{"id":"https://openalex.org/W4304080636","doi":"https://doi.org/10.1145/3503161.3548318","title":"Span-based Audio-Visual Localization","display_name":"Span-based Audio-Visual Localization","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304080636","doi":"https://doi.org/10.1145/3503161.3548318"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548318","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548318","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","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/A5101973798","display_name":"Yiling Wu","orcid":"https://orcid.org/0000-0002-7598-7183"},"institutions":[{"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":true,"raw_author_name":"Yiling Wu","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055937409","display_name":"Xinfeng Zhang","orcid":"https://orcid.org/0000-0002-7517-3868"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinfeng Zhang","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100631216","display_name":"Yaowei Wang","orcid":"https://orcid.org/0000-0003-2197-9038"},"institutions":[{"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":"Yaowei Wang","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028597017","display_name":"Qingming Huang","orcid":"https://orcid.org/0000-0001-7542-296X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingming Huang","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101973798"],"corresponding_institution_ids":["https://openalex.org/I4210136793"],"apc_list":null,"apc_paid":null,"fwci":0.854,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.74338791,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1252","last_page":"1260"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9987000226974487,"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":0.9952999949455261,"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":0.7803257703781128},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.605600893497467},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5910419821739197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5874088406562805},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.48118382692337036},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.45121315121650696},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.44154155254364014},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42567169666290283},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.41171592473983765},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3591075539588928},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34333765506744385},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.195695698261261},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.11100643873214722}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803257703781128},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.605600893497467},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5910419821739197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5874088406562805},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.48118382692337036},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.45121315121650696},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.44154155254364014},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42567169666290283},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.41171592473983765},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3591075539588928},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34333765506744385},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.195695698261261},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.11100643873214722},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/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},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548318","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548318","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5296556450","display_name":null,"funder_award_id":"2022M711728","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2551572271","https://openalex.org/W2593116425","https://openalex.org/W2891359673","https://openalex.org/W2931433835","https://openalex.org/W2964010806","https://openalex.org/W2964109005","https://openalex.org/W2970231061","https://openalex.org/W2990113535","https://openalex.org/W2997909293","https://openalex.org/W3034743747","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3093287838","https://openalex.org/W3094550259","https://openalex.org/W3102094970","https://openalex.org/W3173909648","https://openalex.org/W3175514052","https://openalex.org/W4301104990","https://openalex.org/W6745136726"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W2271369634","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W4385009901","https://openalex.org/W4385572700"],"abstract_inverted_index":{"This":[0],"paper":[1],"focuses":[2],"on":[3,159],"the":[4,23,31,44,54,89,95,100,111,119,130,135,141,150,155,160,165],"audio-visual":[5,34,90],"event":[6,24,45,96,101,120],"localization":[7,91],"task":[8,92],"that":[9,80,164],"aims":[10],"to":[11,21,109,117,133,148],"match":[12],"both":[13],"visible":[14],"and":[15,36,68,98,124,137,152],"audible":[16],"components":[17],"in":[18,63],"a":[19,77,104],"video":[20,64],"identify":[22],"of":[25,33,48,57,140,154],"interest.":[26],"Existing":[27],"methods":[28],"primarily":[29],"ignore":[30],"continuity":[32],"events":[35,62],"classify":[37,43],"each":[38,49,58],"segment":[39,50,59],"separately.":[40,60],"They":[41],"either":[42],"category":[46],"score":[47,56],"separately":[51],"or":[52],"calculate":[53],"event-relevant":[55],"However,":[61],"are":[65,127,145],"often":[66],"continuous":[67],"last":[69],"several":[70],"segments.":[71],"Motivated":[72],"by":[73,93],"these,":[74],"we":[75],"propose":[76],"span-based":[78,86],"framework":[79,87],"considers":[81],"consecutive":[82],"segments":[83],"jointly.":[84],"The":[85],"handles":[88],"predicting":[94],"class":[97],"extracting":[99],"span.":[102],"Specifically,":[103],"[CLS]":[105],"token":[106],"is":[107],"applied":[108],"collect":[110],"global":[112],"information":[113],"with":[114],"self-attention":[115],"mechanisms":[116],"predict":[118],"class.":[121],"Relevance":[122],"scores":[123],"positional":[125],"embeddings":[126],"inserted":[128],"into":[129],"span":[131],"predictor":[132],"estimate":[134],"start":[136],"end":[138],"boundaries":[139],"event.":[142],"Multi-modal":[143],"Mixup":[144],"further":[146],"used":[147],"improve":[149],"robustness":[151],"generalization":[153],"model.":[156],"Experiments":[157],"conducted":[158],"AVE":[161],"dataset":[162],"demonstrate":[163],"proposed":[166],"method":[167],"outperforms":[168],"state-of-the-art":[169],"methods.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}