{"id":"https://openalex.org/W4402353861","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650230","title":"ERF: Generating Hierarchical Editing Audio-Driven Talking Head Using Dynamic Neural Radiance Fields","display_name":"ERF: Generating Hierarchical Editing Audio-Driven Talking Head Using Dynamic Neural Radiance Fields","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402353861","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650230"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650230","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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/A5103052046","display_name":"Rui Lang","orcid":"https://orcid.org/0009-0002-3444-0461"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rui Lang","raw_affiliation_strings":["Xiamen University,School of Informatics,Xiamen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5103052046"],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17716213,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9986000061035156,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973999857902527,"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/radiance","display_name":"Radiance","score":0.8511718511581421},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7485145926475525},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.6923143863677979},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.40253108739852905},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3906978666782379},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3885849714279175},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38758575916290283},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.11670145392417908},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.0818248987197876}],"concepts":[{"id":"https://openalex.org/C23690007","wikidata":"https://www.wikidata.org/wiki/Q1411145","display_name":"Radiance","level":2,"score":0.8511718511581421},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7485145926475525},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.6923143863677979},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.40253108739852905},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3906978666782379},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3885849714279175},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38758575916290283},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.11670145392417908},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0818248987197876},{"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/ijcnn60899.2024.10650230","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2133665775","https://openalex.org/W2604379605","https://openalex.org/W2962770929","https://openalex.org/W2962785568","https://openalex.org/W2969985801","https://openalex.org/W2981263323","https://openalex.org/W3019952993","https://openalex.org/W3034431451","https://openalex.org/W3035574324","https://openalex.org/W3036601975","https://openalex.org/W3037784242","https://openalex.org/W3081492798","https://openalex.org/W3097792222","https://openalex.org/W3101631197","https://openalex.org/W3109114891","https://openalex.org/W3173102319","https://openalex.org/W3174763799","https://openalex.org/W3178406257","https://openalex.org/W3182714435","https://openalex.org/W3204663154","https://openalex.org/W3211147706","https://openalex.org/W3215121054","https://openalex.org/W4200150166","https://openalex.org/W4200630629","https://openalex.org/W4214926101","https://openalex.org/W4221144911","https://openalex.org/W4283761699","https://openalex.org/W4285981704","https://openalex.org/W4295312788","https://openalex.org/W4309876056","https://openalex.org/W4311034013","https://openalex.org/W4311804540","https://openalex.org/W4312301053","https://openalex.org/W4312546057","https://openalex.org/W4312853918","https://openalex.org/W4312959196","https://openalex.org/W4312990833","https://openalex.org/W4318906029","https://openalex.org/W4379527433","https://openalex.org/W4386065566","https://openalex.org/W4386066205","https://openalex.org/W4386072021","https://openalex.org/W4386075893","https://openalex.org/W4386076143","https://openalex.org/W4386076215","https://openalex.org/W4386076250","https://openalex.org/W4386076391","https://openalex.org/W4390872116","https://openalex.org/W6631190155","https://openalex.org/W6766978945","https://openalex.org/W6779809370","https://openalex.org/W6780218876","https://openalex.org/W6839604326","https://openalex.org/W6847187194","https://openalex.org/W6849049266"],"related_works":["https://openalex.org/W2896728493","https://openalex.org/W2392142157","https://openalex.org/W2043512367","https://openalex.org/W4321518006","https://openalex.org/W2331836163","https://openalex.org/W1994657804","https://openalex.org/W2005276308","https://openalex.org/W1970182911","https://openalex.org/W2024462231","https://openalex.org/W2347721387"],"abstract_inverted_index":{"Audio-driven":[0],"talking":[1,25,46,63,86,109,137,159,181],"head":[2,26,31,87,138,182],"generation":[3],"has":[4],"long":[5],"been":[6],"a":[7,35,55,80,88,149,163,199],"challenging":[8],"problem":[9],"in":[10],"computer":[11],"vision.":[12],"Most":[13],"existing":[14],"research":[15],"focused":[16],"on":[17,96],"improving":[18],"the":[19,42,77,85,97,101,104,108,116,120,133,136,140,146,205],"cross-modal":[20],"mapping":[21],"of":[22,38,44,103,107,135,176,192],"audio":[23,118,129],"and":[24,30,70,194],"for":[27,60,139,165],"facial":[28],"expressions":[29],"pose.":[32],"However,":[33],"only":[34],"limited":[36],"number":[37],"studies":[39],"have":[40],"explored":[41],"editing":[43,58,72,95,134,166,191],"personalized":[45,62,190],"head.":[47,64,110],"To":[48,154],"address":[49],"this":[50,52],"gap,":[51],"paper":[53],"introduces":[54],"novel":[56],"hierarchical":[57],"approach":[59],"generating":[61,177],"Specifically,":[65],"to":[66,83,99,113,126,131,198,204,208],"achieve":[67],"more":[68],"flexible":[69],"diverse":[71],"effects,":[73],"we":[74,92,123,144,161],"first":[75,141],"edit":[76],"portrait":[78,98],"at":[79],"coarse-grained":[81],"level":[82],"give":[84],"preliminary":[89],"style.":[90],"Then,":[91],"perform":[93],"fine-grained":[94],"complete":[100,145],"control":[102],"local":[105],"details":[106],"In":[111],"order":[112],"better":[114],"match":[115],"driving":[117,128],"with":[119],"edited":[121,158,179],"portrait,":[122],"also":[124],"propose":[125,162],"introduce":[127],"information":[130],"guide":[132],"time.":[142],"Finally,":[143],"rendering":[147],"using":[148,183],"dynamic":[150,184],"neural":[151,185],"radiance":[152,186],"field.":[153],"generate":[155],"higher":[156],"quality":[157],"head,":[160],"strategy":[164],"degree":[167],"selection.":[168],"Extensive":[169],"experiments":[170],"demonstrate":[171],"that":[172],"our":[173],"proposed":[174],"method":[175],"hierarchically":[178],"audio-driven":[180],"fields":[187],"(ERF)":[188],"achieves":[189],"portraits":[193],"protects":[195],"user":[196],"privacy":[197],"certain":[200],"extent.":[201],"Please":[202],"go":[203],"link":[206],"below":[207],"view":[209],"detailed":[210],"video":[211],"results:":[212],"https://drive.google.com/drive/folders/1Jo4XD2fac5ptSopOL7SG2J6bWkWIF3qZ?usp=sharing":[213]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}