{"id":"https://openalex.org/W4385488490","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191516","title":"LisaCLIP: Locally Incremental Semantics Adaptation towards Zero-shot Text-driven Image Synthesis","display_name":"LisaCLIP: Locally Incremental Semantics Adaptation towards Zero-shot Text-driven Image Synthesis","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385488490","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191516"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10191516","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10191516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","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/A5103016592","display_name":"An Cao","orcid":"https://orcid.org/0009-0003-5398-9246"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"An Cao","raw_affiliation_strings":["School of Software Engineering Huazhong University of Science and Technology,Wuhan,China","School of Software Engineering Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering Huazhong University of Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"School of Software Engineering Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100645661","display_name":"Yilin Zhou","orcid":"https://orcid.org/0009-0000-4748-8865"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yilin Zhou","raw_affiliation_strings":["School of Software Engineering Huazhong University of Science and Technology,Wuhan,China","School of Software Engineering Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering Huazhong University of Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"School of Software Engineering Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101743038","display_name":"Gang Shen","orcid":"https://orcid.org/0000-0001-5961-8110"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Shen","raw_affiliation_strings":["School of Software Engineering Huazhong University of Science and Technology,Wuhan,China","School of Software Engineering Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering Huazhong University of Science and Technology,Wuhan,China","institution_ids":["https://openalex.org/I47720641"]},{"raw_affiliation_string":"School of Software Engineering Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103016592"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08205305,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"139","issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9994999766349792,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9994999766349792,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9846000075340271,"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/computer-science","display_name":"Computer science","score":0.8377238512039185},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5217945575714111},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5052600502967834},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4927254021167755},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.46221062541007996},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4486251473426819},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4385715126991272},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3588014245033264},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3438512682914734},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09631162881851196}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8377238512039185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5217945575714111},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5052600502967834},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4927254021167755},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.46221062541007996},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4486251473426819},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4385715126991272},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3588014245033264},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3438512682914734},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09631162881851196},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn54540.2023.10191516","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn54540.2023.10191516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1834627138","https://openalex.org/W2475287302","https://openalex.org/W2603777577","https://openalex.org/W2741137940","https://openalex.org/W2885380450","https://openalex.org/W2962750014","https://openalex.org/W2962770929","https://openalex.org/W2969803502","https://openalex.org/W3034431451","https://openalex.org/W3094502228","https://openalex.org/W3129576130","https://openalex.org/W3162926177","https://openalex.org/W3166396011","https://openalex.org/W3201927751","https://openalex.org/W3216156094","https://openalex.org/W4211083527","https://openalex.org/W4214926101","https://openalex.org/W4225307095","https://openalex.org/W4286611278","https://openalex.org/W4288055722","https://openalex.org/W4301206121","https://openalex.org/W4310827791","https://openalex.org/W4312534259","https://openalex.org/W4312740349","https://openalex.org/W4312741694","https://openalex.org/W4312938727","https://openalex.org/W6765779288","https://openalex.org/W6784333009","https://openalex.org/W6790978476","https://openalex.org/W6791353385","https://openalex.org/W6795288823","https://openalex.org/W6805300346","https://openalex.org/W6840608908"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"The":[0],"automatic":[1],"transfer":[2,43,142],"of":[3,20,140],"a":[4,8,66,84,114,137],"plain":[5],"photo":[6,21],"into":[7],"desired":[9],"synthetic":[10],"style":[11,42,141],"has":[12],"attracted":[13],"numerous":[14],"users":[15],"in":[16,149],"the":[17,32,40,46,51,75,80,100,105,125,151],"application":[18],"fields":[19],"editing,":[22],"visual":[23],"art,":[24],"and":[25,30,56,144,155],"entertainment.":[26],"By":[27],"connecting":[28],"images":[29],"texts,":[31],"Contrastive":[33],"Language-":[34],"Image":[35],"Pre-Training":[36],"(CLIP)":[37],"model":[38,77],"facilitates":[39],"text-driven":[41],"without":[44],"exploring":[45],"image's":[47],"latent":[48],"domain.":[49],"However,":[50],"trade-off":[52],"between":[53,153],"content":[54,154],"fidelity":[55],"stylization":[57],"remains":[58],"challenging.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63],"present":[64],"LisaCLIP,":[65],"CLIP-":[67],"based":[68],"image":[69,90],"synthesis":[70],"framework":[71],"that":[72,134],"only":[73],"exploits":[74],"CLIP":[76],"to":[78,118],"guide":[79],"imagery":[81],"manipulations":[82],"with":[83],"depth-adaptive":[85],"encoder-decoder":[86],"network.":[87],"Since":[88],"an":[89],"patch's":[91],"semantics":[92],"depend":[93],"on":[94,130],"its":[95],"size,":[96],"LisaCLIP":[97,135],"progressively":[98],"downsizes":[99],"patches":[101],"while":[102],"adaptively":[103],"selecting":[104],"most":[106],"significant":[107],"ones":[108],"for":[109],"further":[110],"stylization.":[111],"We":[112],"introduce":[113],"multi-stage":[115],"training":[116],"strategy":[117],"speed":[119],"up":[120],"LisaCLIP's":[121],"convergence":[122],"by":[123],"decoupling":[124],"optimization":[126],"objectives.":[127],"Various":[128],"experiments":[129],"public":[131],"datasets":[132],"demonstrated":[133],"supported":[136],"wide":[138],"range":[139],"tasks":[143],"outperformed":[145],"other":[146],"state-of-the-art":[147],"methods":[148],"maintaining":[150],"balance":[152],"style.":[156]},"counts_by_year":[],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}