{"id":"https://openalex.org/W4407760088","doi":"https://doi.org/10.1109/iccv51701.2025.01324","title":"AV-Flow: Transforming Text to Audio-Visual Human-Like Interactions","display_name":"AV-Flow: Transforming Text to Audio-Visual Human-Like Interactions","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4407760088","doi":"https://doi.org/10.1109/iccv51701.2025.01324"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01324","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01324","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/2502.13133","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059880574","display_name":"Aggelina Chatziagapi","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aggelina Chatziagapi","raw_affiliation_strings":["Stony Brook University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081398601","display_name":"Louis\u2010Philippe Morency","orcid":"https://orcid.org/0000-0001-6376-7696"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Louis-Philippe Morency","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016254106","display_name":"Hongyu Gong","orcid":"https://orcid.org/0000-0001-9190-9006"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongyu Gong","raw_affiliation_strings":["Meta AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044917356","display_name":"Michael Zollhoefer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Zollh\u00f6fer","raw_affiliation_strings":["Codec Avatars Lab, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Codec Avatars Lab, Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003241274","display_name":"Dimitris Samaras","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dimitris Samaras","raw_affiliation_strings":["Stony Brook University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112845052","display_name":"Alexander Richard","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Richard","raw_affiliation_strings":["Codec Avatars Lab, Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Codec Avatars Lab, Meta","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5059880574"],"corresponding_institution_ids":["https://openalex.org/I59553526"],"apc_list":null,"apc_paid":null,"fwci":2.0398,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86710625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"14270","last_page":"14282"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.8392999768257141,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12031","display_name":"Speech and dialogue systems","score":0.8392999768257141,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8205999732017517,"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/T12032","display_name":"Multisensory perception and integration","score":0.7615000009536743,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.839332103729248},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.5261313915252686},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5180850028991699},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2967489957809448},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15590310096740723},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.06446173787117004}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.839332103729248},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.5261313915252686},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5180850028991699},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2967489957809448},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15590310096740723},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.06446173787117004}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01324","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01324","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:2502.13133","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.13133","pdf_url":"https://arxiv.org/pdf/2502.13133","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2502.13133","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.13133","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:2502.13133","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.13133","pdf_url":"https://arxiv.org/pdf/2502.13133","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":{"grobid_xml":false,"pdf":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/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128"],"abstract_inverted_index":{"We":[0,34],"introduce":[1],"AV-Flow,":[2],"an":[3,24,113],"audio-visual":[4,123],"generative":[5],"model":[6,93],"that":[7,22,116,133],"animates":[8],"photo-realistic":[9],"4D":[10,141],"talking":[11,142],"avatars":[12],"given":[13],"only":[14],"text":[15,52],"input.":[16],"In":[17,106],"contrast":[18],"to":[19,100,121],"prior":[20,137],"work":[21],"assumes":[23],"existing":[25],"speech":[26,30,37,84],"signal,":[27],"we":[28,131],"synthesize":[29],"and":[31,45,78,81,86,103,119],"vision":[32],"jointly.":[33],"demonstrate":[35],"human-like":[36],"synthesis,":[38],"synchronized":[39,83],"lip":[40],"motion,":[41],"lively":[42],"facial":[43,87],"expressions":[44],"head":[46],"pose;":[47],"all":[48],"generated":[49],"from":[50],"just":[51],"characters.":[53],"The":[54],"core":[55],"premise":[56],"of":[57,64,108,125],"our":[58,65,134],"approach":[59],"lies":[60],"in":[61],"the":[62,76,122],"architecture":[63],"two":[66],"parallel":[67],"diffusion":[68],"transformers.":[69],"Intermediate":[70],"highway":[71],"connections":[72],"ensure":[73],"communication":[74],"between":[75],"audio":[77],"visual":[79],"modalities,":[80],"thus,":[82],"intonation":[85],"dynamics":[88],"(e.g.,":[89],"eyebrow":[90],"motion).":[91],"Our":[92],"is":[94],"trained":[95],"with":[96],"flow":[97],"matching,":[98],"leading":[99],"expressive":[101],"results":[102],"fast":[104],"inference.":[105],"case":[107],"dyadic":[109],"conversations,":[110],"AV-Flow":[111],"produces":[112],"always-on":[114],"avatar,":[115],"actively":[117],"listens":[118],"reacts":[120],"input":[124],"a":[126],"user.":[127],"Through":[128],"extensive":[129],"experiments,":[130],"show":[132],"method":[135],"outperforms":[136],"work,":[138],"synthesizing":[139],"natural-looking":[140],"avatars.":[143],"Project":[144],"page:":[145],"https://aggelinacha.github.io/AV-Flow/":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}
