{"id":"https://openalex.org/W4372266970","doi":"https://doi.org/10.1109/icassp49357.2023.10095807","title":"Collaborative Audio-Visual Event Localization Based on Sequential Decision and Cross-Modal Consistency","display_name":"Collaborative Audio-Visual Event Localization Based on Sequential Decision and Cross-Modal Consistency","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266970","doi":"https://doi.org/10.1109/icassp49357.2023.10095807"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095807","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095807","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5064028466","display_name":"Yuqian Kuang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqian Kuang","raw_affiliation_strings":["Harbin Institute of Technology,Harbin,China","Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033392371","display_name":"Xiaopeng Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaopeng Fan","raw_affiliation_strings":["Harbin Institute of Technology,Harbin,China","PengCheng Lab, Shenzhen, China","Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"PengCheng Lab, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5543,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.6142132,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"30","issue":null,"first_page":"1","last_page":"5"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9988999962806702,"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":0.9919000267982483,"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":0.8119275569915771},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.733797550201416},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6708184480667114},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6297472715377808},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6274678111076355},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6005299687385559},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.581573486328125},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.556948184967041},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5223007202148438},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.4358668327331543},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39390334486961365},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32759878039360046},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07328370213508606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8119275569915771},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.733797550201416},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6708184480667114},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6297472715377808},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6274678111076355},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6005299687385559},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.581573486328125},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.556948184967041},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5223007202148438},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.4358668327331543},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39390334486961365},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32759878039360046},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07328370213508606},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095807","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095807","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"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":27,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2157331557","https://openalex.org/W2162931300","https://openalex.org/W2255466643","https://openalex.org/W2741307002","https://openalex.org/W2931433835","https://openalex.org/W2964109005","https://openalex.org/W2997909293","https://openalex.org/W3015925607","https://openalex.org/W3021321555","https://openalex.org/W3093287838","https://openalex.org/W3110606395","https://openalex.org/W3118366136","https://openalex.org/W3170717896","https://openalex.org/W3170936177","https://openalex.org/W3175514052","https://openalex.org/W4221139374","https://openalex.org/W4225112989","https://openalex.org/W4309660795","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6683965311","https://openalex.org/W6739901393","https://openalex.org/W6749633790","https://openalex.org/W6780226713","https://openalex.org/W6786949882","https://openalex.org/W6846958374"],"related_works":["https://openalex.org/W2382566571","https://openalex.org/W2349321798","https://openalex.org/W2366686860","https://openalex.org/W3036520466","https://openalex.org/W2350859087","https://openalex.org/W2387118502","https://openalex.org/W4233775131","https://openalex.org/W2391262724","https://openalex.org/W1986903754","https://openalex.org/W2361622496"],"abstract_inverted_index":{"We":[0,110],"focus":[1],"on":[2],"the":[3,13,43,66,80,99,112,119],"audio-visual":[4],"event":[5,20],"(AVE)":[6],"localization":[7,45,82],"task,":[8],"which":[9,53],"refers":[10],"to":[11,91],"locating":[12],"segments":[14,26,56,77],"with":[15,60],"AVE":[16,44,81],"and":[17,132],"identifying":[18],"their":[19,106],"categories.":[21],"Since":[22],"different":[23,29],"event-relevant":[24,54,75],"video":[25,55,76],"often":[27],"describe":[28],"aspects":[30],"of":[31],"an":[32],"AVE,":[33],"they":[34],"can":[35,72],"complement":[36],"each":[37,61],"other.":[38,62],"However,":[39],"current":[40],"approaches":[41],"model":[42],"task":[46,83],"as":[47,84],"a":[48,85],"sequential":[49,86],"classification":[50],"process,":[51],"through":[52],"cannot":[57],"accurately":[58],"collaborate":[59,73],"Therefore,":[63],"we":[64,97],"propose":[65,98,111],"Collaborative":[67,113],"Segments":[68],"Decision":[69,114],"(CSD)":[70],"that":[71,125],"between":[74,94],"by":[78,104,117],"modeling":[79],"decision":[87],"process.":[88],"In":[89],"addition,":[90],"realize":[92],"collaboration":[93],"cross-modal":[95],"features,":[96],"Consistent":[100],"Feature":[101],"Propagation":[102],"(CFP)":[103],"exploiting":[105],"consistency":[107],"over":[108],"time.":[109],"Network":[115],"(CDN)":[116],"combining":[118],"above":[120],"components.":[121],"Experimental":[122],"results":[123],"show":[124],"CDN":[126],"outperforms":[127],"baseline":[128],"methods":[129],"in":[130],"fully":[131],"weakly":[133],"supervised":[134],"settings.":[135]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
