{"id":"https://openalex.org/W4386598226","doi":"https://doi.org/10.1109/icip49359.2023.10222631","title":"Tell Your Story: Text-Driven Face Video Synthesis with High Diversity via Adversarial Learning","display_name":"Tell Your Story: Text-Driven Face Video Synthesis with High Diversity via Adversarial Learning","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386598226","doi":"https://doi.org/10.1109/icip49359.2023.10222631"},"language":"en","primary_location":{"id":"doi:10.1109/icip49359.2023.10222631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10222631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5090010416","display_name":"Xia Hou","orcid":"https://orcid.org/0000-0001-6006-4215"},"institutions":[{"id":"https://openalex.org/I78675632","display_name":"Beijing Information Science & Technology University","ror":"https://ror.org/04xnqep60","country_code":"CN","type":"education","lineage":["https://openalex.org/I78675632"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xia Hou","raw_affiliation_strings":["Beijing Information Science and Technology University,Computer School","Computer School, Beijing Information Science and Technology University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Information Science and Technology University,Computer School","institution_ids":["https://openalex.org/I78675632"]},{"raw_affiliation_string":"Computer School, Beijing Information Science and Technology University","institution_ids":["https://openalex.org/I78675632"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100583870","display_name":"Meng Sun","orcid":"https://orcid.org/0000-0002-5431-8781"},"institutions":[{"id":"https://openalex.org/I78675632","display_name":"Beijing Information Science & Technology University","ror":"https://ror.org/04xnqep60","country_code":"CN","type":"education","lineage":["https://openalex.org/I78675632"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Sun","raw_affiliation_strings":["Beijing Information Science and Technology University,Computer School","Computer School, Beijing Information Science and Technology University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Information Science and Technology University,Computer School","institution_ids":["https://openalex.org/I78675632"]},{"raw_affiliation_string":"Computer School, Beijing Information Science and Technology University","institution_ids":["https://openalex.org/I78675632"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064016745","display_name":"Wenfeng Song","orcid":"https://orcid.org/0000-0002-5101-1071"},"institutions":[{"id":"https://openalex.org/I78675632","display_name":"Beijing Information Science & Technology University","ror":"https://ror.org/04xnqep60","country_code":"CN","type":"education","lineage":["https://openalex.org/I78675632"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenfeng Song","raw_affiliation_strings":["Beijing Information Science and Technology University,Computer School","Computer School, Beijing Information Science and Technology University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Information Science and Technology University,Computer School","institution_ids":["https://openalex.org/I78675632"]},{"raw_affiliation_string":"Computer School, Beijing Information Science and Technology University","institution_ids":["https://openalex.org/I78675632"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78675632"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12636304,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"515","last_page":"519"},"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":0.9997000098228455,"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":0.9997000098228455,"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":0.9994000196456909,"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/T13877","display_name":"Law in Society and Culture","score":0.9452999830245972,"subfield":{"id":"https://openalex.org/subfields/3308","display_name":"Law"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7970742583274841},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.5976810455322266},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5906648635864258},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5874663591384888},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5822871327400208},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5757972002029419},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5741804838180542},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5576620697975159},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.5197926759719849},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4548625648021698},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4423026740550995},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3693024516105652},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36268481612205505},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2033759355545044},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09608924388885498},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08717060089111328}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7970742583274841},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