{"id":"https://openalex.org/W4416751080","doi":"https://doi.org/10.1109/iros60139.2025.11246337","title":"EmoRLTalk: Speech-Driven Emotional Facial Animation With Offline Reinforcement Learning","display_name":"EmoRLTalk: Speech-Driven Emotional Facial Animation With Offline Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416751080","doi":"https://doi.org/10.1109/iros60139.2025.11246337"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246337","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246337","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5023914609","display_name":"Gaofeng Liu","orcid":"https://orcid.org/0000-0001-6238-7560"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Gaofeng Liu","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Automation and Perception,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Automation and Perception,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113116645","display_name":"Xuetong Li","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuetong Li","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Automation and Perception,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Automation and Perception,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112916680","display_name":"R. S. Gao","orcid":"https://orcid.org/0009-0007-0306-2433"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruoyu Gao","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Automation and Perception,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Automation and Perception,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054999570","display_name":"Ye Yuan","orcid":"https://orcid.org/0000-0002-6967-6856"},"institutions":[{"id":"https://openalex.org/I283854653","display_name":"Machine Intelligence Research Institute","ror":"https://ror.org/01h4ass90","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I283854653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ye Yuan","raw_affiliation_strings":["University of Shanghai for Science and Technology,Institute of Machine Intelligence"],"affiliations":[{"raw_affiliation_string":"University of Shanghai for Science and Technology,Institute of Machine Intelligence","institution_ids":["https://openalex.org/I283854653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100414686","display_name":"Jian Liu","orcid":"https://orcid.org/0000-0002-5968-4318"},"institutions":[{"id":"https://openalex.org/I283854653","display_name":"Machine Intelligence Research Institute","ror":"https://ror.org/01h4ass90","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I283854653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Liu","raw_affiliation_strings":["University of Shanghai for Science and Technology,Institute of Machine Intelligence"],"affiliations":[{"raw_affiliation_string":"University of Shanghai for Science and Technology,Institute of Machine Intelligence","institution_ids":["https://openalex.org/I283854653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054942099","display_name":"Hongqun Li","orcid":"https://orcid.org/0000-0002-6793-4364"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengsen Li","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Automation and Perception,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Automation and Perception,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011090035","display_name":"Hong Huo","orcid":"https://orcid.org/0000-0002-2862-9455"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Huo","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Automation and Perception,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Automation and Perception,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101615935","display_name":"Tao Fang","orcid":"https://orcid.org/0000-0002-8277-2551"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Fang","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Automation and Perception,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Automation and Perception,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5023914609"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37177156,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18297","last_page":"18303"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.8701000213623047,"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":0.8701000213623047,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0333000011742115,"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":0.023900000378489494,"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/facial-expression","display_name":"Facial expression","score":0.6894000172615051},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.6287000179290771},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5501999855041504},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5468999743461609},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5055999755859375},{"id":"https://openalex.org/keywords/facial-motion-capture","display_name":"Facial motion