{"id":"https://openalex.org/W4389383543","doi":"https://doi.org/10.1109/tpami.2023.3339964","title":"DaGAN++: Depth-Aware Generative Adversarial Network for Talking Head Video Generation","display_name":"DaGAN++: Depth-Aware Generative Adversarial Network for Talking Head Video Generation","publication_year":2023,"publication_date":"2023-12-06","ids":{"openalex":"https://openalex.org/W4389383543","doi":"https://doi.org/10.1109/tpami.2023.3339964","pmid":"https://pubmed.ncbi.nlm.nih.gov/38055369"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2023.3339964","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3339964","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5074327829","display_name":"Fa-Ting Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Fa-Ting Hong","raw_affiliation_strings":["Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108393212","display_name":"Li Shen","orcid":"https://orcid.org/0000-0002-2283-4976"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Li Shen","raw_affiliation_strings":["Alibaba Group, Hangzhou, China","Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341938","display_name":"Dan Xu","orcid":"https://orcid.org/0000-0003-0136-9603"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dan Xu","raw_affiliation_strings":["Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5074327829"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":1.9258,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88489905,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"46","issue":"5","first_page":"2997","last_page":"3012"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9990000128746033,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9990000128746033,"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/T11448","display_name":"Face recognition and analysis","score":0.9983000159263611,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9959999918937683,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7736151218414307},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.758987545967102},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7060257792472839},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6972134709358215},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5552074909210205},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5534798502922058},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4692615866661072},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.4381643533706665},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3803842067718506}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7736151218414307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.758987545967102},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7060257792472839},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6972134709358215},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5552074909210205},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5534798502922058},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4692615866661072},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.4381643533706665},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3803842067718506},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpami.2023.3339964","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3339964","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:38055369","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38055369","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-135069","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-135069","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":77,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2237250383","https://openalex.org/W2422409530","https://openalex.org/W2431101926","https://openalex.org/W2605938684","https://openalex.org/W2609883120","https://openalex.org/W2726515241","https://openalex.org/W2796822548","https://openalex.org/W2808631503","https://openalex.org/W2884460600","https://openalex.org/W2950689937","https://openalex.org/W2962865004","https://openalex.org/W2963066677","https://openalex.org/W2963168844","https://openalex.org/W2963290645","https://openalex.org/W2963488291","https://openalex.org/W2963652981","https://openalex.org/W2964449965","https://openalex.org/W2964559396","https://openalex.org/W2967294981","https://openalex.org/W2981767644","https://openalex.org/W2981816492","https://openalex.org/W2981851635","https://openalex.org/W2982102242","https://openalex.org/W2982624843","https://openalex.org/W2985775862","https://openalex.org/W2990452356","