{"id":"https://openalex.org/W4416956410","doi":"https://doi.org/10.1109/wacv61042.2026.00303","title":"TalkingPose: Efficient Face and Gesture Animation with Feedback-guided Diffusion Model","display_name":"TalkingPose: Efficient Face and Gesture Animation with Feedback-guided Diffusion Model","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4416956410","doi":"https://doi.org/10.1109/wacv61042.2026.00303"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.00909","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077121568","display_name":"Alireza Javanmardi","orcid":"https://orcid.org/0000-0002-4901-5989"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Alireza Javanmardi","raw_affiliation_strings":["German Research Center for Artificial Intelligence (DFKI)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence (DFKI)","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032713028","display_name":"Pragati Jaiswal","orcid":"https://orcid.org/0000-0003-0422-0695"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Pragati Jaiswal","raw_affiliation_strings":["German Research Center for Artificial Intelligence (DFKI)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence (DFKI)","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003297379","display_name":"Tewodros Habtegebrial","orcid":null},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tewodros Amberbir Habtegebrial","raw_affiliation_strings":["German Research Center for Artificial Intelligence (DFKI)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence (DFKI)","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022699526","display_name":"Christen Millerdurai","orcid":null},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christen Millerdurai","raw_affiliation_strings":["German Research Center for Artificial Intelligence (DFKI)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence (DFKI)","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107875707","display_name":"Shaoxiang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Shaoxiang Wang","raw_affiliation_strings":["German Research Center for Artificial Intelligence (DFKI)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence (DFKI)","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046969927","display_name":"Alain Pagani","orcid":"https://orcid.org/0000-0002-5136-0837"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alain Pagani","raw_affiliation_strings":["German Research Center for Artificial Intelligence (DFKI)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence (DFKI)","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051650277","display_name":"Didier Stricker","orcid":"https://orcid.org/0009-0004-8794-6858"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Didier Stricker","raw_affiliation_strings":["German Research Center for Artificial Intelligence (DFKI)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence (DFKI)","institution_ids":["https://openalex.org/I33256026"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5077121568"],"corresponding_institution_ids":["https://openalex.org/I33256026"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01090668,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3098","last_page":"3108"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.40220001339912415,"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":0.40220001339912415,"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":0.29499998688697815,"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":0.1882999986410141,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.7010999917984009},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.5978999733924866},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5809000134468079},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.5771999955177307},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.5580000281333923},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.532800018787384},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4975999891757965},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.46880000829696655},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4648999869823456}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8434000015258789},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.7010999917984009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6574000120162964},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.631600022315979},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5978999733924866},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5809000134468079},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.5771999955177307},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.5580000281333923},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.532800018787384},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4975999891757965},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.46880000829696655},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4648999869823456},{"id":"https://openalex.org/C2780575108","wikidata":"https://www.wikidata.org/wiki/Q7316652","display_name":"Retargeting","level":2,"score":0.4375999867916107},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4336000084877014},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.43209999799728394},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.42419999837875366},{"id":"https://openalex.org/C98907195","wikidata":"https://www.wikidata.org/wiki/Q5428562","display_name":"Facial motion capture","level":5,"score":0.39489999413490295},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.37439998984336853},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.3698999881744385},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3682999908924103},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.36550000309944153},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33809998631477356},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.33230000734329224},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3075000047683716},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C90697248","wikidata":"https://www.wikidata.org/wiki/Q1062896","display_name":"Character animation","level":4,"score":0.25949999690055847},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.25870001316070557},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.00909","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.00909","pdf_url":"https://arxiv.org/pdf/2512.00909","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2512.00909","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.00909","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.00909","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.00909","pdf_url":"https://arxiv.org/pdf/2512.00909","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2],"diffusion":[3,118,136],"models":[4],"have":[5],"significantly":[6],"improved":[7],"the":[8,16,153],"realism":[9],"and":[10,27,47,67,105,124],"generalizability":[11],"of":[12,18,30,155],"character-driven":[13],"animation,":[14],"enabling":[15,152],"synthesis":[17],"high-quality":[19],"motion":[20,123],"from":[21],"just":[22],"a":[23,28,82,112,116,130,163,170],"single":[24],"RGB":[25],"image":[26],"set":[29],"driving":[31,98],"poses.":[32],"Nevertheless,":[33],"generating":[34],"temporally":[35,91],"coherent":[36,73],"long-form":[37],"content":[38],"remains":[39],"challenging.":[40],"Existing":[41],"approaches":[42],"are":[43,52],"constrained":[44],"by":[45],"computational":[46,145],"memory":[48],"limitations,":[49],"as":[50,169],"they":[51],"typically":[53],"trained":[54],"on":[55],"short":[56],"video":[57],"segments,":[58],"thus":[59],"performing":[60],"effectively":[61],"only":[62],"over":[63],"limited":[64],"frame":[65],"lengths":[66],"hindering":[68],"their":[69],"potential":[70],"for":[71,88,173],"extended":[72],"generation.":[74],"To":[75,120],"address":[76],"these":[77,109],"constraints,":[78],"we":[79,128,161],"propose":[80],"TalkingPose,":[81],"novel":[83],"diffusion-based":[84],"framework":[85],"specifically":[86],"designed":[87],"producing":[89],"long-form,":[90],"consistent":[92],"human":[93,174],"upper-body":[94,175],"animations.":[95],"TalkingPose":[96],"leverages":[97],"frames":[99],"to":[100,111,167],"precisely":[101],"capture":[102],"expressive":[103],"facial":[104],"hand":[106],"movements,":[107],"transferring":[108],"seamlessly":[110],"target":[113],"actor":[114],"through":[115],"stable":[117],"backbone.":[119],"ensure":[121],"continuous":[122],"enhance":[125],"temporal":[126],"coherence,":[127],"introduce":[129,162],"feedback-driven":[131],"mechanism":[132,140],"built":[133],"upon":[134],"image-based":[135],"models.":[137],"Notably,":[138],"this":[139],"does":[141],"not":[142],"incur":[143],"additional":[144],"costs":[146],"or":[147],"require":[148],"secondary":[149],"training":[150],"stages,":[151],"generation":[154],"animations":[156],"with":[157],"unlimited":[158],"duration.":[159],"Additionally,":[160],"comprehensive,":[164],"large-scale":[165],"dataset":[166],"serve":[168],"new":[171],"benchmark":[172],"animation.":[176],"Project":[177],"page:":[178],"https://dfki-av.github.io/TalkingPose":[179]},"counts_by_year":[],"updated_date":"2026-05-07T06:04:25.777469","created_date":"2025-12-03T00:00:00"}