{"id":"https://openalex.org/W4414404771","doi":"https://doi.org/10.1109/access.2025.3612820","title":"Enhancing Temporal Coherence in Image-to-Video Facial Expression Synthesis: A Dual-Loss Framework for Smoother Generation","display_name":"Enhancing Temporal Coherence in Image-to-Video Facial Expression Synthesis: A Dual-Loss Framework for Smoother Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414404771","doi":"https://doi.org/10.1109/access.2025.3612820"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3612820","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3612820","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3612820","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082646689","display_name":"Rafael Luiz Testa","orcid":"https://orcid.org/0000-0002-7209-1111"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rafael Luiz Testa","raw_affiliation_strings":["Universidade de São Paulo, São Paulo, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-7209-1111","affiliations":[{"raw_affiliation_string":"Universidade de São Paulo, São Paulo, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043984374","display_name":"Ariane Machado\u2010Lima","orcid":"https://orcid.org/0000-0002-5719-338X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ariane Machado-Lima","raw_affiliation_strings":["Universidade de São Paulo, São Paulo, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-5719-338X","affiliations":[{"raw_affiliation_string":"Universidade de São Paulo, São Paulo, Brazil","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054257245","display_name":"F\u00e1tima L. S. Nunes","orcid":"https://orcid.org/0000-0003-0040-0752"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"F\u00e1tima L. S. Nunes","raw_affiliation_strings":["Universidade de São Paulo, São Paulo, Brazil"],"raw_orcid":"https://orcid.org/0000-0003-0040-0752","affiliations":[{"raw_affiliation_string":"Universidade de São Paulo, São Paulo, Brazil","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21007624,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9818999767303467,"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":0.9818999767303467,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9559999704360962,"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/T10860","display_name":"Speech and Audio Processing","score":0.9544000029563904,"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/facial-expression","display_name":"Facial expression","score":0.7950999736785889},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.6714000105857849},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5814999938011169},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5602999925613403},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.5015000104904175},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49459999799728394},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4097000062465668},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.399399995803833}],"concepts":[{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.7950999736785889},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7789000272750854},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.6714000105857849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6416000127792358},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5814999938011169},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5602999925613403},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.5015000104904175},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49459999799728394},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4203000068664551},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4097000062465668},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.399399995803833},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3799000084400177},{"id":"https://openalex.org/C2777375102","wikidata":"https://www.wikidata.org/wiki/Q208351","display_name":"Disgust","level":3,"score":0.34200000762939453},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2955000102519989},{"id":"https://openalex.org/C2987714656","wikidata":"https://www.wikidata.org/wiki/Q1185804","display_name":"Facial expression recognition","level":4,"score":0.29019999504089355},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.28459998965263367},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.26109999418258667}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3612820","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3612820","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:cf74d2584e23472e9a1bd36efc1e32e1","is_oa":true,"landing_page_url":"https://doaj.org/article/cf74d2584e23472e9a1bd36efc1e32e1","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 170876-170894 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3612820","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3612820","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4231038217","display_name":null,"funder_award_id":"18.5.245.86.7","funder_id":"https://openalex.org/F4320335240","funder_display_name":"Pro-Reitoria de Pesquisa, Universidade de S\u00e3o Paulo"},{"id":"https://openalex.org/G4956284797","display_name":"National Institute of Science and Technology Medicine Assisted by Scientific Computing (INCT-MACC)","funder_award_id":"14/50889-7","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"},{"id":"https://openalex.org/G665421920","display_name":null,"funder_award_id":"2020/01992-0","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"},{"id":"https://openalex.org/G8158777786","display_name":null,"funder_award_id":"307710/2022-0","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"}],"funders":[{"id":"https://openalex.org/F4320320997","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","ror":"https://ror.org/02ddkpn78"},{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"},{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"},{"id":"https://openalex.org/F4320335240","display_name":"Pro-Reitoria de Pesquisa, Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Facial":[0,110],"expression":[1,19,41,55,199],"synthesis":[2],"for":[3,49,177],"video":[4],"sequences":[5],"presents":[6,45],"significant":[7],"challenges":[8],"in":[9,32,53,174,195,205],"terms":[10],"of":[11,139,190],"maintaining":[12,150],"temporal":[13,51,193],"coherence":[14,52,194],"while":[15,149],"preserving":[16],"identity":[17],"and":[18,39,71,88,100,121,167,183,208],"accuracy.":[20],"Most":[21],"current":[22],"approaches":[23,125,142],"primarily":[24],"focus":[25],"on":[26,107],"individual":[27],"frame":[28,85,147],"quality.":[29,153],"This":[30,43,144,201],"results":[31],"videos":[33,173],"with":[34,123,156],"unnatural":[35],"transitions,":[36],"flickering":[37],"artifacts,":[38],"inconsistent":[40],"dynamics.":[42],"paper":[44],"a":[46,62,84,89,96,101],"novel":[47],"method":[48,78,131],"improving":[50],"facial":[54,198],"image-to-video":[56],"synthesis.":[57],"The":[58,129],"proposed":[59,130],"approach":[60,117,170],"uses":[61],"dual-focus":[63],"framework":[64],"that":[65,114,160],"explicitly":[66,191],"models":[67],"both":[68],"pixel-level":[69],"transitions":[70,148],"geometric":[72],"consistency":[73,91],"between":[74],"consecutive":[75],"frames.":[76],"Our":[77,169],"includes":[79],"two":[80],"specialized":[81],"loss":[82,87],"functions:":[83],"difference":[86],"landmark":[90],"loss.":[92],"We":[93],"also":[94],"implement":[95],"two-stage":[97],"training":[98],"strategy":[99],"frame-blending":[102],"post-processing":[103],"technique.":[104],"Extensive":[105],"testing":[106],"the":[108,115,127,133,141,161,188],"MUG":[109],"Expression":[111],"Database":[112],"demonstrates":[113],"enhanced-coherence":[116],"outperforms":[118],"baseline":[119],"methods":[120],"competes":[122],"other":[124],"from":[126],"literature.":[128],"has":[132,202],"lowest":[134],"Average":[135],"Content":[136],"Distance":[137],"score":[138],"all":[140],"tested.":[143],"indicates":[145],"smoother":[146],"high":[151],"visual":[152],"Subjective":[154],"evaluation":[155],"140":[157],"participants":[158],"confirms":[159],"synthesized":[162],"expressions":[163],"are":[164],"more":[165],"realistic":[166,197],"expressive.":[168],"outperformed":[171],"real":[172],"recognition":[175],"rates":[176],"certain":[178],"emotion":[179],"expressions,":[180],"particularly":[181],"disgust":[182],"sadness.":[184],"These":[185],"findings":[186],"demonstrate":[187],"effectiveness":[189],"modeling":[192],"generating":[196],"videos.":[200],"promising":[203],"applications":[204],"therapy,":[206],"entertainment,":[207],"human-computer":[209],"interaction.":[210]},"counts_by_year":[],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}