{"id":"https://openalex.org/W4402979798","doi":"https://doi.org/10.1109/icme57554.2024.10688218","title":"Landmark-guided Diffusion Model for High-fidelity and Temporally Coherent Talking Head Generation","display_name":"Landmark-guided Diffusion Model for High-fidelity and Temporally Coherent Talking Head Generation","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979798","doi":"https://doi.org/10.1109/icme57554.2024.10688218"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688218","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5068597659","display_name":"Jintao Tan","orcid":"https://orcid.org/0009-0002-4195-6036"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jintao Tan","raw_affiliation_strings":["South China University of Technology"],"affiliations":[{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009897266","display_name":"Xize Cheng","orcid":"https://orcid.org/0000-0001-9708-3225"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xize Cheng","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001102230","display_name":"Lingyu Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingyu Xiong","raw_affiliation_strings":["South China University of Technology"],"affiliations":[{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100380630","display_name":"Lei Zhu","orcid":"https://orcid.org/0000-0003-0506-4268"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhu","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111346914","display_name":"Xiandong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiandong Li","raw_affiliation_strings":["Huawei Cloud"],"affiliations":[{"raw_affiliation_string":"Huawei Cloud","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114236922","display_name":"Xianjia Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xianjia Wu","raw_affiliation_strings":["Huawei Cloud"],"affiliations":[{"raw_affiliation_string":"Huawei Cloud","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100566768","display_name":"Kai Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Gong","raw_affiliation_strings":["Huawei Cloud"],"affiliations":[{"raw_affiliation_string":"Huawei Cloud","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100780135","display_name":"Minglei Li","orcid":"https://orcid.org/0000-0002-1427-3507"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minglei Li","raw_affiliation_strings":["Huawei Cloud"],"affiliations":[{"raw_affiliation_string":"Huawei Cloud","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070704493","display_name":"Yi Cai","orcid":"https://orcid.org/0000-0002-0853-2779"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Cai","raw_affiliation_strings":["South China University of Technology"],"affiliations":[{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5068597659"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":1.4566,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.85194259,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.953499972820282,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9279000163078308,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/fidelity","display_name":"Fidelity","score":0.6773650050163269},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.668411374092102},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.6337370276451111},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.4931027591228485},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.44581037759780884},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4317472577095032},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3666079044342041},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13945835828781128},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12659305334091187},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.1002034842967987},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09409758448600769}],"concepts":[{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.6773650050163269},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.668411374092102},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.6337370276451111},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.4931027591228485},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.44581037759780884},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4317472577095032},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3666079044342041},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13945835828781128},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12659305334091187},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.1002034842967987},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09409758448600769},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10688218","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320335795","display_name":"Science and Technology Planning Project of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2087681821","https://openalex.org/W2604379605","https://openalex.org/W2962788625","https://openalex.org/W2996880115","https://openalex.org/W3034257218","https://openalex.org/W3081492798","https://openalex.org/W3180355996","https://openalex.org/W3180770160","https://openalex.org/W3197199219","https://openalex.org/W4312933868","https://openalex.org/W4385571016","https://openalex.org/W4386065999","https://openalex.org/W4386072021","https://openalex.org/W4386075487","https://openalex.org/W4390873467","https://openalex.org/W4391072501","https://openalex.org/W4394597549","https://openalex.org/W4402670354"],"related_works":["https://openalex.org/W4313443006","https://openalex.org/W2945374968","https://openalex.org/W4385452045","https://openalex.org/W4293777179","https://openalex.org/W2164070813","https://openalex.org/W2135608140","https://openalex.org/W2895525995","https://openalex.org/W4224231624","https://openalex.org/W2332512904","https://openalex.org/W2319626700"],"abstract_inverted_index":{"Audio-driven":[0],"talking":[1,110],"head":[2,111],"generation":[3],"is":[4],"a":[5,65,91],"significant":[6],"and":[7,20,103,107],"challenging":[8],"task":[9],"applicable":[10],"to":[11,98],"various":[12],"fields":[13],"such":[14],"as":[15,90],"virtual":[16],"avatars,":[17],"film":[18],"production,":[19],"online":[21],"conferences.":[22],"However,":[23],"the":[24,35,60,79,83,94,120],"existing":[25],"GAN-based":[26],"models":[27,43],"emphasize":[28],"generating":[29,45,73],"well-synchronized":[30],"lip":[31,50],"shapes":[32],"but":[33,48],"overlook":[34],"visual":[36],"quality":[37],"of":[38],"generated":[39,87],"frames,":[40],"while":[41],"diffusion-based":[42,67],"prioritize":[44],"high-quality":[46],"frames":[47],"neglect":[49],"shape":[51],"matching,":[52],"resulting":[53],"in":[54,93],"jittery":[55],"mouth":[56,100],"movements.":[57],"To":[58],"address":[59],"aforementioned":[61],"problems,":[62],"we":[63],"introduce":[64],"two-stage":[66],"model.":[68],"The":[69],"first":[70],"stage":[71],"involves":[72],"synchronized":[74],"facial":[75],"landmarks":[76,88],"based":[77],"on":[78],"given":[80],"speech.":[81],"In":[82],"second":[84],"stage,":[85],"these":[86],"serve":[89],"condition":[92],"denoising":[95],"process,":[96],"aiming":[97],"optimize":[99],"jitter":[101],"issues":[102],"generate":[104],"high-fidelity,":[105],"well-synchronized,":[106],"temporally":[108],"coherent":[109],"videos.":[112],"Extensive":[113],"experiments":[114],"demonstrate":[115],"that":[116],"our":[117],"model":[118],"yields":[119],"best":[121],"performance.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}