{"id":"https://openalex.org/W4401024028","doi":"https://doi.org/10.24963/ijcai.2024/198","title":"Zero-shot High-fidelity and Pose-controllable Character Animation","display_name":"Zero-shot High-fidelity and Pose-controllable Character Animation","publication_year":2024,"publication_date":"2024-07-26","ids":{"openalex":"https://openalex.org/W4401024028","doi":"https://doi.org/10.24963/ijcai.2024/198"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2024/198","doi":"https://doi.org/10.24963/ijcai.2024/198","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2024/198","pdf_url":"https://www.ijcai.org/proceedings/2024/0198.pdf","source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2024/0198.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111180315","display_name":"Bingwen Zhu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingwen Zhu","raw_affiliation_strings":["Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070831046","display_name":"Fanyi Wang","orcid":"https://orcid.org/0000-0002-8685-4300","observed_orcids":["https://orcid.org/0000-0002-8685-4300"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fanyi Wang","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046419644","display_name":"Tianyi Lu","orcid":"https://orcid.org/0000-0001-8410-9051","observed_orcids":["https://orcid.org/0000-0001-8410-9051","https://orcid.org/0000-0003-3294-6354","https://orcid.org/0000-0003-3086-3539","https://orcid.org/0009-0005-2755-3056"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyi Lu","raw_affiliation_strings":["Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5151996807","display_name":"Peng Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Liu","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152027321","display_name":"Jingwen Su","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingwen Su","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018379453","display_name":"Jinxiu Liu","orcid":"https://orcid.org/0009-0001-3820-8195","observed_orcids":["https://orcid.org/0009-0001-3820-8195","https://orcid.org/0009-0001-2915-7402"]},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinxiu Liu","raw_affiliation_strings":["South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152025220","display_name":"Yanhao Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanhao Zhang","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152012657","display_name":"Zuxuan Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuxuan Wu","raw_affiliation_strings":["Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100766907","display_name":"Guo-Jun Qi","orcid":"https://orcid.org/0000-0003-3508-1851","observed_orcids":["https://orcid.org/0000-0003-3508-1851"]},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo-Jun Qi","raw_affiliation_strings":["Westlake University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Westlake University","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5152034631","display_name":"Yu-Gang Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Gang Jiang","raw_affiliation_strings":["Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6818,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.89398213,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1788","last_page":"1797"},"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":0.9994999766349792,"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":0.9994999766349792,"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":0.00019999999494757503,"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/T14254","display_name":"Digital Media and Visual Art","score":0.00019999999494757503,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/image-to-video-generation","display_name":"image-to-video generation","score":0.9539999961853027},{"id":"https://openalex.org/keywords/character-animation","display_name":"character animation","score":0.9490000009536743},{"id":"https://openalex.org/keywords/pose-control","display_name":"pose control","score":0.8389999866485596},{"id":"https://openalex.org/keywords/temporal-coherence","display_name":"temporal coherence","score":0.7200000286102295},{"id":"https://openalex.org/keywords/text-embeddings","display_name":"text embeddings","score":0.42500001192092896},{"id":"https://openalex.org/keywords/attention-mechanism","display_name":"attention mechanism","score":0.5699999928474426}],"concepts":[{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.7088451385498047},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6777423620223999},{"id":"https://openalex.org/C90697248","wikidata":"https://www.wikidata.org/wiki/Q1062896","display_name":"Character