capture","score":0.49300000071525574},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4844000041484833},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.47620001435279846}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7163000106811523},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.6894000172615051},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.6287000179290771},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5501999855041504},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5468999743461609},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5293999910354614},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5055999755859375},{"id":"https://openalex.org/C98907195","wikidata":"https://www.wikidata.org/wiki/Q5428562","display_name":"Facial motion capture","level":5,"score":0.49300000071525574},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4844000041484833},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.47620001435279846},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4625000059604645},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4163999855518341},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.3864000141620636},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.37450000643730164},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34439998865127563},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3255000114440918},{"id":"https://openalex.org/C54654163","wikidata":"https://www.wikidata.org/wiki/Q5428359","display_name":"Face hallucination","level":5,"score":0.3174999952316284},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.30300000309944153},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.2851000130176544},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.28279998898506165},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.27469998598098755},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2678000032901764},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2639999985694885}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246337","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246337","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2030435512","https://openalex.org/W2031080503","https://openalex.org/W2050658984","https://openalex.org/W2099019320","https://openalex.org/W2236592196","https://openalex.org/W2808631503","https://openalex.org/W2889191349","https://openalex.org/W2922127468","https://openalex.org/W2944294033","https://openalex.org/W2981263323","https://openalex.org/W3025521275","https://openalex.org/W3081192838","https://openalex.org/W3097792222","https://openalex.org/W3099284785","https://openalex.org/W3154411171","https://openalex.org/W3168292752","https://openalex.org/W3174763799","https://openalex.org/W3180770160","https://openalex.org/W3195529437","https://openalex.org/W3211147706","https://openalex.org/W4200630629","https://openalex.org/W4210974288","https://openalex.org/W4221145616","https://openalex.org/W4281730245","https://openalex.org/W4285119160","https://openalex.org/W4312801317","https://openalex.org/W4312933868","https://openalex.org/W4372270072","https://openalex.org/W4385490328","https://openalex.org/W4386071831","https://openalex.org/W4386076250","https://openalex.org/W4388157164","https://openalex.org/W4390872742","https://openalex.org/W4390873054","https://openalex.org/W4392780157","https://openalex.org/W4393159314","https://openalex.org/W4403791280","https://openalex.org/W4405778623","https://openalex.org/W4405787415"],"related_works":[],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"significant":[3],"breakthroughs":[4],"have":[5],"been":[6],"made":[7],"in":[8],"audio-guided":[9],"3D":[10,60],"facial":[11,33,61,84,134,151],"animation.":[12],"However,":[13],"existing":[14],"methods":[15],"mainly":[16],"focus":[17],"on":[18,96],"lip":[19],"shape":[20],"and":[21,24,35,63,112,163],"audio":[22],"consistency":[23],"still":[25],"face":[26],"key":[27],"challenges":[28],"to":[29,53,82,126,132,148,167],"achieve":[30,149],"alignment":[31],"between":[32,59],"emotions":[34],"speech":[36],"emotions.":[37,135],"To":[38,136],"overcome":[39],"this":[40],"limitation,":[41],"we":[42,74,101,117,141],"introduce":[43],"EmoRLTalk,":[44],"a":[45,103,108,113,124],"novel":[46],"framework":[47,106],"that":[48,86,157],"integrates":[49],"offline":[50],"reinforcement":[51],"learning":[52,99],"implicitly":[54],"capture":[55],"the":[56,68,76,91,97,129,143],"intricate":[57],"relationship":[58],"landmarks":[62],"blendshape":[64,122],"parameters,":[65],"thereby":[66],"enhancing":[67],"granularity":[69],"of":[70,78,107,121],"emotional":[71,161],"expression.":[72],"Furthermore,":[73],"harness":[75],"strength":[77],"conditional":[79],"diffusion":[80],"models":[81],"synthesize":[83],"motions":[85],"are":[87],"emotionally":[88],"coherent":[89],"with":[90],"input":[92],"speech.":[93],"Additionally,":[94],"based":[95],"multi-task":[98],"paradigm,":[100],"construct":[102],"collaborative":[104],"training":[105],"regression":[109],"main":[110],"task":[111],"classification":[114,120],"sub-task.":[115],"Specifically,":[116],"use":[118],"emotion":[119],"as":[123],"sub-task":[125],"further":[127,137],"improve":[128],"model\u2019s":[130],"ability":[131],"express":[133],"enhance":[138],"system":[139],"controllability,":[140],"integrate":[142],"ControlNet":[144],"module,":[145],"allowing":[146],"users":[147],"precise":[150],"expression":[152],"control.":[153],"Extensive":[154],"experiments":[155],"demonstrate":[156],"EmoRLTalk":[158],"achieves":[159],"superior":[160],"expressiveness":[162],"lip-sync":[164],"performance":[165],"compared":[166],"previous":[168],"approaches.":[169]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}