{"id":"https://openalex.org/W4417041436","doi":"https://doi.org/10.1109/iccv51701.2025.01204","title":"ARIG: Autoregressive Interactive Head Generation for Real-Time Conversations","display_name":"ARIG: Autoregressive Interactive Head Generation for Real-Time Conversations","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417041436","doi":"https://doi.org/10.1109/iccv51701.2025.01204"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01204","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.00472","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109056818","display_name":"Ying Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110199","display_name":"Vision Medicals (China)","ror":"https://ror.org/01z86wn38","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210110199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Guo","raw_affiliation_strings":["Vision AI Department,Meituan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vision AI Department,Meituan","institution_ids":["https://openalex.org/I4210110199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450824","display_name":"Xi Liu","orcid":"https://orcid.org/0000-0003-4886-2876"},"institutions":[{"id":"https://openalex.org/I4210110199","display_name":"Vision Medicals (China)","ror":"https://ror.org/01z86wn38","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210110199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Liu","raw_affiliation_strings":["Vision AI Department,Meituan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vision AI Department,Meituan","institution_ids":["https://openalex.org/I4210110199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101806211","display_name":"Zhen Cheng","orcid":"https://orcid.org/0000-0003-0114-7269"},"institutions":[{"id":"https://openalex.org/I4210110199","display_name":"Vision Medicals (China)","ror":"https://ror.org/01z86wn38","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210110199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Zhen","raw_affiliation_strings":["Vision AI Department,Meituan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vision AI Department,Meituan","institution_ids":["https://openalex.org/I4210110199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023232152","display_name":"Pengfei Yan","orcid":"https://orcid.org/0000-0002-8635-8403"},"institutions":[{"id":"https://openalex.org/I4210110199","display_name":"Vision Medicals (China)","ror":"https://ror.org/01z86wn38","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210110199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Yan","raw_affiliation_strings":["Vision AI Department,Meituan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vision AI Department,Meituan","institution_ids":["https://openalex.org/I4210110199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024979844","display_name":"Xiaoming Wei","orcid":"https://orcid.org/0000-0001-6136-5335"},"institutions":[{"id":"https://openalex.org/I4210110199","display_name":"Vision Medicals (China)","ror":"https://ror.org/01z86wn38","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210110199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoming Wei","raw_affiliation_strings":["Vision AI Department,Meituan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vision AI Department,Meituan","institution_ids":["https://openalex.org/I4210110199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210110199"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12956","last_page":"12965"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.33980000019073486,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.33980000019073486,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.12999999523162842,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.11249999701976776,"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/motion","display_name":"Motion (physics)","score":0.6484000086784363},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.6266999840736389},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5346999764442444},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5198000073432922},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.42089998722076416},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.3750999867916107},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.364300012588501}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7472000122070312},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6484000086784363},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6266999840736389},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5346999764442444},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5198000073432922},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5177000164985657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5101000070571899},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.476500004529953},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.42089998722076416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3752000033855438},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.364300012588501},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.28700000047683716},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2840999960899353},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.2612999975681305}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01204","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:2507.00472","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.00472","pdf_url":"https://arxiv.org/pdf/2507.00472","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.00472","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.00472","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.00472","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.00472","pdf_url":"https://arxiv.org/pdf/2507.00472","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417041436.pdf","grobid_xml":"https://content.openalex.org/works/W4417041436.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Face-to-face":[0],"communication,":[1],"as":[2,100,188],"a":[3,101],"common":[4],"human":[5],"activity,":[6],"motivates":[7],"the":[8,29,35,85,174,191,200],"research":[9],"on":[10,28,142],"interactive":[11,129],"head":[12],"generation.":[13],"A":[14],"virtual":[15],"agent":[16],"can":[17],"generate":[18],"motion":[19,32,98,111,194],"responses":[20],"with":[21,88],"both":[22],"listening":[23],"and":[24,38,59,68,133,153,167],"speaking":[25],"capabilities":[26],"based":[27,78,141],"audio":[30],"or":[31,45],"signals":[33,166],"of":[34,170,202],"other":[36],"user":[37],"itself.":[39],"However,":[40],"previous":[41],"clip-wise":[42],"generation":[43,87],"paradigm":[44],"explicit":[46],"listener/speaker":[47],"generator-switching":[48],"methods":[49],"have":[50,198],"limitations":[51],"in":[52,120,183],"future":[53],"signal":[54],"acquisition,":[55],"contextual":[56,155],"behavioral":[57],"understanding,":[58],"switching":[60],"smoothness,":[61],"making":[62],"it":[63],"challenging":[64],"to":[65,83,172],"be":[66],"real-time":[67,86,94],"realistic.":[69],"In":[70,139,160],"this":[71],"paper,":[72],"we":[73,96,109,127,146,162],"propose":[74],"an":[75],"autoregressive":[76],"(AR)":[77],"frame-wise":[79],"framework":[80],"called":[81],"ARIG":[82],"realize":[84],"better":[89],"interaction":[90,125],"realism.":[91],"To":[92,123],"achieve":[93],"generation,":[95],"model":[97],"prediction":[99],"non-vector-quantized":[102],"AR":[103],"process.":[104],"Unlike":[105],"discrete":[106],"codebook-index":[107],"prediction,":[108],"represent":[110],"distribution":[112],"using":[113],"diffusion":[114],"procedure,":[115],"achieving":[116],"more":[117],"accurate":[118],"predictions":[119],"continuous":[121],"space.":[122],"improve":[124],"realism,":[126],"emphasize":[128],"behavior":[130],"understanding":[131,137,156],"(IBU)":[132],"detailed":[134],"conversational":[135],"state":[136],"(CSU).":[138],"IBU,":[140],"dual-track":[143],"dual-modal":[144],"signals,":[145],"summarize":[147],"short-range":[148],"behaviors":[149],"through":[150],"bidirectional-integrated":[151],"learning":[152],"perform":[154],"over":[157],"long":[158],"ranges.":[159],"CSU,":[161],"use":[163],"voice":[164],"activity":[165],"context":[168],"features":[169],"IBU":[171],"understand":[173],"various":[175],"states":[176],"(interruption,":[177],"feedback,":[178],"pause,":[179],"etc.)":[180],"that":[181],"exist":[182],"actual":[184],"conversations.":[185],"These":[186],"serve":[187],"conditions":[189],"for":[190],"final":[192],"progressive":[193],"prediction.":[195],"Extensive":[196],"experiments":[197],"verified":[199],"effectiveness":[201],"our":[203],"model.":[204]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}