{"id":"https://openalex.org/W2978628216","doi":"https://doi.org/10.1145/3340555.3353725","title":"To React or not to React: End-to-End Visual Pose Forecasting for Personalized Avatar during Dyadic Conversations","display_name":"To React or not to React: End-to-End Visual Pose Forecasting for Personalized Avatar during Dyadic Conversations","publication_year":2019,"publication_date":"2019-10-14","ids":{"openalex":"https://openalex.org/W2978628216","doi":"https://doi.org/10.1145/3340555.3353725","mag":"2978628216"},"language":"en","primary_location":{"id":"doi:10.1145/3340555.3353725","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3340555.3353725","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3340555.3353725","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3340555.3353725","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050602513","display_name":"Chaitanya Ahuja","orcid":"https://orcid.org/0000-0003-4396-2050"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chaitanya Ahuja","raw_affiliation_strings":["Carnegie Mellon University, USA","Carnegie -Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie -Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032460666","display_name":"Shugao Ma","orcid":"https://orcid.org/0000-0002-4986-2221"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shugao Ma","raw_affiliation_strings":["Facebook Reality Labs, USA"],"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081398601","display_name":"Louis\u2013Philippe Morency","orcid":"https://orcid.org/0000-0001-6376-7696"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Louis-Philippe Morency","raw_affiliation_strings":["Carnegie Mellon University, USA","Carnegie -Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie -Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060280374","display_name":"Yaser Sheikh","orcid":"https://orcid.org/0000-0001-6512-9348"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yaser Sheikh","raw_affiliation_strings":["Facebook Reality Labs, USA"],"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs, USA","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5050602513"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.10689345,"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":"74","last_page":"84"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","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"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","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"}},{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9958999752998352,"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/T10860","display_name":"Speech and Audio Processing","score":0.9918000102043152,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/intrapersonal-communication","display_name":"Intrapersonal communication","score":0.8659179210662842},{"id":"https://openalex.org/keywords/avatar","display_name":"Avatar","score":0.8197112083435059},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.6705183386802673},{"id":"https://openalex.org/keywords/interpersonal-communication","display_name":"Interpersonal communication","score":0.588240385055542},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.5836309790611267},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5594776272773743},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.5590657591819763},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5106313824653625},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.50718092918396},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.47852858901023865},{"id":"https://openalex.org/keywords/nonverbal-communication","display_name":"Nonverbal communication","score":0.44727662205696106},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.33825644850730896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2586076557636261}],"concepts":[{"id":"https://openalex.org/C153721897","wikidata":"https://www.wikidata.org/wiki/Q3436149","display_name":"Intrapersonal communication","level":3,"score":0.8659179210662842},{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.8197112083435059},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.6705183386802673},{"id":"https://openalex.org/C164850336","wikidata":"https://www.wikidata.org/wiki/Q3685487","display_name":"Interpersonal communication","level":2,"score":0.588240385055542},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.5836309790611267},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5594776272773743},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.5590657591819763},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5106313824653625},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.50718092918396},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.47852858901023865},{"id":"https://openalex.org/C145633318","wikidata":"https://www.wikidata.org/wiki/Q207125","display_name":"Nonverbal communication","level":2,"score":0.44727662205696106},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.33825644850730896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2586076557636261},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3340555.3353725","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3340555.3353725","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3340555.3353725","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.02181","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.02181","pdf_url":"https://arxiv.org/pdf/1910.02181","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.1910.02181","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.02181","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"},{"id":"mag:2978628216","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.1145/3340555.3353725","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3340555.3353725","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3340555.3353725","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G574185058","display_name":null,"funder_award_id":"1722822","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2978628216.pdf","grobid_xml":"https://content.openalex.org/works/W2978628216.