{"id":"https://openalex.org/W7160255570","doi":"https://doi.org/10.1109/wacv61042.2026.00061","title":"Learning to Animate Images from A Few Videos to Portray Delicate Human Actions","display_name":"Learning to Animate Images from A Few Videos to Portray Delicate Human Actions","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160255570","doi":"https://doi.org/10.1109/wacv61042.2026.00061"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5101724920","display_name":"Haoxin Li","orcid":"https://orcid.org/0000-0001-7671-5609"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haoxin Li","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135371377","display_name":"Yingchen Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingchen Yu","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135284714","display_name":"Qilong Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qilong Wu","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077061182","display_name":"H L Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hanwang Zhang","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135387451","display_name":"Song Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song Bai","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135393797","display_name":"Boyang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Boyang Li","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]}],"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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"547","last_page":"559"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.32359999418258667,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.32359999418258667,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.13079999387264252,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.10159999877214432,"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/action","display_name":"Action (physics)","score":0.33809998631477356},{"id":"https://openalex.org/keywords/photography","display_name":"Photography","score":0.31290000677108765},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.30219998955726624},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.2712000012397766}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.474700003862381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3831000030040741},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C119657128","wikidata":"https://www.wikidata.org/wiki/Q11633","display_name":"Photography","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3037000000476837},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.2827000021934509},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.26499998569488525},{"id":"https://openalex.org/C2776196576","wikidata":"https://www.wikidata.org/wiki/Q196113","display_name":"Camouflage","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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":65,"referenced_works":["https://openalex.org/W147001025","https://openalex.org/W2029167031","https://openalex.org/W2603777577","https://openalex.org/W2625366777","https://openalex.org/W2799055999","https://openalex.org/W2963524571","https://openalex.org/W3086541756","https://openalex.org/W3095374178","https://openalex.org/W3096831136","https://openalex.org/W3109908659","https://openalex.org/W3173271747","https://openalex.org/W3178284600","https://openalex.org/W3204588463","https://openalex.org/W4214951466","https://openalex.org/W4226289673","https://openalex.org/W4312933868","https://openalex.org/W4385535562","https://openalex.org/W4386071957","https://openalex.org/W4386072096","https://openalex.org/W4386076323","https://openalex.org/W4386076425","https://openalex.org/W4389539288","https://openalex.org/W4390871782","https://openalex.org/W4390872556","https://openalex.org/W4390873054","https://openalex.org/W4390873135","https://openalex.org/W4390874580","https://openalex.org/W4400573519","https://openalex.org/W4400580599","https://openalex.org/W4400582084","https://openalex.org/W4402716309","https://openalex.org/W4402727040","https://openalex.org/W4402727092","https://openalex.org/W4402727699","https://openalex.org/W4402727736","https://openalex.org/W4402727798","https://openalex.org/W4402753569","https://openalex.org/W4402753775","https://openalex.org/W4402753903","https://openalex.org/W4402754023","https://openalex.org/W4402754262","https://openalex.org/W4402775841","https://openalex.org/W4402917185","https://openalex.org/W4403003238","https://openalex.org/W4403021266","https://openalex.org/W4403792036","https://openalex.org/W4403878131","https://openalex.org/W4403906510","https://openalex.org/W4404693162","https://openalex.org/W4404725289","https://openalex.org/W4404971889","https://openalex.org/W4408351875","https://openalex.org/W4409367025","https://openalex.org/W4409367401","https://openalex.org/W4412588088","https://openalex.org/W4413144599","https://openalex.org/W4413146118","https://openalex.org/W4413147690","https://openalex.org/W4413157524","https://openalex.org/W4413158011","https://openalex.org/W7133198828","https://openalex.org/W7133212340","https://openalex.org/W7133218093","https://openalex.org/W7133229070","https://openalex.org/W7133239857"],"related_works":[],"abstract_inverted_index":{"Despite":[0],"recent":[1],"progress,":[2],"video":[3,112,123],"generative":[4],"models":[5],"still":[6],"struggle":[7],"to":[8,20,36,95,109,141,156,163,200],"generate":[9],"delicate":[10,43],"human":[11,44],"actions":[12,45],"(e.g.,":[13],"gymnastics),":[14],"particularly":[15],"when":[16],"they":[17],"are":[18,198],"required":[19],"start":[21],"from":[22,78,121,159,202],"a":[23,47,84,111],"user-provided":[24,79],"reference":[25,80,161],"image.":[26],"In":[27],"this":[28],"paper,":[29],"we":[30],"explore":[31],"the":[32,59,107,114,125,133,142,151,160,187,190],"task":[33],"of":[34,50,103,135,176],"learning":[35,134],"animate":[37],"images":[38,81],"into":[39],"videos":[40,51,188],"that":[41,75],"portray":[42],"using":[46,113],"small":[48],"number":[49],"\u2014":[52,56],"16":[53],"or":[54],"fewer":[55],"which":[57,100],"reduces":[58],"need":[60],"for":[61,68],"extensive":[62],"data":[63],"collection":[64],"and":[65,97,117,138],"enhances":[66,101],"practicality":[67],"real-world":[69],"applications.":[70],"Learning":[71,94],"generalizable":[72],"motion":[73,104,115,127,137,196],"patterns":[74],"smoothly":[76],"transition":[77,167],"in":[82,144],"such":[83],"few-shot":[85],"setting":[86],"is":[87],"highly":[88],"challenging.":[89],"We":[90,183],"propose":[91],"FLASH":[92,149,180],"(Few-shot":[93],"Animate":[96],"Steer":[98],"Humans),":[99],"generalization":[102],"by":[105],"training":[106,146],"model":[108],"reconstruct":[110],"features":[116],"cross-frame":[118],"correspondences":[119],"extracted":[120],"another":[122],"with":[124,153,174],"same":[126],"but":[128],"different":[129],"appearance.":[130],"This":[131],"encourages":[132],"transferable":[136],"mitigates":[139],"overfitting":[140],"appearance":[143],"limited":[145],"data.":[147],"Additionally,":[148],"extends":[150],"decoder":[152],"additional":[154],"layers":[155],"propagate":[157],"details":[158],"image":[162],"generated":[164],"frames,":[165],"improving":[166],"smoothness.":[168],"Human":[169],"judges":[170],"significantly":[171],"favor":[172],"FLASH,":[173],"65.78%":[175],"488":[177],"responses":[178],"prefer":[179],"over":[181],"baselines.":[182],"strongly":[184],"recommend":[185],"watching":[186],"on":[189],"webpage":[191],"<sup":[192],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[193],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>,":[194],"as":[195],"artifacts":[197],"hard":[199],"notice":[201],"images.":[203]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-06T00:00:00"}