{"id":"https://openalex.org/W4400573497","doi":"https://doi.org/10.1145/3641519.3657459","title":"X-Portrait: Expressive Portrait Animation with Hierarchical Motion Attention","display_name":"X-Portrait: Expressive Portrait Animation with Hierarchical Motion Attention","publication_year":2024,"publication_date":"2024-07-12","ids":{"openalex":"https://openalex.org/W4400573497","doi":"https://doi.org/10.1145/3641519.3657459"},"language":"en","primary_location":{"id":"doi:10.1145/3641519.3657459","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3641519.3657459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers 24","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/A5102446690","display_name":"You Xie","orcid":"https://orcid.org/0000-0001-7320-6518"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"You Xie","raw_affiliation_strings":["ByteDance Inc., United States of America"],"raw_orcid":"https://orcid.org/0000-0001-7320-6518","affiliations":[{"raw_affiliation_string":"ByteDance Inc., United States of America","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100691898","display_name":"Hongyi Xu","orcid":"https://orcid.org/0009-0006-4455-5632"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongyi Xu","raw_affiliation_strings":["ByteDance Inc., United States of America"],"raw_orcid":"https://orcid.org/0009-0006-4455-5632","affiliations":[{"raw_affiliation_string":"ByteDance Inc., United States of America","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012261844","display_name":"Guoxian Song","orcid":"https://orcid.org/0000-0002-3664-572X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guoxian Song","raw_affiliation_strings":["ByteDance Inc., United States of America"],"raw_orcid":"https://orcid.org/0000-0002-3664-572X","affiliations":[{"raw_affiliation_string":"ByteDance Inc., United States of America","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003677947","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0003-4378-0193"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["ByteDance Inc., United States of America"],"raw_orcid":"https://orcid.org/0000-0003-4378-0193","affiliations":[{"raw_affiliation_string":"ByteDance Inc., United States of America","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100347727","display_name":"Yichun Shi","orcid":"https://orcid.org/0000-0003-3121-8785"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yichun Shi","raw_affiliation_strings":["ByteDance Inc., United States of America"],"raw_orcid":"https://orcid.org/0000-0003-3121-8785","affiliations":[{"raw_affiliation_string":"ByteDance Inc., United States of America","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081407963","display_name":"Linjie Luo","orcid":"https://orcid.org/0000-0001-6322-1175"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linjie Luo","raw_affiliation_strings":["ByteDance Inc., United States of America"],"raw_orcid":"https://orcid.org/0000-0001-6322-1175","affiliations":[{"raw_affiliation_string":"ByteDance Inc., United States of America","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.6668,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.97350674,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9987000226974487,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9965999722480774,"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/portrait","display_name":"Portrait","score":0.9436420798301697},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.7471276521682739},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6250115036964417},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.5576058030128479},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5269457101821899},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.4615078270435333},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42125675082206726},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3753131031990051},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.3268624544143677},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3219253122806549},{"id":"https://openalex.org/keywords/art-history","display_name":"Art