{"id":"https://openalex.org/W7164804530","doi":"https://doi.org/10.1145/3805622.3810680","title":"MultiSoundGen: Video-to-Audio Generation for Multi-Event Scenarios via SlowFast Contrastive Audio-Visual Pretraining and Direct Preference Optimization","display_name":"MultiSoundGen: Video-to-Audio Generation for Multi-Event Scenarios via SlowFast Contrastive Audio-Visual Pretraining and Direct Preference Optimization","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164804530","doi":"https://doi.org/10.1145/3805622.3810680"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810680","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810680","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810680","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047110986","display_name":"Jianxuan Yang","orcid":"https://orcid.org/0000-0002-7329-3671"},"institutions":[{"id":"https://openalex.org/I4210154338","display_name":"Hubei Engineering University","ror":"https://ror.org/05amnwk22","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210154338"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianxuan Yang","raw_affiliation_strings":["MiLM Plus, Xiaomi Inc., Wuhan, Hubei, China"],"raw_orcid":"https://orcid.org/0000-0002-7329-3671","affiliations":[{"raw_affiliation_string":"MiLM Plus, Xiaomi Inc., Wuhan, Hubei, China","institution_ids":["https://openalex.org/I4210154338"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138651727","display_name":"Xiaoran Yang","orcid":"https://orcid.org/0009-0003-0824-9169"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoran Yang","raw_affiliation_strings":["MiLM Plus, Xiaomi Inc. & School of Electronic Information, Wuhan University, Wuhan, Hubei, China"],"raw_orcid":"https://orcid.org/0009-0003-0824-9169","affiliations":[{"raw_affiliation_string":"MiLM Plus, Xiaomi Inc. & School of Electronic Information, Wuhan University, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000000826","display_name":"Lipan Zhang","orcid":"https://orcid.org/0009-0000-8010-9011"},"institutions":[{"id":"https://openalex.org/I4210154338","display_name":"Hubei Engineering University","ror":"https://ror.org/05amnwk22","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210154338"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lipan Zhang","raw_affiliation_strings":["MiLM Plus, Xiaomi Inc., Wuhan, Hubei, China"],"raw_orcid":"https://orcid.org/0009-0006-4810-2948","affiliations":[{"raw_affiliation_string":"MiLM Plus, Xiaomi Inc., Wuhan, Hubei, China","institution_ids":["https://openalex.org/I4210154338"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102509274","display_name":"Xinyue Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210154338","display_name":"Hubei Engineering University","ror":"https://ror.org/05amnwk22","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210154338"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyue Guo","raw_affiliation_strings":["MiLM Plus, Xiaomi Inc., Wuhan, Hubei, China"],"raw_orcid":"https://orcid.org/0009-0009-3548-9874","affiliations":[{"raw_affiliation_string":"MiLM Plus, Xiaomi Inc., Wuhan, Hubei, China","institution_ids":["https://openalex.org/I4210154338"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138639872","display_name":"Zhao Wang","orcid":"https://orcid.org/0009-0005-3549-1270"},"institutions":[{"id":"https://openalex.org/I4210154338","display_name":"Hubei Engineering University","ror":"https://ror.org/05amnwk22","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210154338"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Wang","raw_affiliation_strings":["Mi Ecosystem, Xiaomi Inc., Wuhan, Hubei, China"],"raw_orcid":"https://orcid.org/0009-0005-3549-1270","affiliations":[{"raw_affiliation_string":"Mi Ecosystem, Xiaomi Inc., Wuhan, Hubei, China","institution_ids":["https://openalex.org/I4210154338"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034257180","display_name":"Gongping Huang","orcid":"https://orcid.org/0000-0002-6825-7473"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gongping Huang","raw_affiliation_strings":["School of Electronic Information, Wuhan University, Wuhan, Hubei, China"],"raw_orcid":"https://orcid.org/0000-0002-6825-7473","affiliations":[{"raw_affiliation_string":"School of Electronic Information, Wuhan University, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"1918","last_page":"1926"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.6323000192642212,"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"}},"topics":[{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.6323000192642212,"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":0.10949999839067459,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.08959999680519104,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.4023999869823456},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2957000136375427},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.26910001039505005},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.2533000111579895},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2492000013589859}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5181999802589417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5123000144958496},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.4023999869823456},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2547000050544739},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2492000013589859},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.24420000612735748},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24310000240802765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810680","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810680","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810680","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810680","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2593116425","https://openalex.org/W2760103357","https://openalex.org/W2990503944","https://openalex.org/W3094550259","https://openalex.org/W3163937874","https://openalex.org/W3170088426","https://openalex.org/W3196974791","https://openalex.org/W4312420631","https://openalex.org/W4372260310","https://openalex.org/W4372348103","https://openalex.org/W4386071707","https://openalex.org/W4392904679","https://openalex.org/W4393160294","https://openalex.org/W4393181080","https://openalex.org/W4402727849","https://openalex.org/W4402753790","https://openalex.org/W4403511263","https://openalex.org/W4408345615","https://openalex.org/W4408347324","https://openalex.org/W4408355450","https://openalex.org/W4411245083","https://openalex.org/W4413145987","https://openalex.org/W4415795232","https://openalex.org/W7133208539"],"related_works":[],"abstract_inverted_index":{"Current":[0],"video-to-audio":[1],"(V2A)":[2],"methods":[3,26],"struggle":[4],"in":[5,29,63,97,181],"complex":[6,98],"multi-event":[7,65,99,138,182],"scenarios":[8,10],"(video":[9],"involving":[11],"multiple":[12],"sound":[13,15],"sources,":[14],"events,":[16],"or":[17],"transitions)":[18],"due":[19],"to":[20,58,94,136,162],"two":[21,104],"critical":[22,166],"limitations.":[23],"First,":[24],"existing":[25],"face":[27],"challenges":[28],"precisely":[30],"aligning":[31],"intricate":[32],"semantic":[33,127,192],"information":[34],"together":[35],"with":[36,118],"rapid":[37,130],"dynamic":[38,131],"features.":[39],"Second,":[40],"foundational":[41],"training":[42],"lacks":[43],"quantitative":[44],"preference":[45,83],"optimization":[46,84],"for":[47],"semantic-temporal":[48,167],"alignment":[49],"and":[50,129,149,164,194],"audio":[51,171,190],"quality.":[52,172],"As":[53],"a":[54,75,114,119,159],"result,":[55],"it":[56],"fails":[57],"enhance":[59,95],"integrated":[60],"generation":[61],"quality":[62],"cluttered":[64],"scenes.":[66],"To":[67],"address":[68],"these":[69],"core":[70,126],"limitations,":[71],"this":[72],"study":[73],"proposes":[74],"novel":[76],"V2A":[77,88,147],"framework:":[78],"MultiSoundGen.":[79],"It":[80,155],"introduces":[81],"direct":[82],"(DPO)":[85],"into":[86,146],"the":[87,107,143],"domain,":[89],"leveraging":[90],"audio-visual":[91,134],"pretraining":[92],"(AVP)":[93],"performance":[96,180],"scenarios.":[100],"Our":[101],"contributions":[102],"include":[103],"key":[105],"innovations:":[106],"first":[108],"is":[109],"SlowFast":[110],"Contrastive":[111],"AVP":[112,116],"(SF-CAVP),":[113],"pioneering":[115],"model":[117,161],"unified":[120],"dual-stream":[121],"architecture.":[122],"SF-CAVP":[123,157],"explicitly":[124],"aligns":[125],"representations":[128],"features":[132],"of":[133],"data":[135],"handle":[137],"complexity;":[139],"second,":[140],"we":[141],"integrate":[142],"DPO":[144],"method":[145],"task":[148],"propose":[150],"AVP-Ranked":[151],"Preference":[152],"Optimization":[153],"(AVP-RPO).":[154],"uses":[156],"as":[158],"reward":[160],"quantify":[163],"prioritize":[165],"matches":[168],"while":[169],"enhancing":[170],"Experiments":[173],"demonstrate":[174],"that":[175],"Multi-SoundGen":[176],"achieves":[177],"state-of-the-art":[178],"(SOTA)":[179],"scenarios,":[183],"delivering":[184],"comprehensive":[185],"gains":[186],"across":[187],"distribution":[188],"matching,":[189],"quality,":[191],"alignment,":[193],"temporal":[195],"synchronization.":[196]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-06-16T00:00:00"}