{"id":"https://openalex.org/W4401953181","doi":"https://doi.org/10.1007/s41095-023-0375-z","title":"CLIP-Flow: Decoding images encoded in CLIP space","display_name":"CLIP-Flow: Decoding images encoded in CLIP space","publication_year":2024,"publication_date":"2024-08-28","ids":{"openalex":"https://openalex.org/W4401953181","doi":"https://doi.org/10.1007/s41095-023-0375-z"},"language":"en","primary_location":{"id":"doi:10.1007/s41095-023-0375-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41095-023-0375-z","pdf_url":null,"source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1007/s41095-023-0375-z","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009211676","display_name":"Hao Ma","orcid":"https://orcid.org/0000-0002-4915-5893"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Ma","raw_affiliation_strings":["Visual Computing Research Center, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, China","Visual Computing Research Center, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, 518060, China"],"affiliations":[{"raw_affiliation_string":"Visual Computing Research Center, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, China","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"Visual Computing Research Center, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, 518060, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351382","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-1218-2804"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["Visual Computing Research Center, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, China","Visual Computing Research Center, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, 518060, China"],"affiliations":[{"raw_affiliation_string":"Visual Computing Research Center, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, China","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"Visual Computing Research Center, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, 518060, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100966997","display_name":"Jingyuan Yang","orcid":"https://orcid.org/0009-0004-5385-5253"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyuan Yang","raw_affiliation_strings":["Visual Computing Research Center, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, China","Visual Computing Research Center, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, 518060, China"],"affiliations":[{"raw_affiliation_string":"Visual Computing Research Center, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, China","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"Visual Computing Research Center, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, 518060, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076541595","display_name":"Or Patashnik","orcid":"https://orcid.org/0000-0001-7757-6137"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Or Patashnik","raw_affiliation_strings":["Department of Computer Science, Tel Aviv University, Tel Aviv 6997801, Israel","Department of Computer Science, Tel Aviv University, Tel Aviv, 6997801, Israel"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tel Aviv University, Tel Aviv 6997801, Israel","institution_ids":["https://openalex.org/I16391192"]},{"raw_affiliation_string":"Department of Computer Science, Tel Aviv University, Tel Aviv, 6997801, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091260693","display_name":"Dani Lischinski","orcid":"https://orcid.org/0000-0002-6191-0361"},"institutions":[{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Dani Lischinski","raw_affiliation_strings":["School of Computer Science and Engineering, the Hebrew University of Jerusalem, Jerusalem 91904, Israel","School of Computer Science and Engineering, the Hebrew University of Jerusalem, Jerusalem, 91904, Israel"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, the Hebrew University of Jerusalem, Jerusalem 91904, Israel","institution_ids":["https://openalex.org/I197251160"]},{"raw_affiliation_string":"School of Computer Science and Engineering, the Hebrew University of Jerusalem, Jerusalem, 91904, Israel","institution_ids":["https://openalex.org/I197251160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036688260","display_name":"Daniel Cohen\u2010Or","orcid":"https://orcid.org/0000-0001-6777-7445"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daniel Cohen-Or","raw_affiliation_strings":["Visual Computing Research Center, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, China; Department of Computer Science, Tel Aviv University, Tel Aviv 6997801, Israel","Visual Computing Research Center, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, 518060, China"],"affiliations":[{"raw_affiliation_string":"Visual Computing Research Center, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, China; Department of Computer Science, Tel Aviv University, Tel Aviv 6997801, Israel","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"Visual Computing Research Center, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, 518060, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034304352","display_name":"Hui Huang","orcid":"https://orcid.org/0000-0003-3212-0544"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Huang","raw_affiliation_strings":["Visual Computing Research Center, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, China","Visual Computing Research Center, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, 518060, China"],"affiliations":[{"raw_affiliation_string":"Visual Computing Research Center, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, China","institution_ids":["https://openalex.org/I180726961"]},{"raw_affiliation_string":"Visual Computing Research