history","score":0.26812005043029785}],"concepts":[{"id":"https://openalex.org/C162462552","wikidata":"https://www.wikidata.org/wiki/Q134307","display_name":"Portrait","level":2,"score":0.9436420798301697},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.7471276521682739},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6250115036964417},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5576058030128479},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5269457101821899},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.4615078270435333},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42125675082206726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3753131031990051},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.3268624544143677},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3219253122806549},{"id":"https://openalex.org/C52119013","wikidata":"https://www.wikidata.org/wiki/Q50637","display_name":"Art history","level":1,"score":0.26812005043029785}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3641519.3657459","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3641519.3657459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers 24","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":26,"referenced_works":["https://openalex.org/W2331128040","https://openalex.org/W2902266071","https://openalex.org/W2962730651","https://openalex.org/W2963168844","https://openalex.org/W3002992380","https://openalex.org/W3034371424","https://openalex.org/W3035719652","https://openalex.org/W3036167779","https://openalex.org/W3091249416","https://openalex.org/W3178284600","https://openalex.org/W3180794345","https://openalex.org/W4281485151","https://openalex.org/W4286696412","https://openalex.org/W4304014863","https://openalex.org/W4311137635","https://openalex.org/W4312473638","https://openalex.org/W4312933868","https://openalex.org/W4323338379","https://openalex.org/W4385801140","https://openalex.org/W4390872774","https://openalex.org/W4390873054","https://openalex.org/W4390874403","https://openalex.org/W6600376255","https://openalex.org/W6601067093","https://openalex.org/W6602344735","https://openalex.org/W6779823529"],"related_works":["https://openalex.org/W2121378366","https://openalex.org/W3112102641","https://openalex.org/W2013184069","https://openalex.org/W2535923857","https://openalex.org/W2989004599","https://openalex.org/W1976926596","https://openalex.org/W126583968","https://openalex.org/W2532377291","https://openalex.org/W2359575859","https://openalex.org/W2215755978"],"abstract_inverted_index":{"We":[0],"propose":[1],"X-Portrait,":[2],"an":[3],"innovative":[4],"conditional":[5],"diffusion":[6,61],"model":[7,62],"tailored":[8],"for":[9],"generating":[10,188],"expressive":[11,180],"and":[12,41,72,179,183],"temporally":[13],"coherent":[14],"portrait":[15,21,190],"animation.":[16],"Specifically,":[17],"given":[18],"a":[19,34,59,119,173],"single":[20],"as":[22,63,92],"appearance":[23,161],"reference,":[24],"we":[25,53,146],"aim":[26],"to":[27,86,101,130,137],"animate":[28],"it":[29],"with":[30,46,75,118,152,192],"motion":[31,96,113,128,149],"derived":[32],"from":[33,106,142,159],"driving":[35,109,144,181],"video,":[36],"capturing":[37],"both":[38],"highly":[39],"dynamic":[40],"subtle":[42],"facial":[43,93,177],"expressions":[44],"along":[45],"wide-range":[47],"head":[48,70],"movements.":[49],"As":[50],"its":[51,185],"core,":[52],"leverage":[54],"the":[55,64,80,103,107,127,139,143,160,167],"generative":[56],"prior":[57],"of":[58,82,170,176],"pre-trained":[60],"rendering":[65],"backbone,":[66],"while":[67],"achieve":[68],"fine-grained":[69],"pose":[71],"expression":[73],"control":[74,97,122,150],"novel":[76],"controlling":[77],"signals":[78],"within":[79],"framework":[81],"ControlNet.":[83],"In":[84],"contrast":[85],"conventional":[87],"coarse":[88],"explicit":[89],"controls":[90],"such":[91],"landmarks,":[94],"our":[95,148],"module":[98,123],"is":[99,115],"learned":[100],"interpret":[102],"dynamics":[104],"directly":[105],"original":[108],"RGB":[110],"inputs.":[111],"The":[112],"accuracy":[114],"further":[116],"enhanced":[117],"patch-based":[120],"local":[121],"that":[124],"effectively":[125],"enhance":[126],"attention":[129],"small-scale":[131],"nuances":[132],"like":[133],"eyeball":[134],"positions.":[135],"Notably,":[136],"mitigate":[138],"identity":[140,195],"leakage":[141],"signals,":[145],"train":[147],"modules":[151],"scaling-augmented":[153],"cross-identity":[154],"images,":[155],"ensuring":[156],"maximized":[157],"disentanglement":[158],"reference":[162],"modules.":[163],"Experimental":[164],"results":[165],"demonstrate":[166],"universal":[168],"effectiveness":[169],"X-Portrait":[171],"across":[172],"diverse":[174],"range":[175],"portraits":[178],"sequences,":[182],"showcase":[184],"proficiency":[186],"in":[187],"captivating":[189],"animations":[191],"consistently":[193],"maintained":[194],"characteristics.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}