":"https://openalex.org/G2989632234","display_name":null,"funder_award_id":"61906064","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3967457896","display_name":"\u57fa\u4e8e\u5206\u5e03\u5f0f\u9ea6\u514b\u98ce\u9635\u5217\u7f51\u7edc\u7684\u4e00\u4f53\u5316\u591a\u58f0\u6e90\u68c0\u6d4b\u3001\u8ddf\u8e2a\u4e0e\u4fe1\u53f7\u5206\u79bb\u7814\u7a76","funder_award_id":"61971186","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"},{"id":"https://openalex.org/F4320322843","display_name":"Natural Science Foundation of\u00a0Hunan Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2022856253","https://openalex.org/W2032337854","https://openalex.org/W2060300932","https://openalex.org/W2088725063","https://openalex.org/W2117539524","https://openalex.org/W2123046721","https://openalex.org/W2123843894","https://openalex.org/W2138621090","https://openalex.org/W2140647972","https://openalex.org/W2146792684","https://openalex.org/W2167734090","https://openalex.org/W2341412280","https://openalex.org/W2526050071","https://openalex.org/W2550143307","https://openalex.org/W2550553598","https://openalex.org/W2558649592","https://openalex.org/W2593116425","https://openalex.org/W2619697695","https://openalex.org/W2752782242","https://openalex.org/W2884585870","https://openalex.org/W2896034938","https://openalex.org/W2896902935","https://openalex.org/W2931433835","https://openalex.org/W2962826786","https://openalex.org/W2962865004","https://openalex.org/W2962960500","https://openalex.org/W2963022469","https://openalex.org/W2963115079","https://openalex.org/W2963680395","https://openalex.org/W2963801643","https://openalex.org/W2964109005","https://openalex.org/W2964891022","https://openalex.org/W2969987364","https://openalex.org/W2990113535","https://openalex.org/W3015597694","https://openalex.org/W3123416659","https://openalex.org/W4294576248","https://openalex.org/W6623517193","https://openalex.org/W6631216910","https://openalex.org/W6637373629","https://openalex.org/W6679436768","https://openalex.org/W6684193366","https://openalex.org/W6719057275","https://openalex.org/W6729831399","https://openalex.org/W6738806211","https://openalex.org/W6739901393","https://openalex.org/W6754048563"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2110523656","https://openalex.org/W1482209366","https://openalex.org/W2521627374"],"abstract_inverted_index":{"This":[0],"work":[1],"aims":[2],"to":[3,85,154,169],"temporally":[4],"localize":[5],"events":[6,23,41],"that":[7,113,151,191],"are":[8,152],"both":[9],"audible":[10],"and":[11,29,49,60,89,95,123,127,146,158,178,201],"visible":[12],"in":[13,53,56,114],"video.":[14],"Previous":[15],"methods":[16],"mainly":[17],"focused":[18],"on":[19,183],"temporal":[20],"modeling":[21],"of":[22,27,42,66,74,103,141],"with":[24],"simple":[25],"fusion":[26,65],"audio":[28,59,94,122],"visual":[30,50,61,96,124],"features.":[31,62],"In":[32,77],"natural":[33],"scenes,":[34],"a":[35,82,142,147],"video":[36],"records":[37],"not":[38],"only":[39],"the":[40,57,67,75,87,93,101,135,156,184,192],"interest":[43],"but":[44],"also":[45],"ambient":[46],"acoustic":[47],"noise":[48],"background,":[51],"resulting":[52],"redundant":[54],"information":[55,120],"raw":[58],"Thus,":[63],"direct":[64],"two":[68],"features":[69,105,125],"often":[70],"causes":[71],"false":[72],"localization":[73,172,177],"events.":[76],"this":[78],"paper,":[79],"we":[80],"propose":[81],"co-attention":[83,137,164],"model":[84,138,155,165],"exploit":[86],"spatial":[88,157,200],"semantic":[90,119,159,202],"correlations":[91],"between":[92,121],"features,":[97],"which":[98],"helps":[99],"guide":[100],"extraction":[102],"discriminative":[104],"for":[106],"better":[107],"event":[108,171,180,187],"localization.":[109,181],"Our":[110],"assumption":[111],"is":[112,139],"an":[115],"audio-visual":[116,186],"event,":[117],"shared":[118],"exists":[126],"can":[128,166],"be":[129,167],"extracted":[130],"by":[131,198],"attention":[132,144,149],"learning.":[133],"Specifically,":[134],"proposed":[136,163,193],"composed":[140],"co-spatial":[143],"module":[145,150],"co-semantic":[148],"used":[153],"correlations,":[160],"respectively.":[161],"The":[162],"applied":[168],"various":[170],"tasks,":[173],"such":[174],"as":[175],"cross-modality":[176],"multimodal":[179],"Experiments":[182],"public":[185],"(AVE)":[188],"dataset":[189],"demonstrate":[190],"method":[194],"achieves":[195],"state-of-the-art":[196],"performance":[197],"learning":[199],"co-attention.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
