{"id":"https://openalex.org/W4416799620","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249337","title":"Efficient Video to Audio Mapper with Visual Scene Detection","display_name":"Efficient Video to Audio Mapper with Visual Scene Detection","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799620","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249337"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249337","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249337","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5035871063","display_name":"Mingjing Yi","orcid":"https://orcid.org/0009-0008-0765-066X"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjing Yi","raw_affiliation_strings":["Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Digital Innovation Research Center,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Digital Innovation Research Center,China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050545197","display_name":"Y. Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxi Wang","raw_affiliation_strings":["Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Digital Innovation Research Center,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Digital Innovation Research Center,China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351421","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-4073-0273"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Digital Innovation Research Center,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Digital Innovation Research Center,China","institution_ids":["https://openalex.org/I4210159968"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210159968"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1981","last_page":"1985"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.4147000014781952,"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/T10860","display_name":"Speech and Audio Processing","score":0.4147000014781952,"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/T11309","display_name":"Music and Audio Processing","score":0.2718999981880188,"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":0.15160000324249268,"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/high-fidelity","display_name":"High fidelity","score":0.4828999936580658},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46720001101493835},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.41749998927116394},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.38769999146461487},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.37119999527931213},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.36550000309944153},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.3614000082015991},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.35510000586509705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8080000281333923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6585000157356262},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6320000290870667},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.4828999936580658},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46720001101493835},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.41749998927116394},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.37119999527931213},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.36550000309944153},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33649998903274536},{"id":"https://openalex.org/C30814859","wikidata":"https://www.wikidata.org/wiki/Q4119603","display_name":"Video denoising","level":5,"score":0.3285999894142151},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2964000105857849},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28929999470710754},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C151211776","wikidata":"https://www.wikidata.org/wiki/Q2778015","display_name":"Video capture","level":3,"score":0.2858999967575073},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2773999869823456},{"id":"https://openalex.org/C108803254","wikidata":"https://www.wikidata.org/wiki/Q857512","display_name":"Smacker video","level":4,"score":0.2596000134944916},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249337","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249337","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321209","display_name":"Dankook University","ror":"https://ror.org/058pdbn81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2912947616","https://openalex.org/W2963066677","https://openalex.org/W3015371781","https://openalex.org/W4284898017","https://openalex.org/W4312933868","https://openalex.org/W4372260310","https://openalex.org/W4372260387","https://openalex.org/W4372348103","https://openalex.org/W4385988359","https://openalex.org/W4392910528","https://openalex.org/W4393160294","https://openalex.org/W4402727849","https://openalex.org/W4404545746","https://openalex.org/W4411245083"],"related_works":[],"abstract_inverted_index":{"Video-to-audio":[0],"(V2A)":[1],"generation":[2,79],"aims":[3],"to":[4,18,64,76,114],"produce":[5],"corresponding":[6],"audio":[7,45,78],"given":[8],"silent":[9],"video":[10,41,52,139],"inputs.":[11],"This":[12],"task":[13],"is":[14,47,61],"particularly":[15],"challenging":[16],"due":[17],"the":[19,25,37,51,100,116,145],"cross-modality":[20],"and":[21,42,67,133,140,150,155],"sequential":[22],"nature":[23],"of":[24,58,118],"audio-visual":[26],"features":[27],"involved.":[28],"Recent":[29],"works":[30],"have":[31],"made":[32],"significant":[33],"progress":[34],"in":[35,80],"bridging":[36],"domain":[38],"gap":[39],"between":[40,120],"audio,":[43],"generating":[44],"that":[46,109,128],"semantically":[48],"aligned":[49],"with":[50,93],"content.":[53],"However,":[54],"a":[55,72,89,94,111,138],"critical":[56],"limitation":[57],"these":[59],"approaches":[60],"their":[62],"inability":[63],"effectively":[65],"recognize":[66,132],"handle":[68,134],"multiple":[69,121,135],"scenes":[70,136],"within":[71,137],"video,":[73],"often":[74],"leading":[75],"suboptimal":[77],"such":[81],"cases.":[82],"In":[83],"this":[84],"paper,":[85],"we":[86],"first":[87],"reimplement":[88],"state-of-the-art":[90],"V2A":[91,107],"model":[92,108,130],"slightly":[95],"modified":[96],"light-weight":[97],"architecture,":[98],"outperforming":[99],"baseline.":[101],"We":[102],"then":[103],"propose":[104],"an":[105],"improved":[106],"incorporates":[110],"scene":[112],"detector":[113],"address":[115],"challenge":[117],"switching":[119],"visual":[122],"scenes.":[123],"Results":[124],"on":[125],"VGGSound":[126],"show":[127],"our":[129],"can":[131],"achieve":[141],"superior":[142],"performance":[143],"against":[144],"baseline":[146],"for":[147],"both":[148],"fidelity":[149],"relevance.":[151],"The":[152],"demo":[153],"samples":[154],"codes":[156],"are":[157],"available":[158],"at":[159],"https://1mageyi.github.io/V2A-SceneDetector.demo/.":[160]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}