{"id":"https://openalex.org/W4415540375","doi":"https://doi.org/10.1145/3746027.3755217","title":"FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis","display_name":"FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540375","doi":"https://doi.org/10.1145/3746027.3755217"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755217","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":null,"display_name":"Mengchao Wang","orcid":"https://orcid.org/0009-0008-4207-4434"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengchao Wang","raw_affiliation_strings":["AMAP, Alibaba Group, Chaoyang, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-4207-4434","affiliations":[{"raw_affiliation_string":"AMAP, Alibaba Group, Chaoyang, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qiang Wang","orcid":"https://orcid.org/0009-0006-6266-1287"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Wang","raw_affiliation_strings":["AMAP, Alibaba Group, Chaoyang, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-6266-1287","affiliations":[{"raw_affiliation_string":"AMAP, Alibaba Group, Chaoyang, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101101520","display_name":"Fan Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Jiang","raw_affiliation_strings":["AMAP, Alibaba Group, Chaoyang, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-5801-6431","affiliations":[{"raw_affiliation_string":"AMAP, Alibaba Group, Chaoyang, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yaqi Fan","orcid":"https://orcid.org/0009-0000-2896-3691"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaqi Fan","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Haidian, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-2896-3691","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Haidian, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yunpeng Zhang","orcid":"https://orcid.org/0009-0004-8552-845X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunpeng Zhang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Haidian, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-8552-845X","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Haidian, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075315261","display_name":"Yonggang Qi","orcid":"https://orcid.org/0000-0001-8280-3541"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonggang Qi","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Haidian, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8280-3541","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Haidian, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kun Zhao","orcid":"https://orcid.org/0009-0008-1008-6617"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Zhao","raw_affiliation_strings":["AMAP, Alibaba Group, Chaoyang, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-1008-6617","affiliations":[{"raw_affiliation_string":"AMAP, Alibaba Group, Chaoyang, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064060832","display_name":"Mu Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mu Xu","raw_affiliation_strings":["AMAP, Alibaba Group, Chaoyang, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-6098-4703","affiliations":[{"raw_affiliation_string":"AMAP, Alibaba Group, Chaoyang, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9891","last_page":"9900"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9995999932289124,"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/T11448","display_name":"Face recognition and analysis","score":0.9995999932289124,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","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":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5572999715805054},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5081999897956848},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.414000004529953},{"id":"https://openalex.org/keywords/avatar","display_name":"Avatar","score":0.40380001068115234},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.36320000886917114},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.3531000018119812},{"id":"https://openalex.org/keywords/portrait","display_name":"Portrait","score":0.3474000096321106},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.29899999499320984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7664999961853027},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.642799973487854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5909000039100647},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5572999715805054},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5081999897956848},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.414000004529953},{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.40380001068115234},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.36320000886917114},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C162462552","wikidata":"https://www.wikidata.org/wiki/Q134307","display_name":"Portrait","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C195704467","wikidata":"https://www.wikidata.org/wiki/Q327968","display_name":"Facial expression","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.2944999933242798},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.28839999437332153},{"id":"https://openalex.org/C39394851","wikidata":"https://www.wikidata.org/wiki/Q921594","display_name":"Inter frame","level":4,"score":0.2827000021934509},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C95020103","wikidata":"https://www.wikidata.org/wiki/Q1813492","display_name":"Match moving","level":3,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755217","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2604379605","https://openalex.org/W2769666294","https://openalex.org/W2796822548","https://openalex.org/W2964449965","https://openalex.org/W2969985801","https://openalex.org/W3034552680","https://openalex.org/W3159481202","https://openalex.org/W3197199219","https://openalex.org/W4297095647","https://openalex.org/W4312722235","https://openalex.org/W4312933868","https://openalex.org/W4386071653","https://openalex.org/W4386072021","https://openalex.org/W4390190334","https://openalex.org/W4390872297","https://openalex.org/W4390874575"],"related_works":[],"abstract_inverted_index":{"Creating":[0],"a":[1,6,36,41,64,75,113,137,152],"realistic":[2],"animatable":[3],"avatar":[4],"from":[5],"single":[7],"static":[8],"portrait":[9,170],"remains":[10],"challenging.":[11],"Existing":[12],"approaches":[13],"often":[14],"struggle":[15],"to":[16,47,79],"capture":[17],"subtle":[18],"facial":[19,144,160],"expressions,":[20],"the":[21,27,58,70,89,93,101,109,131,147],"associated":[22],"global":[23,82],"body":[24,163],"movements,":[25],"and":[26,98,162,193],"dynamic":[28],"background.":[29,99],"To":[30,122],"address":[31],"these":[32],"limitations,":[33],"we":[34,73,104,129,150],"propose":[35],"novel":[37],"framework":[38],"that":[39,141,157,180],"leverages":[40],"pretrained":[42],"video":[43],"diffusion":[44],"Transformer":[45],"model":[46],"generate":[48],"high-fidelity,":[49],"coherent":[50,81],"talking":[51],"portraits":[52],"with":[53,119,136,187],"controllable":[54],"motion":[55,83,127,153,191],"dynamics.":[56],"At":[57],"core":[59],"of":[60,169],"our":[61,181],"work":[62],"is":[63],"dual-stage":[65],"audio-visual":[66],"alignment":[67],"strategy.":[68],"In":[69,100],"first":[71],"stage,":[72,103],"employ":[74],"clip-level":[76],"training":[77],"scheme":[78],"establish":[80],"by":[84],"aligning":[85],"audio-driven":[86],"dynamics":[87],"across":[88],"entire":[90],"scene,":[91],"including":[92],"reference":[94,134],"portrait,":[95],"contextual":[96],"objects,":[97],"second":[102],"refine":[105],"lip":[106,174],"movements":[107,171],"at":[108],"frame":[110],"level":[111],"using":[112],"lip-tracing":[114],"mask,":[115],"ensuring":[116],"precise":[117],"synchronization":[118],"audio":[120],"signals.":[121],"preserve":[123],"identity":[124,194],"without":[125],"compromising":[126],"flexibility,":[128],"replace":[130],"commonly":[132],"used":[133],"network":[135],"lightweight":[138],"cross-attention":[139],"module":[140,156],"effectively":[142],"maintains":[143],"consistency":[145],"throughout":[146],"video.":[148],"Furthermore,":[149],"integrate":[151],"intensity":[154],"modulation":[155],"explicitly":[158],"controls":[159],"keypoints":[161],"joint":[164],"trajectories,":[165],"enabling":[166],"fine-grained":[167],"manipulation":[168],"beyond":[172],"mere":[173],"motion.":[175],"Extensive":[176],"experimental":[177],"results":[178],"show":[179],"proposed":[182],"approach":[183],"achieves":[184],"higher":[185],"quality":[186],"better":[188],"realism,":[189],"coherence,":[190],"intensity,":[192],"preservation.":[195],"Our":[196],"demo,":[197],"code,":[198],"models":[199],"can":[200],"be":[201],"found":[202],"on":[203],"this":[204],"page:":[205],"https://fantasy-amap.github.io/fantasy-talking/.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}