{"id":"https://openalex.org/W4405655750","doi":"https://doi.org/10.1109/iccv51701.2025.01801","title":"AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generation","display_name":"AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405655750","doi":"https://doi.org/10.1109/iccv51701.2025.01801"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.15191","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090496923","display_name":"Moayed Haji-Ali","orcid":"https://orcid.org/0009-0006-8224-5299"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Moayed Haji-Ali","raw_affiliation_strings":["Rice University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rice University","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052645912","display_name":"Willi Menapace","orcid":"https://orcid.org/0000-0002-0715-9300"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Willi Menapace","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021757527","display_name":"Aliaksandr Siarohin","orcid":"https://orcid.org/0000-0001-9252-1775"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aliaksandr Siarohin","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028188014","display_name":"Ivan Skorokhodov","orcid":"https://orcid.org/0000-0002-7611-9310"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ivan Skorokhodov","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115572809","display_name":"Alper Canberk","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alper Canberk","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021774342","display_name":"Kwot Sin Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kwot Sin Lee","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027328044","display_name":"Vicente Ord\u00f3\u00f1ez","orcid":null},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vicente Ordonez","raw_affiliation_strings":["Rice University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rice University","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058028206","display_name":"Sergey Tulyakov","orcid":"https://orcid.org/0000-0003-3465-1592"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sergey Tulyakov","raw_affiliation_strings":["Snap Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Inc","institution_ids":["https://openalex.org/I4210142583"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"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":0.00151569,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19373","last_page":"19385"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9965999722480774,"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":0.9965999722480774,"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/T10860","display_name":"Speech and Audio Processing","score":0.9876000285148621,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9848999977111816,"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/link","display_name":"Link (geometry)","score":0.7348190546035767},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7149103879928589},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5990431308746338},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5027608871459961},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.16783446073532104},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.16449210047721863},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.1166999340057373}],"concepts":[{"id":"https://openalex.org/C2778753846","wikidata":"https://www.wikidata.org/wiki/Q6554239","display_name":"Link (geometry)","level":2,"score":0.7348190546035767},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7149103879928589},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5990431308746338},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5027608871459961},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.16783446073532104},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.16449210047721863},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.1166999340057373},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2412.15191","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.15191","pdf_url":"https://arxiv.org/pdf/2412.15191","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.15191","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.15191","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.15191","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.15191","pdf_url":"https://arxiv.org/pdf/2412.15191","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W1518185400","https://openalex.org/W3200586296","https://openalex.org/W2390279801","https://openalex.org/W4230332972","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W1998033311"],"abstract_inverted_index":{"We":[0],"propose":[1],"AV-Link,":[2],"a":[3,34,76,110],"unified":[4],"framework":[5,32],"for":[6,24,60],"Video-to-Audio":[7],"(A2V)":[8,11],"and":[9,20,44,62,65,102],"Audio-to-Video":[10],"generation":[12],"that":[13,37,56,106],"leverages":[14],"the":[15,85,122],"activations":[16],"of":[17],"frozen":[18],"video":[19,43,89],"audio":[21,45,95],"diffusion":[22,46],"models":[23,47,59],"temporally-aligned":[25,49],"cross-modal":[26],"conditioning.":[27],"The":[28],"key":[29],"to":[30,91,97],"our":[31,107],"is":[33],"Fusion":[35],"Block":[36],"facilitates":[38],"bidirectional":[39],"information":[40],"exchange":[41],"between":[42],"through":[48],"self":[50],"attention":[51],"operations.":[52],"Unlike":[53],"prior":[54],"work":[55],"uses":[57],"dedicated":[58],"A2V":[61],"V2A":[63],"tasks":[64,74],"relies":[66],"on":[67],"pretrained":[68],"feature":[69],"extractors,":[70],"AV-Link":[71],"achieves":[72,109],"both":[73],"in":[75,113],"single":[77],"self-contained":[78],"framework,":[79],"directly":[80],"leveraging":[81],"features":[82,90,96],"obtained":[83],"by":[84],"complementary":[86],"modality":[87],"(i.e.":[88],"generate":[92,98],"audio,":[93],"or":[94],"video).":[99],"Extensive":[100],"automatic":[101],"subjective":[103],"evaluations":[104],"demonstrate":[105],"method":[108],"substantial":[111],"improvement":[112],"audio-video":[114],"synchronization,":[115],"outperforming":[116],"more":[117],"expensive":[118],"baselines":[119],"such":[120],"as":[121],"MovieGen":[123],"video-to-audio":[124],"model.":[125]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
