{"id":"https://openalex.org/W4415535436","doi":"https://doi.org/10.1145/3746027.3758140","title":"Let Your Video Listen to Your Music! -- Beat-Aligned, Content-Preserving Video Editing with Arbitrary Music","display_name":"Let Your Video Listen to Your Music! -- Beat-Aligned, Content-Preserving Video Editing with Arbitrary Music","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415535436","doi":"https://doi.org/10.1145/3746027.3758140"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3758140","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758140","pdf_url":null,"source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3758140","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100390693","display_name":"Xinyu Zhang","orcid":"https://orcid.org/0000-0002-2999-3291"},"institutions":[{"id":"https://openalex.org/I39854758","display_name":"Auckland University of Technology","ror":"https://ror.org/01zvqw119","country_code":"NZ","type":"education","lineage":["https://openalex.org/I39854758"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Xinyu Zhang","raw_affiliation_strings":["The Australian Institute for Machine Learning, Adelaide, SA, Australia and The University of Auckland, Auckland, New Zealand"],"raw_orcid":"https://orcid.org/0000-0002-2999-3291","affiliations":[{"raw_affiliation_string":"The Australian Institute for Machine Learning, Adelaide, SA, Australia and The University of Auckland, Auckland, New Zealand","institution_ids":["https://openalex.org/I39854758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101768095","display_name":"Dong Gong","orcid":"https://orcid.org/0000-0002-2668-9630"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dong Gong","raw_affiliation_strings":["University of New South Wales, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-2668-9630","affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050830643","display_name":"Zicheng Duan","orcid":"https://orcid.org/0000-0002-5681-6960"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The 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":"Zicheng Duan","raw_affiliation_strings":["The University of Adelaide, Adelaide, SA, Australia"],"raw_orcid":"https://orcid.org/0000-0002-5681-6960","affiliations":[{"raw_affiliation_string":"The University of Adelaide, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028024287","display_name":"Anton van den Hengel","orcid":"https://orcid.org/0000-0003-3027-8364"},"institutions":[{"id":"https://openalex.org/I2802355861","display_name":"Australian Institute of Business","ror":"https://ror.org/01wf5jq34","country_code":"AU","type":"education","lineage":["https://openalex.org/I2802355861"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Anton van den Hengel","raw_affiliation_strings":["The Australian Institute for Machine Learning, Adelaide, SA, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3027-8364","affiliations":[{"raw_affiliation_string":"The Australian Institute for Machine Learning, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I2802355861"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070976480","display_name":"Lingqiao Liu","orcid":"https://orcid.org/0000-0003-3584-795X"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The 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":"Lingqiao Liu","raw_affiliation_strings":["The University of Adelaide, Adelaide, SA, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3584-795X","affiliations":[{"raw_affiliation_string":"The University of Adelaide, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I5681781"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32313984,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12140","last_page":"12149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9993000030517578,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9962000250816345,"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/video-editing","display_name":"Video editing","score":0.5110999941825867},{"id":"https://openalex.org/keywords/timestamp","display_name":"Timestamp","score":0.46470001339912415},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4507000148296356},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4422000050544739},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42739999294281006},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4221999943256378},{"id":"https://openalex.org/keywords/motion-compensation","display_name":"Motion