https://openalex.org/W2998605827","https://openalex.org/W3017343282","https://openalex.org/W3018564516","https://openalex.org/W3019952993","https://openalex.org/W3034371424","https://openalex.org/W3038429043","https://openalex.org/W3048510980","https://openalex.org/W3067169454","https://openalex.org/W3099363577","https://openalex.org/W3105763085","https://openalex.org/W3108240585","https://openalex.org/W3109114891","https://openalex.org/W3138516171","https://openalex.org/W3157990890","https://openalex.org/W3178284600","https://openalex.org/W3180770160","https://openalex.org/W3186090335","https://openalex.org/W3187364420","https://openalex.org/W3197199219","https://openalex.org/W3204680331","https://openalex.org/W3207250917","https://openalex.org/W3211147706","https://openalex.org/W4200150166","https://openalex.org/W4205124152","https://openalex.org/W4221145616","https://openalex.org/W4226204502","https://openalex.org/W4288327876","https://openalex.org/W4312301053","https://openalex.org/W4312472600","https://openalex.org/W4312473638","https://openalex.org/W4312959196","https://openalex.org/W4313304691","https://openalex.org/W4315589026","https://openalex.org/W4386066083","https://openalex.org/W4386075487","https://openalex.org/W4390872428","https://openalex.org/W4390872774","https://openalex.org/W4390872968","https://openalex.org/W4390874181","https://openalex.org/W4390874403","https://openalex.org/W4394597549","https://openalex.org/W6737896281","https://openalex.org/W6764045775","https://openalex.org/W6766674170","https://openalex.org/W6767264202","https://openalex.org/W6779823529","https://openalex.org/W6803376173","https://openalex.org/W6810221379","https://openalex.org/W6811548253","https://openalex.org/W6848056488"],"related_works":["https://openalex.org/W2380075625","https://openalex.org/W2888032422","https://openalex.org/W2996316059","https://openalex.org/W4377980832","https://openalex.org/W2897769091","https://openalex.org/W2845413374","https://openalex.org/W3005996785","https://openalex.org/W4297411772","https://openalex.org/W4235873501","https://openalex.org/W4389345324"],"abstract_inverted_index":{"Predominant":[0],"techniques":[1],"on":[2,8,156,184],"talking":[3,177],"head":[4],"generation":[5,142],"largely":[6],"depend":[7],"2D":[9],"information,":[10],"including":[11],"facial":[12,23,37,51,72,113,146],"appearances":[13],"and":[14,39,83,132,163],"motions":[15],"from":[16,76],"input":[17],"face":[18,77],"images.":[19],"Nevertheless,":[20],"dense":[21,47,70],"3D":[22,36,48,71,84],"geometry,":[24],"such":[25],"as":[26],"pixel-wise":[27],"depth,":[28],"plays":[29],"a":[30,64,92,127,149],"critical":[31],"role":[32],"in":[33,87,148],"constructing":[34],"accurate":[35,118],"structures":[38],"suppressing":[40],"complex":[41],"background":[42],"noises":[43],"for":[44,50,68,104,120],"generation.":[45],"However,":[46],"annotations":[49,86],"videos":[52],"is":[53],"prohibitively":[54],"costly":[55],"to":[56,94,98,140,144],"obtain.":[57],"In":[58],"this":[59],"paper,":[60],"first,":[61],"we":[62,108,125],"present":[63],"novel":[65],"self-supervised":[66],"method":[67],"learning":[69],"geometry":[73,85,105],"(i.e.,":[74,130,160],"depth)":[75,133],"videos,":[78,178],"without":[79],"requiring":[80],"camera":[81],"parameters":[82],"training.":[88],"We":[89],"further":[90],"propose":[91],"strategy":[93],"learn":[95],"pixel-level":[96],"uncertainties":[97],"perceive":[99],"more":[100],"reliable":[101],"rigid-motion":[102],"pixels":[103],"learning.":[106],"Second,":[107],"design":[109],"an":[110],"effective":[111],"geometry-guided":[112],"keypoint":[114],"estimation":[115],"module,":[116],"providing":[117],"keypoints":[119],"generating":[121],"motion":[122],"fields.":[123],"Lastly,":[124],"develop":[126],"3D-aware":[128],"cross-modal":[129],"appearance":[131],"attention":[134],"mechanism,":[135],"which":[136],"can":[137,172],"be":[138],"applied":[139],"each":[141],"layer,":[143],"capture":[145],"geometries":[147],"coarse-to-fine":[150],"manner.":[151],"Extensive":[152],"experiments":[153],"are":[154],"conducted":[155],"three":[157],"challenging":[158],"benchmarks":[159],"VoxCeleb1,":[161],"VoxCeleb2,":[162],"HDTF).":[164],"The":[165],"results":[166],"demonstrate":[167],"that":[168],"our":[169],"proposed":[170],"framework":[171],"generate":[173],"highly":[174],"realistic-looking":[175],"reenacted":[176],"with":[179],"new":[180],"state-of-the-art":[181],"performances":[182],"established":[183],"these":[185],"benchmarks.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-29T08:15:47.926485","created_date":"2025-10-10T00:00:00"}