{"id":"https://openalex.org/W7160263840","doi":"https://doi.org/10.1109/wacv61042.2026.00202","title":"Learnable Query-Enhanced Pose Transformation","display_name":"Learnable Query-Enhanced Pose Transformation","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160263840","doi":"https://doi.org/10.1109/wacv61042.2026.00202"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00202","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/A5135301960","display_name":"Yi-Zhen Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Zhen Wang","raw_affiliation_strings":["National Yang Ming Chiao Tung University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040050806","display_name":"Hong-Han Shuai","orcid":"https://orcid.org/0000-0003-2216-077X"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hong-Han Shuai","raw_affiliation_strings":["National Yang Ming Chiao Tung University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40724466,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2032","last_page":"2041"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.15600000321865082,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.15600000321865082,"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/T12290","display_name":"Human Motion and Animation","score":0.13590000569820404,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.07689999788999557,"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/encoder","display_name":"Encoder","score":0.515999972820282},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.446399986743927},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.43369999527931213},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3955000042915344},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.3919000029563904},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3691999912261963},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.3407999873161316},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3366999924182892}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7483000159263611},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7473999857902527},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5927000045776367},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.515999972820282},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.446399986743927},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.43369999527931213},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3955000042915344},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3919000029563904},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.3345000147819519},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.32010000944137573},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2964000105857849},{"id":"https://openalex.org/C165443888","wikidata":"https://www.wikidata.org/wiki/Q1482183","display_name":"Transformation matrix","level":3,"score":0.26899999380111694},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.2621000111103058},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.2619999945163727},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.25450000166893005},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00202","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":[{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2108598243","https://openalex.org/W2471768434","https://openalex.org/W2559085405","https://openalex.org/W2771558241","https://openalex.org/W2962963674","https://openalex.org/W2963266880","https://openalex.org/W2963734522","https://openalex.org/W2964002510","https://openalex.org/W2982413914","https://openalex.org/W2991530302","https://openalex.org/W2998175569","https://openalex.org/W3034950620","https://openalex.org/W3035515747","https://openalex.org/W3096338808","https://openalex.org/W3138516171","https://openalex.org/W3166096919","https://openalex.org/W3176412779","https://openalex.org/W3180355996","https://openalex.org/W4312881655","https://openalex.org/W4312896571","https://openalex.org/W4312933868","https://openalex.org/W4313030876","https://openalex.org/W4385800625","https://openalex.org/W4386076520","https://openalex.org/W4390873054","https://openalex.org/W4390873194","https://openalex.org/W4390873280","https://openalex.org/W4393148714","https://openalex.org/W4402727583","https://openalex.org/W4413156547"],"related_works":[],"abstract_inverted_index":{"Pose-Guided":[0],"Person":[1],"Image":[2],"Synthesis":[3],"(PGPIS)":[4],"aims":[5],"to":[6,14,97,103,149,154],"transfer":[7],"a":[8,11,15,72,147],"person":[9],"from":[10,38,63,101,134],"source":[12,65,136],"image":[13],"target":[16],"pose":[17,129,144,158],"(e.g.,":[18],"skeleton)":[19],"while":[20],"preserving":[21],"their":[22],"original":[23],"appearance.":[24],"Although":[25],"existing":[26,169],"methods":[27],"can":[28],"produce":[29],"high-quality":[30],"results":[31,166],"at":[32],"first":[33],"glance,":[34],"they":[35],"often":[36],"suffer":[37],"noticeable":[39],"distortions":[40],"in":[41,119],"fine":[42],"details.":[43],"We":[44],"identify":[45],"the":[46,53,64,82,108,114,120,126,135,143,151,157,184],"root":[47],"cause":[48],"of":[49,78,116],"these":[50],"issues":[51],"as":[52,146],"heavy":[54],"reliance":[55],"on":[56,156,171,183],"pre-trained":[57],"encoders":[58],"for":[59],"extracting":[60],"visual":[61,132],"features":[62,100,133],"image.":[66],"To":[67,123],"address":[68],"this,":[69],"we":[70,138],"propose":[71],"novel":[73],"Query":[74],"Enhancement":[75],"Network":[76],"composed":[77],"two":[79],"key":[80],"components:":[81],"Query-based":[83],"Feature":[84],"Fusion":[85],"Transformer":[86],"(QFFT)":[87],"and":[88,131,167,178],"Pose-Masked":[89],"Attention":[90],"(PMA).":[91],"The":[92],"QFFT":[93],"uses":[94,142],"learnable":[95],"queries":[96],"fuses":[98],"multi-scale":[99],"high":[102],"low":[104],"resolution":[105],"extracted":[106],"by":[107],"backbone":[109],"encoder,":[110],"thereby":[111],"significantly":[112],"enhancing":[113],"realism":[115],"texture":[117],"details":[118],"generated":[121],"images.":[122],"better":[124],"capture":[125],"relationship":[127],"between":[128],"information":[130],"image,":[137],"introduce":[139],"PMA":[140],"that":[141],"skeleton":[145],"mask":[148],"guide":[150],"attention":[152],"mechanism":[153],"focus":[155],"regions.":[159],"Our":[160],"method":[161],"produces":[162],"high-quality,":[163],"visually":[164],"coherent":[165],"outperforms":[168],"approaches":[170],"standard":[172],"evaluation":[173],"metrics,":[174],"including":[175],"FID,":[176],"SSIM,":[177],"LPIPS,":[179],"demonstrating":[180],"its":[181],"effectiveness":[182],"DeepFashion":[185],"dataset.":[186]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-06T00:00:00"}