.5976810455322266},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5906648635864258},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5874663591384888},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5822871327400208},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5757972002029419},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5741804838180542},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5576620697975159},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5197926759719849},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4548625648021698},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4423026740550995},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3693024516105652},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36268481612205505},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2033759355545044},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09608924388885498},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08717060089111328},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip49359.2023.10222631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10222631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7099999785423279}],"awards":[{"id":"https://openalex.org/G1864300515","display_name":null,"funder_award_id":"VRLAB2022A02","funder_id":"https://openalex.org/F4320321125","funder_display_name":"Beihang University"},{"id":"https://openalex.org/G8278685304","display_name":null,"funder_award_id":"62102036","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8748097188","display_name":null,"funder_award_id":"VRLAB2022A02","funder_id":"https://openalex.org/F4320326839","funder_display_name":"State Key Laboratory of Virtual Reality Technology and Systems"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321125","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56"},{"id":"https://openalex.org/F4320321793","display_name":"Beijing Municipal Education Commission","ror":"https://ror.org/04bpn6s66"},{"id":"https://openalex.org/F4320326839","display_name":"State Key Laboratory of Virtual Reality Technology and Systems","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2325939864","https://openalex.org/W2890007666","https://openalex.org/W2902437806","https://openalex.org/W2905434858","https://openalex.org/W2951984970","https://openalex.org/W2962770929","https://openalex.org/W2962845008","https://openalex.org/W2963612019","https://openalex.org/W2965373594","https://openalex.org/W2970624676","https://openalex.org/W3035500781","https://openalex.org/W3035574324","https://openalex.org/W3166396011","https://openalex.org/W3170082999","https://openalex.org/W3174194560","https://openalex.org/W3174807077","https://openalex.org/W3180355996","https://openalex.org/W3194684016","https://openalex.org/W3195755139","https://openalex.org/W4301206121","https://openalex.org/W4308236853","https://openalex.org/W4312409772","https://openalex.org/W4313186669","https://openalex.org/W6752753668","https://openalex.org/W6756789066","https://openalex.org/W6765779288","https://openalex.org/W6766673545","https://openalex.org/W6797139422","https://openalex.org/W6797179183"],"related_works":["https://openalex.org/W4293202849","https://openalex.org/W1980965563","https://openalex.org/W1489300767","https://openalex.org/W2387995142","https://openalex.org/W2995777218","https://openalex.org/W2951387371","https://openalex.org/W4289106901","https://openalex.org/W2366944513","https://openalex.org/W2187606256","https://openalex.org/W2275988210"],"abstract_inverted_index":{"Face":[0],"synthesis":[1,14,78],"is":[2,15,131],"a":[3,42,65,85,89],"rapidly":[4],"growing":[5],"area":[6],"of":[7,26,79,103,111],"research":[8],"in":[9,22],"computer":[10],"vision.":[11],"Text-driven":[12],"face":[13,51,80,90],"particularly":[16],"flexible,":[17],"but":[18],"challenges":[19],"still":[20],"exist":[21],"fusing":[23],"the":[24,77,95,101,108,123],"semantics":[25],"text":[27,57,61,71,112],"and":[28,62,69,72,113],"images,":[29],"as":[30,32],"well":[31],"generating":[33],"diverse":[34,50],"faces.":[35],"To":[36],"address":[37],"these":[38],"challenges,":[39],"we":[40],"propose":[41],"cross-modality":[43],"adversarial":[44],"learning":[45],"framework":[46],"to":[47,55,75],"generate":[48],"highly":[49],"videos":[52],"that":[53,93],"correspond":[54],"given":[56],"descriptions.":[58],"We":[59,82],"encode":[60],"images":[63],"into":[64],"common":[66],"latent":[67],"space":[68],"align":[70],"image":[73],"features":[74],"control":[76],"attributes.":[81],"have":[83],"designed":[84],"novel":[86],"auto-encoder":[87],"with":[88],"identity":[91],"discriminator":[92],"enlarges":[94],"margin":[96],"between":[97],"different":[98],"individuals,":[99],"increasing":[100],"variety":[102],"created":[104],"faces":[105],"while":[106],"maintaining":[107],"semantic":[109],"coherence":[110],"images.":[114],"Our":[115,129],"proposed":[116],"method":[117],"has":[118],"been":[119],"successfully":[120],"tested":[121],"on":[122],"recently":[124],"released":[125],"Multimodal":[126],"VoxCeleb":[127],"dataset.":[128],"code":[130],"public":[132],"available":[133],"at":[134],"https://github.com/sunmeng7/TYS.git.":[135]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}