{"id":"https://openalex.org/W4403792339","doi":"https://doi.org/10.1145/3664647.3680889","title":"MM-LDM: Multi-Modal Latent Diffusion Model for Sounding Video Generation","display_name":"MM-LDM: Multi-Modal Latent Diffusion Model for Sounding Video Generation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792339","doi":"https://doi.org/10.1145/3664647.3680889"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680889","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3680889","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 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3664647.3680889","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101236501","display_name":"Mingzhen Sun","orcid":"https://orcid.org/0000-0002-3010-9432"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"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":true,"raw_author_name":"Mingzhen Sun","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Science, School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Science, School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100683352","display_name":"Weining Wang","orcid":"https://orcid.org/0000-0001-7299-6431"},"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"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weining Wang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Science, School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Science, School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049868894","display_name":"Yanyuan Qiao","orcid":"https://orcid.org/0000-0002-5606-0702"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yanyuan Qiao","raw_affiliation_strings":["University of Adelaide, Adelaide, Australia"],"affiliations":[{"raw_affiliation_string":"University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108253332","display_name":"Jirong Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"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":"Jiahui Sun","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Science, School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Science, School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047329698","display_name":"Zihan Qin","orcid":"https://orcid.org/0009-0002-9872-1975"},"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"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihan Qin","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Science, School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Science, School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040424302","display_name":"Longteng Guo","orcid":"https://orcid.org/0000-0002-4340-4000"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"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":"Longteng Guo","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Science, School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Science, School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103047969","display_name":"Xinxin Zhu","orcid":"https://orcid.org/0000-0002-2142-5580"},"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"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinxin Zhu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Science, School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Science, School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108392430","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0003-0903-9131"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"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":"Jing Liu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Science, School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Science, School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101236501"],"corresponding_institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":1.1206,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.78529742,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"10853","last_page":"10861"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9915000200271606,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9850000143051147,"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/depth-sounding","display_name":"Depth sounding","score":0.7481949329376221},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7025904655456543},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5909034609794617},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5435258746147156},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.2063523530960083},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.13720306754112244},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12389442324638367}],"concepts":[{"id":"https://openalex.org/C55510283","wikidata":"https://www.wikidata.org/wiki/Q1382947","display_name":"Depth sounding","level":2,"score":0.7481949329376221},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7025904655456543},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5909034609794617},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5435258746147156},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.2063523530960083},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.13720306754112244},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12389442324638367},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680889","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3680889","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 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3664647.3680889","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3680889","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 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2593116425","https://openalex.org/W2612690371","https://openalex.org/W3036167779","https://openalex.org/W3092028330","https://openalex.org/W3110013267","https://openalex.org/W3160582690","https://openalex.org/W3177150392","https://openalex.org/W3180355996","https://openalex.org/W3204221554","https://openalex.org/W4212774754","https://openalex.org/W4281485151","https://openalex.org/W4312633146","https://openalex.org/W4312655926","https://openalex.org/W4312933868","https://openalex.org/W4362514612","https://openalex.org/W4386066475","https://openalex.org/W4386071957","https://openalex.org/W4386075767","https://openalex.org/W4386076326","https://openalex.org/W4390872297","https://openalex.org/W4393147998","https://openalex.org/W4393160294","https://openalex.org/W4399766943","https://openalex.org/W4402754198","https://openalex.org/W6779823529","https://openalex.org/W6797906067"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2809612451","https://openalex.org/W1974079146","https://openalex.org/W2373976954","https://openalex.org/W2616411725","https://openalex.org/W2474955975","https://openalex.org/W2383251271","https://openalex.org/W2386558711"],"abstract_inverted_index":{"Sounding":[0],"Video":[1],"Generation":[2],"(SVG)":[3],"is":[4,89],"an":[5],"audio-video":[6],"joint":[7],"generation":[8,179],"task":[9],"challenged":[10],"by":[11,51],"high-dimensional":[12],"signal":[13,95,103],"spaces,":[14],"distinct":[15],"data":[16,50],"formats,":[17],"and":[18,48,79,116,132,146,150,155,176,191],"different":[19],"patterns":[20],"of":[21,46,60,97],"content":[22],"information.":[23],"To":[24],"address":[25],"these":[26],"issues,":[27],"we":[28,63,159],"introduce":[29,64],"a":[30,55,58,65,71,80,139,147,182],"novel":[31],"multi-modal":[32,67],"latent":[33,74],"diffusion":[34],"model":[35],"(MM-LDM)":[36],"for":[37,76,181],"the":[38,44,93,111],"SVG":[39],"task.":[40],"We":[41],"first":[42],"unify":[43],"representation":[45],"audio":[47,172],"video":[49,166,170,174],"converting":[52],"them":[53],"into":[54],"single":[56],"or":[57],"couple":[59],"images.":[61],"Then,":[62],"hierarchical":[66],"autoencoder":[68],"that":[69],"constructs":[70],"low-level":[72],"perceptual":[73],"space":[75,88,96,107],"each":[77,98],"modality":[78,99],"shared":[81],"high-level":[82],"semantic":[83],"feature":[84],"space.":[85],"The":[86,105],"former":[87],"perceptually":[90],"equivalent":[91],"to":[92,109],"raw":[94],"but":[100],"drastically":[101],"reduces":[102],"dimensions.":[104],"latter":[106],"serves":[108],"bridge":[110],"information":[112],"gap":[113],"between":[114],"modalities":[115],"provides":[117],"more":[118],"insightful":[119],"cross-modal":[120],"guidance.":[121],"Our":[122],"proposed":[123],"method":[124,137],"achieves":[125,138],"new":[126],"state-of-the-art":[127],"results":[128],"with":[129],"significant":[130],"quality":[131],"efficiency":[133],"gains.":[134],"Specifically,":[135],"our":[136,186],"comprehensive":[140,183],"improvement":[141],"on":[142,153,163],"all":[143],"evaluation":[144],"metrics":[145],"faster":[148],"training":[149],"sampling":[151],"speed":[152],"Landscape":[154],"AIST++":[156],"datasets.":[157],"Moreover,":[158],"explore":[160],"its":[161],"performance":[162],"open-domain":[164],"sounding":[165,169],"generation,":[167,171],"long":[168],"continuation,":[173,175],"conditional":[177],"single-modal":[178],"tasks":[180],"evaluation,":[184],"where":[185],"MM-LDM":[187],"demonstrates":[188],"exciting":[189],"adaptability":[190],"generalization":[192],"ability.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}