{"id":"https://openalex.org/W4411635462","doi":"https://doi.org/10.1145/3731715.3733276","title":"AnchorTalk: High-Fidelity Upper-Body Talking Human Generation From Speech","display_name":"AnchorTalk: High-Fidelity Upper-Body Talking Human Generation From Speech","publication_year":2025,"publication_date":"2025-06-25","ids":{"openalex":"https://openalex.org/W4411635462","doi":"https://doi.org/10.1145/3731715.3733276"},"language":"en","primary_location":{"id":"doi:10.1145/3731715.3733276","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733276","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","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/A5111043676","display_name":"Yali Cai","orcid":"https://orcid.org/0000-0003-4039-895X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yali Cai","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058476148","display_name":"Peng Qiao","orcid":"https://orcid.org/0000-0001-6752-7892"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Qiao","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100440903","display_name":"Dongsheng Li","orcid":"https://orcid.org/0000-0001-9743-2034"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongsheng Li","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5111043676"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16912331,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"25","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9972000122070312,"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":0.9930999875068665,"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/computer-science","display_name":"Computer science","score":0.6360812187194824},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.549492359161377},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.4517412483692169},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.17280426621437073},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08785048127174377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6360812187194824},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.549492359161377},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.4517412483692169},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.17280426621437073},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08785048127174377}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731715.3733276","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733276","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[{"id":"https://openalex.org/G881855998","display_name":null,"funder_award_id":"61902415","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2107037917","https://openalex.org/W2128409098","https://openalex.org/W3098994456","https://openalex.org/W3175779516","https://openalex.org/W3197199219","https://openalex.org/W3202128205","https://openalex.org/W4214626920","https://openalex.org/W4313472219","https://openalex.org/W4319770604","https://openalex.org/W4385489997","https://openalex.org/W4386066256","https://openalex.org/W4386075487","https://openalex.org/W4386075984","https://openalex.org/W4386083081","https://openalex.org/W4390872116","https://openalex.org/W4394597549","https://openalex.org/W4400413497","https://openalex.org/W4402112200","https://openalex.org/W4402726971","https://openalex.org/W4402727178","https://openalex.org/W4402727180","https://openalex.org/W4402754063","https://openalex.org/W4403676198","https://openalex.org/W4403780586","https://openalex.org/W4403792529"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"While":[0],"most":[1],"existing":[2],"speech-driven":[3],"talking":[4,21,71,204],"head":[5,147,167],"generation":[6,95,126],"methods":[7],"provide":[8],"effective":[9],"solutions,":[10],"they":[11],"primarily":[12],"focus":[13],"on":[14,62,178],"the":[15,114,117,123,141,176,182,192],"facial":[16,36,97,152,158,171],"area.":[17],"However,":[18],"producing":[19,68],"upper-body":[20,203],"videos":[22,206],"from":[23,207],"speech":[24,31,101,105],"remains":[25],"challenging.":[26],"Addressing":[27],"how":[28],"to":[29,32,74,112,134,139,151,169,186],"use":[30],"simultaneously":[33],"drive":[34,113],"subtle":[35],"motion":[37,41,80,115,156],"and":[38,78,96,109,119,154,194],"large-scale":[39],"body":[40,47,118,137,142],"while":[42],"generating":[43,200],"naturally":[44],"synchronized":[45],"upper":[46],"video":[48],"frames":[49],"is":[50],"urgent.":[51],"In":[52],"this":[53,162],"study,":[54],"we":[55,85,128,164],"propose":[56,129,165],"AnchorTalk,":[57],"a":[58,82,87,130,166,179],"novel":[59,187],"system":[60,183],"based":[61],"tri-plane":[63],"hash":[64],"NeRF,":[65],"capable":[66],"of":[67,92,116,196],"high-quality":[69],"anchor-style":[70],"videos.":[72],"Firstly,":[73],"integrate":[75],"both":[76],"rigid":[77],"non-rigid":[79],"within":[81],"unified":[83],"system,":[84],"introduce":[86],"coarse-to-fine":[88],"framework":[89],"that":[90],"consists":[91],"coarse":[93,124],"pose":[94,125],"details":[98],"optimization.":[99,159],"A":[100],"disentanglement":[102],"encoder":[103],"decouples":[104],"features":[106,111],"into":[107],"pose-related":[108],"head-related":[110],"head.":[120],"Secondly,":[121],"during":[122,157],"phase,":[127],"geometry":[131],"correction":[132],"module":[133],"obtain":[135],"precise":[136],"parameters":[138,148],"guide":[140],"motion.":[143],"Thirdly,":[144],"less":[145],"detailed":[146],"can":[149,184],"lead":[150],"distortion":[153],"disjointed":[155],"To":[160],"mitigate":[161],"issue,":[163],"controller":[168],"capture":[170],"expressions":[172],"accurately.":[173],"By":[174],"fine-tuning":[175],"model":[177],"one-minute":[180],"video,":[181],"generalize":[185],"identities.":[188],"Experimental":[189],"results":[190],"validate":[191],"effectiveness":[193],"feasibility":[195],"our":[197],"method":[198],"in":[199],"high-quality,":[201],"coherent":[202],"human":[205],"speech.":[208]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}