{"id":"https://openalex.org/W4408354214","doi":"https://doi.org/10.1109/icassp49660.2025.10889218","title":"Anima <sup>2</sup> : Cross-Species Animal Animation through Image-to-Video Synthesis with Subject Alignment","display_name":"Anima <sup>2</sup> : Cross-Species Animal Animation through Image-to-Video Synthesis with Subject Alignment","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354214","doi":"https://doi.org/10.1109/icassp49660.2025.10889218"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889218","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5062282643","display_name":"Yuanfeng Xu","orcid":"https://orcid.org/0000-0002-1390-2308"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanfeng Xu","raw_affiliation_strings":["Sun Yat-Sen University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100321260","display_name":"Yuhao Chen","orcid":"https://orcid.org/0000-0001-6094-0545"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Chen","raw_affiliation_strings":["Sun Yat-Sen University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009783636","display_name":"Zhongzhan Huang","orcid":"https://orcid.org/0000-0001-8422-2898"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongzhan Huang","raw_affiliation_strings":["Sun Yat-Sen University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108752809","display_name":"Zijian He","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijian He","raw_affiliation_strings":["Sun Yat-Sen University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052611320","display_name":"Guangrun Wang","orcid":"https://orcid.org/0000-0001-7760-1339"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangrun Wang","raw_affiliation_strings":["Sun Yat-Sen University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100412937","display_name":"Liang Lin","orcid":"https://orcid.org/0000-0003-2248-3755"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Lin","raw_affiliation_strings":["Sun Yat-Sen University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University,China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0408807,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9678000211715698,"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"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9678000211715698,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9330000281333923,"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/subject","display_name":"Subject (documents)","score":0.6901026368141174},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.6576558351516724},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6570505499839783},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5507218241691589},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.5249319672584534},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.518726646900177},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47968506813049316},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1462326943874359}],"concepts":[{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.6901026368141174},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.6576558351516724},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6570505499839783},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5507218241691589},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5249319672584534},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.518726646900177},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47968506813049316},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1462326943874359}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889218","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889218","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2470139095","https://openalex.org/W2887114371","https://openalex.org/W2997403210","https://openalex.org/W3025800305","https://openalex.org/W3119653668","https://openalex.org/W3178284600","https://openalex.org/W4214588164","https://openalex.org/W4214753187","https://openalex.org/W4224285690","https://openalex.org/W4312473638","https://openalex.org/W4312651322","https://openalex.org/W4312933868","https://openalex.org/W4386071686","https://openalex.org/W4387968301","https://openalex.org/W4390871782","https://openalex.org/W4390872556","https://openalex.org/W4390872677","https://openalex.org/W4390873135","https://openalex.org/W4390874168","https://openalex.org/W4390874575","https://openalex.org/W4390874580","https://openalex.org/W4390889741","https://openalex.org/W4401905945","https://openalex.org/W4402704510","https://openalex.org/W4402753907","https://openalex.org/W4402774219","https://openalex.org/W4404199654","https://openalex.org/W4404582848","https://openalex.org/W4407196708","https://openalex.org/W6767264202","https://openalex.org/W6791353385","https://openalex.org/W6845281891","https://openalex.org/W6851800889","https://openalex.org/W6854944684","https://openalex.org/W6858096236","https://openalex.org/W6858340613","https://openalex.org/W6860221313","https://openalex.org/W6861168410"],"related_works":["https://openalex.org/W2121378366","https://openalex.org/W3112102641","https://openalex.org/W2013184069","https://openalex.org/W2989004599","https://openalex.org/W1976926596","https://openalex.org/W126583968","https://openalex.org/W2535923857","https://openalex.org/W2532377291","https://openalex.org/W2359575859","https://openalex.org/W2215755978"],"abstract_inverted_index":{"Recent":[0],"video":[1,59,144],"editing":[2],"advancements":[3],"rely":[4],"on":[5,154],"accurate":[6,135,164],"pose":[7,24],"sequences":[8],"to":[9,23,43,61,66,149],"animate":[10],"human":[11],"actors.":[12],"However,":[13],"these":[14,155],"efforts":[15],"are":[16],"not":[17],"suitable":[18],"for":[19,134,174],"cross-species":[20,136,151,184],"animation":[21],"due":[22,42],"misalignment":[25],"between":[26],"species":[27,148],"(for":[28],"example,":[29],"the":[30,72,172],"poses":[31],"of":[32,39],"a":[33,40,56,89,94,121],"cat":[34],"differ":[35],"greatly":[36],"from":[37,116],"that":[38],"pig":[41],"their":[44],"distinct":[45],"body":[46],"structures).":[47],"In":[48],"this":[49,63],"paper,":[50],"we":[51,82,109,139],"present":[52],"Anima<sup":[53],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[54],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>,":[55],"zero-shot":[57],"diffusion-based":[58],"generator":[60],"address":[62,114],"issue,":[64],"aiming":[65],"accurately":[67],"ANIMAte":[68],"ANIMAls":[69],"while":[70],"preserving":[71],"background.":[73],"The":[74],"key":[75],"technique":[76],"involves":[77],"two-fold":[78],"subject":[79,132],"alignment.":[80],"First,":[81],"improve":[83],"appearance":[84,101],"feature":[85],"extraction":[86],"by":[87,119],"integrating":[88],"Laplacian":[90],"detail":[91],"booster":[92],"and":[93,105,113,124,168,189],"prompt-tuning":[95],"identity":[96,104],"extractor.":[97],"They":[98,129],"capture":[99],"essential":[100],"information,":[102],"including":[103],"fine":[106],"details.":[107],"Second,":[108],"align":[110],"shape":[111],"features":[112],"conflicts":[115],"differing":[117],"animals":[118],"introducing":[120],"scale-information":[122],"remover":[123],"an":[125],"adaptive":[126],"rescaling":[127],"module.":[128],"both":[130],"enhance":[131],"alignment":[133],"animation.":[137,152],"Additionally,":[138],"introduce":[140],"two":[141],"high-quality":[142],"animal":[143],"datasets":[145],"with":[146,163],"diverse":[147],"benchmark":[150],"Trained":[153],"extensive":[156],"datasets,":[157],"our":[158,180],"model":[159],"directly":[160],"generates":[161],"videos":[162],"movements,":[165],"consistent":[166],"appearances,":[167],"high-fidelity":[169],"frames,":[170],"eliminating":[171],"need":[173],"test-time":[175],"training.":[176],"Extensive":[177],"experiments":[178],"demonstrate":[179],"method\u2019s":[181],"superiority":[182],"in":[183],"animation,":[185],"showcasing":[186],"robust":[187],"adaptability":[188],"generality.":[190]},"counts_by_year":[],"updated_date":"2026-03-26T06:05:38.182114","created_date":"2025-10-10T00:00:00"}