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W114912394","https://openalex.org/W174460259","https://openalex.org/W950853366","https://openalex.org/W1208039178","https://openalex.org/W1490492941","https://openalex.org/W1735317348","https://openalex.org/W1977985044","https://openalex.org/W2007337857","https://openalex.org/W2009266235","https://openalex.org/W2026243162","https://openalex.org/W2064675550","https://openalex.org/W2080873731","https://openalex.org/W2090777335","https://openalex.org/W2114645359","https://openalex.org/W2118748593","https://openalex.org/W2120654454","https://openalex.org/W2128042196","https://openalex.org/W2141855524","https://openalex.org/W2142824220","https://openalex.org/W2165044370","https://openalex.org/W2210514851","https://openalex.org/W2239141610","https://openalex.org/W2295661697","https://openalex.org/W2475210682","https://openalex.org/W2606862842","https://openalex.org/W2619383789","https://openalex.org/W2737658251","https://openalex.org/W2738406145","https://openalex.org/W2739192055","https://openalex.org/W2762481393","https://openalex.org/W2766709201","https://openalex.org/W2767060796","https://openalex.org/W2792764867","https://openalex.org/W2796290181","https://openalex.org/W2797263747","https://openalex.org/W2798338993","https://openalex.org/W2802441648","https://openalex.org/W2811426698","https://openalex.org/W2949382160","https://openalex.org/W2962865004","https://openalex.org/W2962916650","https://openalex.org/W2963218389","https://openalex.org/W2963488642","https://openalex.org/W2963710346","https://openalex.org/W2986302981","https://openalex.org/W2997581345","https://openalex.org/W3006295631"],"related_works":["https://openalex.org/W2981133004","https://openalex.org/W2785468866","https://openalex.org/W2787512630","https://openalex.org/W2147272821","https://openalex.org/W2553046517","https://openalex.org/W2897337310","https://openalex.org/W3209974982","https://openalex.org/W1685556602","https://openalex.org/W2535017512","https://openalex.org/W3193766423","https://openalex.org/W3021983780","https://openalex.org/W2050289579","https://openalex.org/W121725841","https://openalex.org/W2129180893","https://openalex.org/W2754588217","https://openalex.org/W2404332992","https://openalex.org/W2086586329","https://openalex.org/W316996119","https://openalex.org/W1604371559","https://openalex.org/W2537282113"],"abstract_inverted_index":{"Non":[0],"verbal":[1,20],"behaviours":[2],"such":[3,43],"as":[4],"gestures,":[5],"facial":[6],"expressions,":[7],"body":[8,59,104,110,173],"posture,":[9],"and":[10,57,93,109,115,135,148,181],"para-linguistic":[11],"cues":[12],"have":[13],"been":[14],"shown":[15],"to":[16,23,34,49,65,100,161],"complement":[17],"or":[18],"clarify":[19],"messages.":[21],"Hence":[22],"improve":[24],"telepresence,":[25],"in":[26,39,73],"form":[27],"of":[28,103,112,117,133,137,143,164],"an":[29],"avatar,":[30],"it":[31,62],"is":[32,175],"important":[33],"model":[35,50,66,127],"these":[36],"behaviours,":[37],"especially":[38],"dyadic":[40,129,149],"interactions.":[41],"Creating":[42],"personalized":[44],"avatars":[45],"not":[46],"only":[47],"requires":[48],"intrapersonal":[51,91,179],"dynamics":[52,68,96,150,180,183],"between":[53,146],"a":[54,81,158],"avatar\u2019s":[55],"speech":[56],"their":[58],"pose,":[60],"but":[61],"also":[63,156],"needs":[64],"interpersonal":[67,94,182],"with":[69],"the":[70,74,113,118,121,141,171],"interlocutor":[71,114],"present":[72],"conversation.":[75],"In":[76],"this":[77],"paper,":[78],"we":[79],"introduce":[80],"neural":[82],"architecture":[83],"named":[84],"Dyadic":[85],"Residual-Attention":[86],"Model":[87],"(DRAM),":[88],"which":[89],"integrates":[90],"(monadic)":[92],"(dyadic)":[95],"using":[97],"selective":[98],"attention":[99,145],"generate":[101],"sequences":[102],"pose":[105,111,134,174],"conditioned":[106],"on":[107,128],"audio":[108,116,136],"human":[119,165],"operating":[120],"avatar.":[122],"We":[123,155],"evaluate":[124],"our":[125],"proposed":[126],"conversational":[130],"data":[131],"consisting":[132],"both":[138],"participants,":[139],"confirming":[140],"importance":[142],"adaptive":[144],"monadic":[147],"when":[151],"predicting":[152],"avatar":[153],"pose.":[154],"conduct":[157],"user":[159],"study":[160],"analyze":[162],"judgments":[163],"observers.":[166],"Our":[167],"results":[168],"confirm":[169],"that":[170],"generated":[172],"more":[176],"natural,":[177],"models":[178],"better":[184],"than":[185],"non-adaptive":[186],"monadic/dyadic":[187],"models.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
