{"id":"https://openalex.org/W7131847559","doi":"https://doi.org/10.1109/sii64115.2026.11404449","title":"Improving Robotic Imitation Learning with Predicted Facial Motion Using Transformers","display_name":"Improving Robotic Imitation Learning with Predicted Facial Motion Using Transformers","publication_year":2026,"publication_date":"2026-01-11","ids":{"openalex":"https://openalex.org/W7131847559","doi":"https://doi.org/10.1109/sii64115.2026.11404449"},"language":null,"primary_location":{"id":"doi:10.1109/sii64115.2026.11404449","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sii64115.2026.11404449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/SICE International Symposium on System Integration (SII)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127233776","display_name":"Yitong Li","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yitong Li","raw_affiliation_strings":["University of Tsukuba,Doctoral Program in Intelligent and Mechanical Interaction Systems"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba,Doctoral Program in Intelligent and Mechanical Interaction Systems","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126981174","display_name":"Fumio Kanehiro","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Fumio Kanehiro","raw_affiliation_strings":["University of Tsukuba,Doctoral Program in Intelligent and Mechanical Interaction Systems"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba,Doctoral Program in Intelligent and Mechanical Interaction Systems","institution_ids":["https://openalex.org/I146399215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5127233776"],"corresponding_institution_ids":["https://openalex.org/I146399215"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93340024,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1340","last_page":"1347"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.7757999897003174,"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/T11448","display_name":"Face recognition and analysis","score":0.7757999897003174,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.10109999775886536,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.024399999529123306,"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/landmark","display_name":"Landmark","score":0.7103000283241272},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.49939998984336853},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.4691999852657318},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4632999897003174},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4311999976634979},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.39469999074935913},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.3799999952316284},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.36880001425743103}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7541999816894531},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.7103000283241272},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6859999895095825},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6261000037193298},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.49939998984336853},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.4691999852657318},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4632999897003174},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4311999976634979},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.39469999074935913},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.3799999952316284},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.36880001425743103},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3677000105381012},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.3513000011444092},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2759999930858612},{"id":"https://openalex.org/C98907195","wikidata":"https://www.wikidata.org/wiki/Q5428562","display_name":"Facial motion capture","level":5,"score":0.25619998574256897},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25589999556541443},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sii64115.2026.11404449","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sii64115.2026.11404449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/SICE International Symposium on System Integration (SII)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2604382266","https://openalex.org/W2913389983","https://openalex.org/W2964810439","https://openalex.org/W2982551402","https://openalex.org/W3138984732","https://openalex.org/W3169575318","https://openalex.org/W4312301659","https://openalex.org/W4312392075","https://openalex.org/W4385430674","https://openalex.org/W4386075831","https://openalex.org/W4401878910","https://openalex.org/W4405785334","https://openalex.org/W4411883231","https://openalex.org/W4412346195","https://openalex.org/W4413925192","https://openalex.org/W4414050506"],"related_works":[],"abstract_inverted_index":{"This":[0],"study":[1],"proposes":[2],"a":[3],"Transformer-based":[4],"approach":[5],"with":[6,107],"cross":[7],"attention":[8],"for":[9],"predicting":[10],"human":[11,31,75],"facial":[12,32,69,121],"movements":[13],"in":[14,57,129],"face-related":[15],"robotic":[16,126],"control":[17,127],"tasks":[18],"and":[19,36,49,62,80,89],"integrating":[20],"these":[21],"predictions":[22],"into":[23],"an":[24],"imitation":[25,66],"learning":[26,67],"framework.":[27,43],"A":[28],"dataset":[29],"of":[30],"videos":[33],"was":[34],"constructed,":[35],"landmarks":[37,95],"were":[38,47,78,96],"extracted":[39],"using":[40],"the":[41,50,54,81,100,108,112],"MediaPipe":[42],"Three":[44],"prediction":[45,101],"methods":[46],"compared,":[48],"cross-attention":[51],"model":[52],"achieved":[53],"best":[55],"performance":[56,128],"both":[58],"landmark":[59],"localization":[60],"accuracy":[61],"image":[63],"quality.":[64],"In":[65],"experiments,":[68],"motion":[70,122],"trajectories":[71,77],"sampled":[72],"from":[73,85],"real":[74],"data":[76],"used,":[79],"success":[82],"rate":[83],"increased":[84],"42%":[86],"to":[87,91],"60%":[88],"ultimately":[90],"74%":[92],"when":[93],"predicted":[94,120],"incorporated.":[97],"Additionally,":[98],"varying":[99],"horizon":[102,110],"affected":[103],"task":[104],"completion":[105],"time,":[106],"2-frame":[109],"achieving":[111],"fastest":[113],"completion.":[114],"These":[115],"results":[116],"demonstrate":[117],"that":[118],"incorporating":[119],"can":[123],"significantly":[124],"enhance":[125],"dynamic":[130],"human-robot":[131],"interaction":[132],"scenarios.":[133]},"counts_by_year":[],"updated_date":"2026-03-01T06:05:34.837733","created_date":"2026-02-28T00:00:00"}