{"id":"https://openalex.org/W4385823372","doi":"https://doi.org/10.21437/interspeech.2023-749","title":"Emotional Talking Head Generation based on Memory-Sharing and Attention-Augmented Networks","display_name":"Emotional Talking Head Generation based on Memory-Sharing and Attention-Augmented Networks","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823372","doi":"https://doi.org/10.21437/interspeech.2023-749"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-749","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-749","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5102003658","display_name":"Jianrong Wang","orcid":"https://orcid.org/0000-0002-8980-1634"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jianrong Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101134685","display_name":"Yaxin Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaxin Zhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418765","display_name":"Li Liu","orcid":"https://orcid.org/0000-0001-9685-6599"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051440813","display_name":"Tianyi Xu","orcid":"https://orcid.org/0000-0002-9108-913X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianyi Xu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015487349","display_name":"Qi Li","orcid":"https://orcid.org/0000-0001-7858-2758"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100444232","display_name":"Sen Li","orcid":"https://orcid.org/0000-0001-7850-1866"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sen Li","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102003658"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.676,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.95255257,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13565","display_name":"Education and Learning Interventions","score":0.8723999857902527,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13565","display_name":"Education and Learning Interventions","score":0.8723999857902527,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.839900016784668,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.8151999711990356,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7220034003257751},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5447701811790466},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32636579871177673},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.08191245794296265}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7220034003257751},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5447701811790466},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32636579871177673},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.08191245794296265},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2023-749","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-749","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-139916","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-139916","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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W4246426965","https://openalex.org/W3106945349"],"abstract_inverted_index":{"Given":[0],"an":[1,82],"audio":[2,48,98],"clip":[3],"and":[4,47,50,81,116,123],"a":[5,19,68,75,110],"reference":[6],"face":[7,104],"image,":[8],"the":[9,12,38,52,56,60,113,117,128,131,135],"goal":[10],"of":[11,28,41,59,74,130],"talking":[13,21,30,69],"head":[14,22,31,70],"generation":[15,71],"is":[16],"to":[17,54,99,134],"generate":[18],"high-fidelity":[20],"video.":[23],"Although":[24],"some":[25,35],"audio-driven":[26],"methods":[27],"generating":[29],"videos":[32],"have":[33,126],"made":[34,141],"achievements":[36],"in":[37],"past,":[39],"most":[40],"them":[42],"only":[43],"focused":[44],"on":[45,86],"lip":[46],"synchronization":[49],"lack":[51],"ability":[53],"reproduce":[55],"facial":[57],"expressions":[58],"target":[61],"person.":[62],"To":[63],"this":[64],"end,":[65],"we":[66],"propose":[67],"model":[72],"consisting":[73],"Memory-Sharing":[76],"Emotion":[77],"Feature":[78],"extractor":[79],"(MSEF)":[80],"Attention-Augmented":[83],"Translator":[84],"based":[85],"U-net":[87],"(AATU).":[88],"Firstly,":[89],"MSEF":[90],"can":[91],"extract":[92],"implicit":[93],"emotional":[94,103],"auxiliary":[95],"features":[96],"from":[97],"estimate":[100],"more":[101],"accurate":[102],"landmarks.":[105],"Secondly,":[106],"AATU":[107],"acts":[108],"as":[109],"translator":[111],"between":[112],"estimated":[114],"landmarks":[115],"photo-realistic":[118],"video":[119],"frames.":[120],"Extensive":[121],"qualitative":[122],"quantitative":[124],"experiments":[125],"shown":[127],"superiority":[129],"proposed":[132],"method":[133],"previous":[136],"works.":[137],"Codes":[138],"will":[139],"be":[140],"publicly":[142],"available.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4}],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}