animation","level":4,"score":0.6509968042373657},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.648626983165741},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.6218932867050171},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5969738364219666},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5357173681259155},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4592210650444031},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.4130188226699829},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39256763458251953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39117902517318726},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.38554704189300537},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12309923768043518},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10071757435798645},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.09139272570610046},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06939536333084106},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.06562227010726929},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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":3,"locations":[{"id":"doi:10.24963/ijcai.2024/198","doi":"https://doi.org/10.24963/ijcai.2024/198","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2024/198","pdf_url":"https://www.ijcai.org/proceedings/2024/0198.pdf","source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2404.13680","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.13680","pdf_url":"https://arxiv.org/pdf/2404.13680","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2404.13680","doi":"https://doi.org/10.48550/arxiv.2404.13680","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2404.13680","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2024/198","doi":"https://doi.org/10.24963/ijcai.2024/198","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2024/198","pdf_url":"https://www.ijcai.org/proceedings/2024/0198.pdf","source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G472569701","display_name":null,"funder_award_id":"62032006","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/W4401024028.pdf","grobid_xml":"https://content.openalex.org/works/W4401024028.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W3092442149","https://openalex.org/W4288099666","https://openalex.org/W4297750695","https://openalex.org/W4303440777","https://openalex.org/W4309805222","https://openalex.org/W4309957684","https://openalex.org/W4385848774","https://openalex.org/W4386555052","https://openalex.org/W4388093548","https://openalex.org/W4389115686","https://openalex.org/W4389261665","https://openalex.org/W4390874168","https://openalex.org/W4392909303","https://openalex.org/W4393148505","https://openalex.org/W4401807241","https://openalex.org/W4402582789","https://openalex.org/W4402667906","https://openalex.org/W4402704510","https://openalex.org/W4402727180","https://openalex.org/W4402727496","https://openalex.org/W4402754210","https://openalex.org/W7133213997"],"related_works":["https://openalex.org/W4402754210","https://openalex.org/W7131095348","https://openalex.org/W4402916297","https://openalex.org/W7164020899","https://openalex.org/W4402711993","https://openalex.org/W7201849392","https://openalex.org/W4409366391","https://openalex.org/W6891820632","https://openalex.org/W7126281587","https://openalex.org/W4403791617"],"abstract_inverted_index":{"Image-to-video":[0],"(I2V)":[1],"generation":[2],"aims":[3],"to":[4,86,145],"create":[5],"a":[6,10,39,59,73,97,116,139,173],"video":[7,43],"sequence":[8],"from":[9,25],"single":[11],"image,":[12],"which":[13,47],"requires":[14],"high":[15,174],"temporal":[16,105,177],"coherence":[17,178],"and":[18,30,90,107,111,134,167],"visual":[19],"fidelity.":[20,169],"However,":[21],"existing":[22],"approaches":[23],"suffer":[24],"inconsistency":[26],"of":[27,33,42,94,164,176],"character":[28,65,109,133,165],"appearances":[29],"poor":[31],"preservation":[32],"fine":[34],"details.":[35,114],"Moreover,":[36,170],"they":[37],"require":[38],"large":[40],"amount":[41],"data":[44],"for":[45,64],"training,":[46],"can":[48],"be":[49],"computationally":[50],"demanding.":[51],"To":[52],"address":[53],"these":[54],"limitations,":[55],"we":[56],"propose":[57,138],"PoseAnimate,":[58],"novel":[60],"zero-shot":[61],"I2V":[62],"framework":[63],"animation.":[66],"PoseAnimate":[67],"contains":[68],"three":[69],"key":[70],"components:":[71],"1)":[72],"Pose-Aware":[74],"Control":[75],"Module":[76,101,119],"(PACM)":[77],"that":[78,103,121,154],"incorporates":[79],"diverse":[80],"pose":[81],"signals":[82],"into":[83],"text":[84],"embeddings,":[85],"preserve":[87],"character-independent":[88],"content":[89],"maintain":[91],"precise":[92],"alignment":[93],"actions.":[95],"2)":[96],"Dual":[98],"Consistency":[99],"Attention":[100],"(DCAM)":[102],"enhances":[104],"consistency":[106,166],"retains":[108],"identity":[110],"intricate":[112],"background":[113],"3)":[115],"Mask-Guided":[117],"Decoupling":[118],"(MGDM)":[120],"refines":[122],"distinct":[123],"feature":[124],"perception":[125],"abilities,":[126],"improving":[127],"animation":[128],"fidelity":[129],"by":[130],"decoupling":[131],"the":[132,158,180],"background.":[135],"We":[136],"also":[137],"Pose":[140],"Alignment":[141],"Transition":[142],"Algorithm":[143],"(PATA)":[144],"ensure":[146],"smooth":[147],"action":[148],"transition.":[149],"Extensive":[150],"experiment":[151],"results":[152],"demonstrate":[153],"our":[155],"approach":[156],"outperforms":[157],"state-of-the-art":[159],"training-based":[160],"methods":[161],"in":[162],"terms":[163],"detail":[168],"it":[171],"maintains":[172],"level":[175],"throughout":[179],"generated":[181],"animations.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2024-07-27T00:00:00"}