{"id":"https://openalex.org/W4401384667","doi":"https://doi.org/10.1007/s44267-024-00057-8","title":"DialogueNeRF: towards realistic avatar face-to-face conversation video generation","display_name":"DialogueNeRF: towards realistic avatar face-to-face conversation video generation","publication_year":2024,"publication_date":"2024-08-07","ids":{"openalex":"https://openalex.org/W4401384667","doi":"https://doi.org/10.1007/s44267-024-00057-8"},"language":"en","primary_location":{"id":"doi:10.1007/s44267-024-00057-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-024-00057-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-024-00057-8.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://link.springer.com/content/pdf/10.1007/s44267-024-00057-8.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048907728","display_name":"Yichao Yan","orcid":"https://orcid.org/0000-0003-3209-8965"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yichao Yan","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009692391","display_name":"Zanwei Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zanwei Zhou","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100338326","display_name":"Zi Wang","orcid":"https://orcid.org/0000-0001-9081-7185"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zi Wang","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113204824","display_name":"Jingnan Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingnan Gao","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113323904","display_name":"Xiaokang Yang","orcid":"https://orcid.org/0009-0000-5497-8811"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaokang Yang","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5048907728"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":3.1496,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.92963763,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"2","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","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"}},"topics":[{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","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/T12290","display_name":"Human Motion and Animation","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9975000023841858,"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/avatar","display_name":"Avatar","score":0.8588823676109314},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.7366350889205933},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6040071249008179},{"id":"https://openalex.org/keywords/face-to-face","display_name":"Face-to-face","score":0.5864418745040894},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5861108899116516},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4219723343849182},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3929811418056488},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36942726373672485},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.27311861515045166},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2581806182861328},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1790933609008789}],"concepts":[{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.8588823676109314},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.7366350889205933},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6040071249008179},{"id":"https://openalex.org/C2777359053","wikidata":"https://www.wikidata.org/wiki/Q2463823","display_name":"Face-to-face","level":2,"score":0.5864418745040894},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5861108899116516},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4219723343849182},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3929811418056488},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36942726373672485},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.27311861515045166},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2581806182861328},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1790933609008789},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44267-024-00057-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-024-00057-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-024-00057-8.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:c0a0ab319777480bb6b6ad987b303fbe","is_oa":true,"landing_page_url":"https://doaj.org/article/c0a0ab319777480bb6b6ad987b303fbe","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Visual Intelligence, Vol 2, Iss 1, Pp 1-15 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44267-024-00057-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44267-024-00057-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44267-024-00057-8.pdf","source":{"id":"https://openalex.org/S4387289164","display_name":"Visual Intelligence","issn_l":"2731-9008","issn":["2731-9008"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6800000071525574}],"awards":[{"id":"https://openalex.org/G2597775472","display_name":null,"funder_award_id":"21013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7308652284","display_name":null,"funder_award_id":"62201342","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7659021256","display_name":null,"funder_award_id":"62101325","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8278618053","display_name":null,"funder_award_id":"6210132","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8721642152","display_name":null,"funder_award_id":"2021SHZDZX0102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8955107213","display_name":null,"funder_award_id":"Major","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G96616661","display_name":null,"funder_award_id":"210132","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401384667.pdf","grobid_xml":"https://content.openalex.org/works/W4401384667.grobid-xml"},"referenced_works_count":75,"referenced_works":["https://openalex.org/W2079995984","https://openalex.org/W2081074144","https://openalex.org/W2097470427","https://openalex.org/W2125320996","https://openalex.org/W2131494463","https://openalex.org/W2133665775","https://openalex.org/W2162220380","https://openalex.org/W2192412620","https://openalex.org/W2193413348","https://openalex.org/W2398936787","https://openalex.org/W2419539795","https://openalex.org/W2484951126","https://openalex.org/W2531563875","https://openalex.org/W2604292070","https://openalex.org/W2724314443","https://openalex.org/W2738406145","https://openalex.org/W2739192055","https://openalex.org/W2745771616","https://openalex.org/W2784519437","https://openalex.org/W2796931171","https://openalex.org/W2798539789","https://openalex.org/W2888093771","https://openalex.org/W2889233255","https://openalex.org/W2900939497","https://openalex.org/W2904367110","https://openalex.org/W2904868363","https://openalex.org/W2913738669","https://openalex.org/W2913954081","https://openalex.org/W2914304175","https://openalex.org/W2914584698","https://openalex.org/W2914753947","https://openalex.org/W2921075900","https://openalex.org/W2944294033","https://openalex.org/W2944661720","https://openalex.org/W2948913018","https://openalex.org/W2962854379","https://openalex.org/W2970971581","https://openalex.org/W2979894294","https://openalex.org/W2995238198","https://openalex.org/W3004048296","https://openalex.org/W3011537551","https://openalex.org/W3039828778","https://openalex.org/W3081492798","https://openalex.org/W3109420014","https://openalex.org/W3111632845","https://openalex.org/W3115372334","https://openalex.org/W3136656704","https://openalex.org/W3154411171","https://openalex.org/W3155357996","https://openalex.org/W3180589757","https://openalex.org/W3197199219","https://openalex.org/W3198225285","https://openalex.org/W3211147706","https://openalex.org/W4200174933","https://openalex.org/W4200382072","https://openalex.org/W4212817947","https://openalex.org/W4221151978","https://openalex.org/W4236965008","https://openalex.org/W4286611278","https://openalex.org/W4298334798","https://openalex.org/W4300874750","https://openalex.org/W4301357669","https://openalex.org/W4301409532","https://openalex.org/W4309617235","https://openalex.org/W4309764400","https://openalex.org/W4385289606","https://openalex.org/W4386315163","https://openalex.org/W6631190155","https://openalex.org/W6735927292","https://openalex.org/W6736996214","https://openalex.org/W6750008037","https://openalex.org/W6791838852","https://openalex.org/W6795892701","https://openalex.org/W6797179183","https://openalex.org/W6948150082"],"related_works":["https://openalex.org/W3196465490","https://openalex.org/W2167654528","https://openalex.org/W3214383701","https://openalex.org/W4213235153","https://openalex.org/W2070454487","https://openalex.org/W4388505810","https://openalex.org/W411361004","https://openalex.org/W2560105438","https://openalex.org/W2612607254","https://openalex.org/W650744398"],"abstract_inverted_index":{"Abstract":[0],"Conversation":[1,67],"is":[2,69,139],"an":[3],"essential":[4],"component":[5],"of":[6,16,39,84,148,217],"virtual":[7],"avatar":[8],"activities":[9],"in":[10,25,205,220,230],"the":[11,14,36,82,91,95,108,121,124,142,146,149,171,175,218,221,228,231],"metaverse.":[12],"With":[13],"development":[15],"natural":[17,215],"language":[18],"processing,":[19],"significant":[20],"breakthroughs":[21],"have":[22],"been":[23],"made":[24],"text":[26],"and":[27,60,123,155,199,214,242],"voice":[28],"conversation":[29,65,162,192],"generation.":[30,51],"However,":[31],"face-to-face":[32,64,161],"conversations":[33],"account":[34],"for":[35],"vast":[37],"majority":[38],"daily":[40],"conversations,":[41],"while":[42,145],"most":[43],"existing":[44],"methods":[45],"focused":[46],"on":[47,107,152,183,238],"single-person":[48,73],"talking":[49,74,87],"head":[50,75],"In":[52,97,158],"this":[53,98,159,184],"work,":[54],"we":[55,100,118,186],"take":[56],"a":[57,102,127,189,239],"step":[58],"further":[59],"consider":[61],"generating":[62],"realistic":[63,240],"videos.":[66,223],"generation":[68,83],"more":[70],"challenging":[71],"than":[72],"generation,":[76],"because":[77],"it":[78],"requires":[79],"not":[80],"only":[81],"photo-realistic":[85],"individual":[86,135,244],"heads,":[88],"but":[89],"also":[90,187],"listener\u2019s":[92],"response":[93,147],"to":[94,113,133,179,236],"speaker.":[96],"paper,":[99],"propose":[101],"novel":[103],"unified":[104],"framework":[105,129],"based":[106],"neural":[109],"radiance":[110],"field":[111],"(NeRF)":[112],"address":[114],"these":[115],"challenges.":[116],"Specifically,":[117],"model":[119],"both":[120,153],"speaker":[122,138],"listener":[125,150],"with":[126,169],"NeRF":[128],"under":[130],"different":[131,206],"conditions":[132],"control":[134],"expressions.":[136],"The":[137],"driven":[140],"by":[141],"audio":[143],"signal,":[144],"depends":[151],"visual":[154],"acoustic":[156],"information.":[157],"way,":[160],"videos":[163,233],"are":[164,234],"generated":[165,222],"between":[166],"human":[167,191],"avatars,":[168],"all":[170],"interlocutors":[172],"modeled":[173],"within":[174],"same":[176],"network.":[177],"Moreover,":[178],"facilitate":[180],"future":[181],"research":[182],"task,":[185],"collected":[188],"new":[190],"dataset":[193],"containing":[194],"34":[195],"video":[196],"clips.":[197],"Quantitative":[198],"qualitative":[200],"experiments":[201],"evaluate":[202],"our":[203],"method":[204],"aspects,":[207],"e.g.,":[208],"image":[209],"quality,":[210],"pose":[211],"sequence":[212],"trend,":[213],"rendering":[216],"scene":[219],"Experimental":[224],"results":[225],"demonstrate":[226],"that":[227],"avatars":[229],"resulting":[232],"able":[235],"carry":[237],"conversation,":[241],"maintain":[243],"styles.":[245]},"counts_by_year":[{"year":2025,"cited_by_count":13}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}