{"id":"https://openalex.org/W4385536252","doi":"https://doi.org/10.1145/3588432.3591532","title":"CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for a Disentangled, Interpretable and Controllable Text-Guided Face Manipulation","display_name":"CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for a Disentangled, Interpretable and Controllable Text-Guided Face Manipulation","publication_year":2023,"publication_date":"2023-07-19","ids":{"openalex":"https://openalex.org/W4385536252","doi":"https://doi.org/10.1145/3588432.3591532"},"language":"en","primary_location":{"id":"doi:10.1145/3588432.3591532","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3588432.3591532","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3588432.3591532","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Proceedings","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3588432.3591532","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089079824","display_name":"Chenliang Zhou","orcid":"https://orcid.org/0009-0001-1096-1927"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Chenliang Zhou","raw_affiliation_strings":["University of Cambridge, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084520143","display_name":"Fangcheng Zhong","orcid":"https://orcid.org/0000-0001-5964-5282"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Fangcheng Zhong","raw_affiliation_strings":["University of Cambridge, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020941443","display_name":"A. Cengiz \u00d6ztireli","orcid":"https://orcid.org/0000-0002-4700-2236"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cengiz \u00d6ztireli","raw_affiliation_strings":["University of Cambridge, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5089079824"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":1.4692,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.84398599,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9994000196456909,"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/T11448","display_name":"Face recognition and analysis","score":0.9994000196456909,"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/T12301","display_name":"Facial Nerve Paralysis Treatment and Research","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2728","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9929999709129333,"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/embedding","display_name":"Embedding","score":0.8458436131477356},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7874091863632202},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7822275757789612},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.7054857015609741},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6485078930854797},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.6414092183113098},{"id":"https://openalex.org/keywords/linear-subspace","display_name":"Linear subspace","score":0.6370751261711121},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5880812406539917},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.5327489376068115},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4633263945579529},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38134533166885376},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3666519820690155},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16091805696487427},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11844214797019958}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8458436131477356},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7874091863632202},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7822275757789612},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.7054857015609741},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6485078930854797},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.6414092183113098},{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.6370751261711121},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5880812406539917},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.5327489376068115},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4633263945579529},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38134533166885376},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3666519820690155},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16091805696487427},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11844214797019958},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3588432.3591532","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3588432.3591532","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3588432.3591532","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Proceedings","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3588432.3591532","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3588432.3591532","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3588432.3591532","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Proceedings","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385536252.pdf","grobid_xml":"https://content.openalex.org/works/W4385536252.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W20405322","https://openalex.org/W1587559447","https://openalex.org/W2519536754","https://openalex.org/W2910705748","https://openalex.org/W2962770929","https://openalex.org/W2963105487","https://openalex.org/W2969985801","https://openalex.org/W3034625979","https://openalex.org/W3035574324","https://openalex.org/W3040462728","https://openalex.org/W3094954720","https://openalex.org/W3135367836","https://openalex.org/W3173241699","https://openalex.org/W3173853618","https://openalex.org/W3174194560","https://openalex.org/W3177399056","https://openalex.org/W3193457413","https://openalex.org/W3205181580","https://openalex.org/W3209830847","https://openalex.org/W4206097581","https://openalex.org/W4206210655","https://openalex.org/W4212821657","https://openalex.org/W4214926101","https://openalex.org/W4286611278","https://openalex.org/W4287111106","https://openalex.org/W4294959213","https://openalex.org/W6780043386"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W4361193272","https://openalex.org/W4310278675","https://openalex.org/W2806259446","https://openalex.org/W2036697162","https://openalex.org/W2108916035","https://openalex.org/W1995844989","https://openalex.org/W2794358477","https://openalex.org/W2037681520","https://openalex.org/W4379089547"],"abstract_inverted_index":{"Recently":[0],"introduced":[1],"Contrastive":[2],"Language-Image":[3],"Pre-Training":[4],"(CLIP)":[5],"[Radford":[6],"et":[7],"al.":[8],"2021]":[9],"bridges":[10],"images":[11],"and":[12,48,72,123,131,133,153,171,181,189],"text":[13,49,56],"by":[14,36,92],"embedding":[15,104],"them":[16],"into":[17,136],"a":[18,38,121,157,177],"joint":[19,53],"latent":[20],"space.":[21],"This":[22],"opens":[23],"the":[24,44,52,59,67,112,144,162],"door":[25],"to":[26,31,43,77,87,95,110],"ample":[27],"literature":[28],"that":[29,126,174],"aims":[30],"manipulate":[32],"an":[33,107],"input":[34],"image":[35,47,98,116,139,184],"providing":[37],"textual":[39],"explanation.":[40],"However,":[41],"due":[42],"discrepancy":[45],"between":[46],"embeddings":[50,57],"in":[51,66],"space,":[54],"using":[55],"as":[58,106],"optimization":[60,108],"target":[61,109],"often":[62],"introduces":[63],"undesired":[64],"artifacts":[65],"resulting":[68],"images.":[69],"Disentanglement,":[70],"interpretability,":[71],"controllability":[73],"are":[74],"also":[75],"hard":[76],"guarantee":[78],"for":[79,164],"manipulation.":[80,117],"To":[81,142],"alleviate":[82],"these":[83],"problems,":[84],"we":[85,149,160],"propose":[86],"define":[88],"corpus":[89],"subspaces":[90],"spanned":[91],"relevant":[93],"prompts":[94],"capture":[96],"specific":[97],"characteristics.":[99],"We":[100,169],"introduce":[101],"CLIP":[102],"projection-augmentation":[103],"(PAE)":[105],"improve":[111],"performance":[113],"of":[114,146],"text-guided":[115,165],"Our":[118],"method":[119,163],"is":[120],"simple":[122],"general":[124],"paradigm":[125],"can":[127],"be":[128],"easily":[129],"computed":[130],"adapted,":[132],"smoothly":[134],"incorporated":[135],"any":[137],"CLIP-based":[138],"manipulation":[140,185],"algorithm.":[141],"demonstrate":[143,173],"effectiveness":[145],"our":[147],"method,":[148],"conduct":[150],"several":[151],"theoretical":[152],"empirical":[154],"studies.":[155],"As":[156],"case":[158],"study,":[159],"utilize":[161],"semantic":[166],"face":[167,183],"editing.":[168],"quantitatively":[170],"qualitatively":[172],"PAE":[175],"facilitates":[176],"more":[178],"disentangled,":[179],"interpretable,":[180],"controllable":[182],"with":[186],"state-of-the-art":[187],"quality":[188],"accuracy.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}