{"id":"https://openalex.org/W4403791033","doi":"https://doi.org/10.1145/3664647.3681644","title":"Control-Talker: A Rapid-Customization Talking Head Generation Method for Multi-Condition Control and High-Texture Enhancement","display_name":"Control-Talker: A Rapid-Customization Talking Head Generation Method for Multi-Condition Control and High-Texture Enhancement","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791033","doi":"https://doi.org/10.1145/3664647.3681644"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681644","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5101374929","display_name":"Yiding Li","orcid":"https://orcid.org/0009-0003-2339-601X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiding Li","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089799495","display_name":"Lingyun Yu","orcid":"https://orcid.org/0000-0001-6403-761X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingyun Yu","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107191669","display_name":"Li Wang","orcid":"https://orcid.org/0009-0004-7234-9145"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078162380","display_name":"Hongtao Xie","orcid":"https://orcid.org/0000-0002-6249-5315"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongtao Xie","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101374929"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.2493,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54497529,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3519","last_page":"3527"},"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":0.9987999796867371,"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":0.9987999796867371,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.984499990940094,"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":0.6406024694442749},{"id":"https://openalex.org/keywords/texture","display_name":"Texture (cosmology)","score":0.5472296476364136},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5323793292045593},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.5267148613929749},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5078142285346985},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4208148121833801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39691320061683655},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11867675185203552},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.07409253716468811},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.0697786808013916}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6406024694442749},{"id":"https://openalex.org/C2781195486","wikidata":"https://www.wikidata.org/wiki/Q289436","display_name":"Texture (cosmology)","level":3,"score":0.5472296476364136},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5323793292045593},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.5267148613929749},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5078142285346985},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4208148121833801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39691320061683655},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11867675185203552},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.07409253716468811},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0697786808013916},{"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:10.1145/3664647.3681644","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2134963900","https://openalex.org/W2738406145","https://openalex.org/W2769666294","https://openalex.org/W2962770929","https://openalex.org/W2962785568","https://openalex.org/W2963073614","https://openalex.org/W3019952993","https://openalex.org/W3034257218","https://openalex.org/W3081492798","https://openalex.org/W3101631197","https://openalex.org/W3109114891","https://openalex.org/W3180770160","https://openalex.org/W3180794345","https://openalex.org/W3197199219","https://openalex.org/W3204680331","https://openalex.org/W3211147706","https://openalex.org/W4200174933","https://openalex.org/W4200630629","https://openalex.org/W4214626920","https://openalex.org/W4221145616","https://openalex.org/W4280631290","https://openalex.org/W4304014863","https://openalex.org/W4312301053","https://openalex.org/W4312444931","https://openalex.org/W4312990833","https://openalex.org/W4386066263","https://openalex.org/W4386072006","https://openalex.org/W4386072021","https://openalex.org/W4386076090","https://openalex.org/W4390873054","https://openalex.org/W4391216149","https://openalex.org/W4402727741","https://openalex.org/W4402727853","https://openalex.org/W4402774219"],"related_works":["https://openalex.org/W2109940557","https://openalex.org/W2466832359","https://openalex.org/W4391210591","https://openalex.org/W1582019636","https://openalex.org/W1499005795","https://openalex.org/W3172493050","https://openalex.org/W4385420271","https://openalex.org/W4312192618","https://openalex.org/W2593798266","https://openalex.org/W4385414918"],"abstract_inverted_index":{"In":[0,78,122,189],"recent":[1],"years,":[2],"the":[3,14,34,51,74,108,123,134,155,158,170,185,190,194,200,204,247],"field":[4],"of":[5,27,37,92,157,184,203,211],"talking":[6,95],"head":[7,60,96],"generation":[8,100],"has":[9],"made":[10],"significant":[11],"strides.":[12],"However,":[13],"need":[15],"for":[16,20,33,219,241],"substantial":[17],"computational":[18],"resources":[19],"model":[21,38,97,131,206,248,274],"training,":[22],"coupled":[23],"with":[24],"a":[25,83,129,140,149,165,175,212,237],"scarcity":[26],"high-quality":[28,99,135],"video":[29],"data,":[30],"poses":[31,61],"challenges":[32],"rapid":[35,90],"customization":[36,91,221],"to":[39,53,88,138,153,249],"specific":[40,213],"individual.":[41,214],"Additionally,":[42,272],"existing":[43],"models":[44],"usually":[45],"only":[46],"support":[47],"single-modal":[48],"control,":[49],"lacking":[50],"ability":[52],"generate":[54],"vivid":[55],"facial":[56,143,176,182],"expressions":[57],"and":[58,98,117,244,254,261,279],"controllable":[59,142],"based":[62,101],"on":[63,102,133,207],"multiple":[64],"conditions":[65],"such":[66],"as":[67,174],"audio,":[68],"video,":[69,245],"etc.":[70],"These":[71],"limitations":[72],"restricts":[73],"models'":[75],"widespread":[76],"application.":[77],"this":[79],"paper,":[80],"we":[81,106,127,146,235],"introduce":[82],"two-stage":[84],"method":[85,240,267],"called":[86],"Control-Talker":[87],"achieve":[89],"identity":[93,118,191,195,220],"in":[94],"multimodal":[103],"conditions.":[104,258],"Specifically,":[105],"divide":[107],"training":[109,232,277],"process":[110,218],"into":[111],"two":[112],"stages:":[113],"prior":[114,124],"learning":[115,125],"stage":[116],"rapid-customization":[119,192],"stage.":[120],"1)":[121],"stage,":[126,193],"leverage":[128],"diffusion-based":[130],"pre-trained":[132],"image":[136],"dataset":[137],"acquire":[139],"robust":[141],"prior.":[144],"Meanwhile,":[145],"innovatively":[147],"propose":[148,236],"high-frequency":[150,166],"ControlNet":[151],"structure":[152,162],"enhance":[154],"fidelity":[156],"synthesized":[159],"results.":[160],"This":[161],"adeptly":[163],"extracts":[164],"feature":[167],"map":[168],"from":[169],"source":[171,186],"image,":[172],"serving":[173],"texture":[177,183],"prior,":[178],"thereby":[179,229],"excellently":[180],"preserving":[181],"image.":[187],"2)":[188],"is":[196],"fixed":[197],"by":[198],"fine-tuning":[199,217],"U-Net":[201],"part":[202],"diffusion":[205],"merely":[208],"several":[209],"images":[210],"The":[215],"entire":[216],"can":[222],"be":[223],"completed":[224],"within":[225],"approximately":[226],"ten":[227],"minutes,":[228],"significantly":[230],"reducing":[231],"costs.":[233],"Further,":[234],"unified":[238],"driving":[239],"both":[242],"audio":[243],"enabling":[246],"precisely":[250],"control":[251],"expressions,":[252],"poses,":[253],"lighting":[255],"under":[256],"multi":[257],"Extensive":[259],"experiments":[260],"visual":[262],"results":[263],"demonstrate":[264],"that":[265],"our":[266,273],"outperforms":[268],"other":[269],"state-of-the-art":[270],"models.":[271],"demonstrates":[275],"reduced":[276],"costs":[278],"lower":[280],"data":[281],"requirements.":[282]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}