Center, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, 518060, China","institution_ids":["https://openalex.org/I180726961"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5009211676"],"corresponding_institution_ids":["https://openalex.org/I180726961"],"apc_list":null,"apc_paid":null,"fwci":0.7895,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72798386,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"10","issue":"6","first_page":"1157","last_page":"1168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.991100013256073,"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/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.991100013256073,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9894999861717224,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9836000204086304,"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/decoding-methods","display_name":"Decoding methods","score":0.6828480958938599},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6642770767211914},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.5229538083076477},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.5223634839057922},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics","score":0.49551141262054443},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4947316348552704},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3285544514656067},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13125592470169067},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11030912399291992},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.05938595533370972},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.05925178527832031}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6828480958938599},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6642770767211914},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.5229538083076477},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5223634839057922},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.49551141262054443},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4947316348552704},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3285544514656067},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13125592470169067},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11030912399291992},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.05938595533370972},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.05925178527832031}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s41095-023-0375-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41095-023-0375-z","pdf_url":null,"source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s41095-023-0375-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41095-023-0375-z","pdf_url":null,"source":{"id":"https://openalex.org/S2487656537","display_name":"Computational Visual Media","issn_l":"2096-0433","issn":["2096-0433","2096-0662"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Visual Media","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2526468814","https://openalex.org/W3135367836","https://openalex.org/W4286611278","https://openalex.org/W4301409532","https://openalex.org/W4312282373","https://openalex.org/W4312872987","https://openalex.org/W4313145975","https://openalex.org/W6600254619","https://openalex.org/W6631455383"],"related_works":["https://openalex.org/W2319989118","https://openalex.org/W1503820821","https://openalex.org/W2285491073","https://openalex.org/W1991998366","https://openalex.org/W3112751614","https://openalex.org/W1995979513","https://openalex.org/W4249185555","https://openalex.org/W1999937205","https://openalex.org/W2517707608","https://openalex.org/W2144683202"],"abstract_inverted_index":{"This":[0],"study":[1],"introduces":[2],"CLIP-Flow,":[3],"a":[4,11,28,53],"novel":[5],"network":[6],"for":[7,31,137],"generating":[8],"images":[9,57,88],"from":[10,58],"given":[12],"image":[13],"or":[14],"text.":[15],"To":[16],"effectively":[17],"utilize":[18],"the":[19,64,87,94,119,122,132],"rich":[20],"semantics":[21,49],"contained":[22],"in":[23,91],"both":[24,156],"modalities,":[25],"we":[26,38,129],"designed":[27],"semantics-guided":[29],"methodology":[30],"image-":[32],"and":[33,50,69,78,83,89,150,158],"text-to-image":[34,108,138],"synthesis.":[35,109,139],"In":[36,127],"particular,":[37],"adopted":[39],"Contrastive":[40],"Language-Image":[41],"Pretraining":[42],"(CLIP)":[43],"as":[44,52],"an":[45],"encoder":[46],"to":[47,55,62,106,117],"extract":[48],"StyleGAN":[51],"decoder":[54],"generate":[56,146],"such":[59],"information.":[60],"Moreover,":[61],"bridge":[63],"embedding":[65],"space":[66,71],"of":[67,72,121],"CLIP":[68,92],"latent":[70],"StyleGAN,":[73],"real":[74],"NVP":[75],"is":[76,151],"employed":[77],"modified":[79],"with":[80,153],"activation":[81],"normalization":[82],"invertible":[84],"convolution.":[85],"As":[86],"text":[90,98],"share":[93],"same":[95],"representation":[96],"space,":[97],"prompts":[99],"can":[100,145],"be":[101],"fed":[102],"directly":[103],"into":[104],"CLIP-Flow":[105],"achieve":[107],"We":[110],"conducted":[111],"extensive":[112],"experiments":[113],"on":[114,131],"several":[115],"datasets":[116],"validate":[118],"effectiveness":[120],"proposed":[123],"image-to-image":[124],"synthesis":[125],"method.":[126],"addition,":[128],"tested":[130],"public":[133],"dataset":[134],"Multi-Modal":[135],"CelebA-HQ,":[136],"Experiments":[140],"validated":[141],"that":[142],"our":[143],"approach":[144],"high-quality":[147],"text-matching":[148],"images,":[149],"comparable":[152],"state-of-the-art":[154],"methods,":[155],"qualitatively":[157],"quantitatively.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-11-25T21:42:39.735039","created_date":"2025-10-10T00:00:00"}