{"id":"https://openalex.org/W4414539393","doi":"https://doi.org/10.23919/mva65244.2025.11175115","title":"Data-driven Head Motion Generation through Natural Gaze-Head Coordination","display_name":"Data-driven Head Motion Generation through Natural Gaze-Head Coordination","publication_year":2025,"publication_date":"2025-07-26","ids":{"openalex":"https://openalex.org/W4414539393","doi":"https://doi.org/10.23919/mva65244.2025.11175115"},"language":"en","primary_location":{"id":"doi:10.23919/mva65244.2025.11175115","is_oa":false,"landing_page_url":"https://doi.org/10.23919/mva65244.2025.11175115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 19th International Conference on Machine Vision and Applications (MVA)","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/2605.25810","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100758656","display_name":"Xiaohan Liu","orcid":"https://orcid.org/0000-0002-1154-8122"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xiaohan Liu","raw_affiliation_strings":["The University of Tokyo,Institute of Industrial Science,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Institute of Industrial Science,Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031194653","display_name":"Yilin Wen","orcid":"https://orcid.org/0000-0002-5981-1276"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yilin Wen","raw_affiliation_strings":["The University of Tokyo,Institute of Industrial Science,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Institute of Industrial Science,Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066894394","display_name":"Yusuke Sugano","orcid":"https://orcid.org/0000-0003-4206-710X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Sugano","raw_affiliation_strings":["The University of Tokyo,Institute of Industrial Science,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Institute of Industrial Science,Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T13382","display_name":"Robotics and Automated Systems","score":0.9846000075340271,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9660999774932861,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/motion","display_name":"Motion (physics)","score":0.6833000183105469},{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.619700014591217},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6044999957084656},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5963000059127808},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5584999918937683},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.5054000020027161},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.48910000920295715},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.42730000615119934},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.4016999900341034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7264999747276306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7146000266075134},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6833000183105469},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.619700014591217},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6044999957084656},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5963000059127808},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5803999900817871},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5584999918937683},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.5054000020027161},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.48910000920295715},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.42730000615119934},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.4016999900341034},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.3961000144481659},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.388700008392334},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.37380000948905945},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3653999865055084},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.34279999136924744},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.34209999442100525},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3124000132083893},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.275299996137619},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.23919/mva65244.2025.11175115","is_oa":false,"landing_page_url":"https://doi.org/10.23919/mva65244.2025.11175115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 19th International Conference on Machine Vision and Applications (MVA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2605.25810","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.25810","pdf_url":"https://arxiv.org/pdf/2605.25810","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.2605.25810","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25810","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2605.25810","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.25810","pdf_url":"https://arxiv.org/pdf/2605.25810","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":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414539393.pdf","grobid_xml":"https://content.openalex.org/works/W4414539393.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1531904821","https://openalex.org/W2102530345","https://openalex.org/W2308875002","https://openalex.org/W2805941539","https://openalex.org/W2915250631","https://openalex.org/W2949662773","https://openalex.org/W3005758474","https://openalex.org/W3005863156","https://openalex.org/W3108262631","https://openalex.org/W4221153079","https://openalex.org/W4386071464","https://openalex.org/W4386075862","https://openalex.org/W4386076438"],"related_works":[],"abstract_inverted_index":{"We":[0,71],"present":[1],"the":[2,44,94],"first":[3],"data-driven":[4],"approach":[5,128],"to":[6,76,93],"model":[7,56],"temporal":[8,48],"gaze-head":[9,51],"coordination":[10],"from":[11],"large-scale":[12],"in-the-wild":[13],"facial":[14,78],"videos.":[15],"To":[16,42],"obtain":[17],"training":[18],"data":[19],"for":[20,63,126],"generalizable":[21],"learning,":[22],"we":[23,53,82],"propose":[24],"an":[25,98],"automatic":[26],"pipeline":[27],"that":[28,100],"extracts":[29],"natural":[30,87],"yet":[31,65],"diverse":[32,66],"gaze":[33,40,96],"and":[34,47,88,108,115],"head":[35,68,90],"motions":[36],"with":[37,86,120],"off-the-shelf":[38],"appearance-based":[39],"estimators.":[41],"capture":[43],"probabilistic":[45],"correlation":[46],"dynamics":[49],"of":[50],"coordination,":[52],"build":[54],"our":[55,74,112,117,127],"on":[57],"a":[58],"generative":[59],"conditional":[60],"Variational":[61],"Autoencoder":[62],"plausible":[64],"gaze-conditioned":[67],"motion":[69,91],"generations.":[70],"further":[72],"apply":[73],"framework":[75],"gaze-controlled":[77],"video":[79,84],"generation,":[80],"where":[81],"enable":[83],"generation":[85],"realistic":[89],"correlated":[92],"input":[95],"-":[97],"aspect":[99],"has":[101],"not":[102],"been":[103],"emphasized":[104],"before.":[105],"Human":[106],"evaluation":[107],"quantitative":[109],"comparisons":[110],"demonstrate":[111],"method\u2019s":[113],"effectiveness":[114],"validate":[116],"design":[118],"choices,":[119],"evaluators":[121],"showing":[122],"statistically":[123],"significant":[124],"preference":[125],"over":[129],"baseline":[130],"methods.":[131]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}