compensation","score":0.4081000089645386}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.842199981212616},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.5110999941825867},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.46470001339912415},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4507000148296356},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4422000050544739},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42739999294281006},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4221999943256378},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42160001397132874},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.4081000089645386},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4034000039100647},{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.376800000667572},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3747999966144562},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.29670000076293945},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.27950000762939453},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.25529998540878296},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3758140","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758140","pdf_url":null,"source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3758140","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758140","pdf_url":null,"source":null,"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1973976810","https://openalex.org/W1982145483","https://openalex.org/W1992941345","https://openalex.org/W2052872069","https://openalex.org/W2163301185","https://openalex.org/W2564353236","https://openalex.org/W2586846154","https://openalex.org/W2766606815","https://openalex.org/W2811167645","https://openalex.org/W2886184661","https://openalex.org/W3008003211","https://openalex.org/W3010876998","https://openalex.org/W3024979138","https://openalex.org/W4283372749","https://openalex.org/W4362467713","https://openalex.org/W4377010269","https://openalex.org/W4385287644","https://openalex.org/W4385668779","https://openalex.org/W4386076291"],"related_works":[],"abstract_inverted_index":{"Aligning":[0],"the":[1,82,95,118,127,136,179,197,239,259,264],"rhythm":[2,119],"of":[3,120,263],"visual":[4,41,97,129,253],"motion":[5,33,146,208],"in":[6,18,26,44,87,142],"a":[7,10,15,104,121,139,169,193,201,230],"video":[8,28,75,89,114,154,203],"with":[9,117,148,164,226],"given":[11,122],"music":[12,45,77,91,123],"track":[13,124],"is":[14,275],"practical":[16,270],"need":[17],"multimedia":[19],"production,":[20],"yet":[21],"remains":[22],"an":[23],"underexplored":[24],"task":[25,137],"autonomous":[27],"editing.":[29,51,272],"Effective":[30],"alignment":[31,251],"between":[32],"and":[34,40,49,76,106,252],"musical":[35,165],"beats":[36,92],"enhances":[37],"viewer":[38],"engagement":[39],"appeal,":[42],"particularly":[43],"videos,":[46],"promotional":[47],"content,":[48],"cinematic":[50],"Existing":[52],"methods":[53],"typically":[54],"depend":[55],"on":[56,200,229],"labor-intensive":[57],"manual":[58],"cutting,":[59],"speed":[60],"adjustments,":[61],"or":[62],"heuristic-based":[63],"editing":[64],"techniques":[65],"to":[66,90,115,173,205],"achieve":[67,248],"synchronization.":[68],"While":[69],"some":[70],"generative":[71],"models":[72],"handle":[73],"joint":[74],"generation,":[78],"they":[79],"often":[80],"entangle":[81],"two":[83],"modalities,":[84],"limiting":[85],"flexibility":[86],"aligning":[88,145],"while":[93,125],"preserving":[94,126,178],"full":[96],"content.":[98,130,183],"In":[99],"this":[100],"paper,":[101],"we":[102,134,157,191],"propose":[103],"novel":[105],"efficient":[107],"framework-termed":[108],"MVAA":[109],"(Music-Video":[110],"Auto-Alignment)-that":[111],"automatically":[112],"edits":[113],"align":[116],"original":[128,180],"To":[131],"enhance":[132],"flexibility,":[133],"modularize":[135],"into":[138],"two-step":[140],"process":[141],"our":[143,245],"MVAA:":[144],"keyframes":[147,160],"audio":[149],"beats,":[150,166],"followed":[151,210],"by":[152,211],"rhythm-aware":[153],"inpainting.":[155],"Specifically,":[156],"first":[158],"insert":[159],"at":[161],"timestamps":[162],"aligned":[163],"then":[167],"use":[168],"frame-conditioned":[170],"diffusion":[171],"model":[172],"generate":[174],"coherent":[175],"intermediate":[176],"frames,":[177],"video's":[181],"semantic":[182],"Since":[184],"comprehensive":[185],"test-time":[186],"training":[187],"can":[188,247],"be":[189],"time-consuming,":[190],"adopt":[192],"two-stage":[194],"strategy:":[195],"pretraining":[196],"inpainting":[198],"module":[199],"small":[202],"set":[204],"learn":[206],"general":[207],"priors,":[209],"rapid":[212],"inference-time":[213],"fine-tuning":[214],"for":[215,269],"video-specific":[216],"adaptation.":[217],"This":[218],"hybrid":[219],"approach":[220,246],"enables":[221],"adaptation":[222],"within":[223],"~10":[224],"minutes":[225],"one":[227],"epoch":[228],"single":[231],"NVIDIA":[232],"4090":[233],"GPU":[234],"using":[235],"CogVideoX-5b-I2V":[236],"[77]":[237],"as":[238],"backbone.":[240],"Extensive":[241],"experiments":[242],"show":[243],"that":[244],"high-quality":[249],"beat":[250],"smoothness.":[254],"User":[255],"studies":[256],"further":[257],"validate":[258],"natural":[260],"rhythmic":[261],"quality":[262],"results,":[265],"confirming":[266],"their":[267],"effectiveness":[268],"music-video":[271],"The":[273],"code":[274],"available":[276],"at:":[277],"zhangxinyu-xyz.github.io/MVAA":[278]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}