{"id":"https://openalex.org/W3160786016","doi":"https://doi.org/10.1109/icpr48806.2021.9412425","title":"Talking Face Generation via Learning Semantic and Temporal Synchronous Landmarks","display_name":"Talking Face Generation via Learning Semantic and Temporal Synchronous Landmarks","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3160786016","doi":"https://doi.org/10.1109/icpr48806.2021.9412425","mag":"3160786016"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9412425","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","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/A5017558628","display_name":"Aihua Zheng","orcid":"https://orcid.org/0000-0002-9820-4743"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Aihua Zheng","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Heifei, China"],"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Heifei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091454702","display_name":"Feixia Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feixia Zhu","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Heifei, China"],"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Heifei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101589497","display_name":"Hao Zhu","orcid":"https://orcid.org/0000-0003-2155-1488"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zhu","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Heifei, China"],"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Heifei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064812067","display_name":"Mandi Luo","orcid":"https://orcid.org/0000-0001-8298-3220"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mandi Luo","raw_affiliation_strings":["Center for Research on Intelligent Perception and Computing (CRIPAC) National Laboratory of Pattern Recognition (NLPR), CASIA, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Center for Research on Intelligent Perception and Computing (CRIPAC) National Laboratory of Pattern Recognition (NLPR), CASIA, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112749024","display_name":"Ran He","orcid":"https://orcid.org/0000-0002-3807-991X"},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran He","raw_affiliation_strings":["Center for Excellence in Brain Science and Intelligence Technology, CAS, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Center for Excellence in Brain Science and Intelligence Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210097554"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5017558628"],"corresponding_institution_ids":["https://openalex.org/I143868143"],"apc_list":null,"apc_paid":null,"fwci":0.2882,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.53903595,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3682","last_page":"3689"},"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":0.9993000030517578,"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":0.9950000047683716,"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/computer-science","display_name":"Computer science","score":0.8598629236221313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6421423554420471},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.5891368389129639},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5733851790428162},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5541500449180603},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5509785413742065},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46448689699172974},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.46080565452575684},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43930381536483765},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.42721468210220337}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8598629236221313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6421423554420471},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.5891368389129639},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5733851790428162},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5541500449180603},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5509785413742065},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46448689699172974},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46080565452575684},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43930381536483765},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.42721468210220337},{"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},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr48806.2021.9412425","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3254430106","display_name":null,"funder_award_id":"61976002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2004789217","https://openalex.org/W2015143272","https://openalex.org/W2026203852","https://openalex.org/W2099471712","https://openalex.org/W2105594594","https://openalex.org/W2115252128","https://openalex.org/W2125389028","https://openalex.org/W2520331172","https://openalex.org/W2556783285","https://openalex.org/W2583585015","https://openalex.org/W2594690981","https://openalex.org/W2613087992","https://openalex.org/W2780124704","https://openalex.org/W2783047733","https://openalex.org/W2790649793","https://openalex.org/W2795230330","https://openalex.org/W2884460600","https://openalex.org/W2887901449","https://openalex.org/W2897492344","https://openalex.org/W2899129842","https://openalex.org/W2904622387","https://openalex.org/W2944294033","https://openalex.org/W2949309273","https://openalex.org/W2951270715","https://openalex.org/W2951392520","https://openalex.org/W2953096069","https://openalex.org/W2963081548","https://openalex.org/W2963290645","https://openalex.org/W2963563548","https://openalex.org/W2963800363","https://openalex.org/W2964209717","https://openalex.org/W2977816919","https://openalex.org/W2979894294","https://openalex.org/W2982552333","https://openalex.org/W2987654099","https://openalex.org/W3102288316","https://openalex.org/W3102619627","https://openalex.org/W3189092450","https://openalex.org/W4320013936","https://openalex.org/W6639824700","https://openalex.org/W6677618333","https://openalex.org/W6726954415","https://openalex.org/W6734491695","https://openalex.org/W6746285158","https://openalex.org/W6753894364","https://openalex.org/W6754033747"],"related_works":["https://openalex.org/W2056853153","https://openalex.org/W2057559274","https://openalex.org/W2005087563","https://openalex.org/W2378111931","https://openalex.org/W2052388267","https://openalex.org/W2950647290","https://openalex.org/W1968481813","https://openalex.org/W2620829895","https://openalex.org/W2356918560","https://openalex.org/W4243161226"],"abstract_inverted_index":{"Given":[0],"a":[1,16,67,84,115],"speech":[2],"clip":[3],"and":[4,24,51,60,69,100,104,138],"facial":[5,125],"image,":[6],"the":[7,32,35,38,46,55,97,107,128,141,148],"goal":[8],"of":[9,34,57,143,151],"talking":[10,17,42,76,152],"face":[11,18,26,43,77,153],"generation":[12,62,117],"is":[13],"to":[14,82,87,95,123,147],"synthesize":[15],"video":[19],"with":[20,119],"accurate":[21],"mouth":[22],"synchronization":[23,99],"natural":[25],"motion.":[27],"Recent":[28],"progress":[29],"has":[30],"proven":[31],"effectiveness":[33,142],"landmarks":[36,58,103],"as":[37],"intermediate":[39],"information":[40],"during":[41],"generation.":[44,78,154],"However,":[45],"large":[47],"gap":[48],"between":[49,102],"audio":[50,105],"visual":[52],"modalities":[53],"makes":[54],"prediction":[56],"challenging":[59],"limits":[61],"ability.":[63],"This":[64],"paper":[65],"proposes":[66],"semantic":[68,90],"temporal":[70,98,109],"synchronous":[71],"landmark":[72],"learning":[73],"method":[74],"for":[75,127],"First,":[79],"we":[80,93,113],"propose":[81,94],"introduce":[83],"word":[85],"detector":[86],"enforce":[88],"richer":[89],"information.":[91],"Then,":[92],"preserve":[96],"consistency":[101],"via":[106],"proposed":[108],"residual":[110],"loss.":[111],"Lastly,":[112],"employ":[114],"U-Net":[116],"network":[118],"adaptive":[120],"reconstruction":[121],"loss":[122],"generate":[124],"images":[126],"predicted":[129],"landmarks.":[130],"Experimental":[131],"results":[132],"on":[133],"two":[134],"benchmark":[135],"datasets":[136],"LRW":[137],"GRID":[139],"demonstrate":[140],"our":[144],"model":[145],"compared":[146],"state-of-the-art":[149],"methods":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}