{"id":"https://openalex.org/W4401507675","doi":"https://doi.org/10.1109/access.2024.3442296","title":"Diff-KT: Text-Driven Image Editing by Knowledge Enhancement and Mask Transformer","display_name":"Diff-KT: Text-Driven Image Editing by Knowledge Enhancement and Mask Transformer","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401507675","doi":"https://doi.org/10.1109/access.2024.3442296"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3442296","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3442296","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2024.3442296","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103242236","display_name":"Hong Zhao","orcid":"https://orcid.org/0000-0002-5515-6139"},"institutions":[{"id":"https://openalex.org/I22716506","display_name":"Lanzhou University of Technology","ror":"https://ror.org/03panb555","country_code":"CN","type":"education","lineage":["https://openalex.org/I22716506"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Zhao","raw_affiliation_strings":["Department of Computing and Communication, Lanzhou University of Technology, Lanzhou, Gansu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing and Communication, Lanzhou University of Technology, Lanzhou, Gansu, China","institution_ids":["https://openalex.org/I22716506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032307728","display_name":"Wengai Li","orcid":"https://orcid.org/0009-0006-2570-9173"},"institutions":[{"id":"https://openalex.org/I22716506","display_name":"Lanzhou University of Technology","ror":"https://ror.org/03panb555","country_code":"CN","type":"education","lineage":["https://openalex.org/I22716506"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wengai Li","raw_affiliation_strings":["Department of Computing and Communication, Lanzhou University of Technology, Lanzhou, Gansu, China"],"raw_orcid":"https://orcid.org/0009-0006-2570-9173","affiliations":[{"raw_affiliation_string":"Department of Computing and Communication, Lanzhou University of Technology, Lanzhou, Gansu, China","institution_ids":["https://openalex.org/I22716506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000231514","display_name":"Zhaobin Chang","orcid":"https://orcid.org/0000-0002-1574-979X"},"institutions":[{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaobin Chang","raw_affiliation_strings":["Department of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Science and Engineering, Lanzhou University, Lanzhou, Gansu, China","institution_ids":["https://openalex.org/I76214153"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101542380","display_name":"Ce Yang","orcid":"https://orcid.org/0000-0002-6432-443X"},"institutions":[{"id":"https://openalex.org/I22716506","display_name":"Lanzhou University of Technology","ror":"https://ror.org/03panb555","country_code":"CN","type":"education","lineage":["https://openalex.org/I22716506"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ce Yang","raw_affiliation_strings":["Department of Computing and Communication, Lanzhou University of Technology, Lanzhou, Gansu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing and Communication, Lanzhou University of Technology, Lanzhou, Gansu, China","institution_ids":["https://openalex.org/I22716506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.2187,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.48956202,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"12","issue":null,"first_page":"112948","last_page":"112965"},"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":0.9980999827384949,"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":0.9980999827384949,"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":0.9980999827384949,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9961000084877014,"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":0.6616739630699158},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5747898817062378},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.303653359413147},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13717153668403625},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.11229836940765381}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6616739630699158},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5747898817062378},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.303653359413147},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13717153668403625},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.11229836940765381}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3442296","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3442296","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:25b2bbba452f4936a5954ea82f08adbf","is_oa":true,"landing_page_url":"https://doaj.org/article/25b2bbba452f4936a5954ea82f08adbf","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 112948-112965 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3442296","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3442296","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2405023128","display_name":null,"funder_award_id":"21YF5GA073","funder_id":"https://openalex.org/F4320336616","funder_display_name":"Science and Technology Program of Gansu Province"},{"id":"https://openalex.org/G4394550696","display_name":null,"funder_award_id":"62166025","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336616","display_name":"Science and Technology Program of Gansu Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1797268635","https://openalex.org/W1861492603","https://openalex.org/W2009423060","https://openalex.org/W2117539524","https://openalex.org/W2745461083","https://openalex.org/W2962785568","https://openalex.org/W3049024148","https://openalex.org/W3121370741","https://openalex.org/W3153469116","https://openalex.org/W3174807077","https://openalex.org/W3206395542","https://openalex.org/W3216237230","https://openalex.org/W3216352822","https://openalex.org/W4224035735","https://openalex.org/W4226125322","https://openalex.org/W4229042118","https://openalex.org/W4283388932","https://openalex.org/W4287029626","https://openalex.org/W4289785045","https://openalex.org/W4307076412","https://openalex.org/W4312388283","https://openalex.org/W4312740349","https://openalex.org/W4312933868","https://openalex.org/W4312946364","https://openalex.org/W4312974539","https://openalex.org/W4312977351","https://openalex.org/W4323650883","https://openalex.org/W4383503489","https://openalex.org/W4386075639","https://openalex.org/W6742999658","https://openalex.org/W6765779288","https://openalex.org/W6783713337","https://openalex.org/W6790978476","https://openalex.org/W6796242362","https://openalex.org/W6802517614","https://openalex.org/W6804566349","https://openalex.org/W6809885388","https://openalex.org/W6810940779","https://openalex.org/W6811072154","https://openalex.org/W6838639034","https://openalex.org/W6839643428","https://openalex.org/W6840155194","https://openalex.org/W6841366371","https://openalex.org/W6846344700","https://openalex.org/W6850360799","https://openalex.org/W6850480200","https://openalex.org/W6852648671"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2864363823"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,19,104,137,159],"text-to-image":[3,58],"generation":[4,96],"have":[5],"demonstrated":[6],"significant":[7],"progress,":[8],"especially":[9],"with":[10],"diffusion-based":[11],"models":[12],"conditioned":[13],"on":[14,94],"textual":[15,68,81,92,116],"prompts,":[16,179],"which":[17],"excel":[18],"image":[20,33,44,95,106,151,188],"quality":[21],"and":[22,34,37,69,80,115,131,146,149,177],"diversity.":[23],"However,":[24],"these":[25,48],"methods":[26],"often":[27],"encounter":[28],"a":[29,120],"semantic":[30],"gap":[31],"between":[32,144,174],"text":[35,145,178],"modalities":[36],"suffer":[38],"from":[39],"imprecise":[40],"localization":[41,152,185],"during":[42,186],"text-based":[43],"editing.":[45,108],"To":[46,109],"address":[47],"challenges,":[49],"we":[50,118],"propose":[51],"the":[52,78,89,105,134,142,155,165,168],"Diffusion-based":[53],"Knowledge-enhanced":[54],"Mask":[55],"Transformer":[56],"(Diff-KT)":[57],"model.":[59],"Diff-KT":[60,140,169],"leverages":[61],"knowledge":[62,71],"enhancement":[63],"strategies":[64],"to":[65,100,125],"incorporate":[66],"fine-grained":[67],"visual":[70,114],"of":[72,83,91,113,129,167],"key":[73],"scene":[74],"elements,":[75],"thereby":[76],"improving":[77],"fidelity":[79],"consistency":[82],"generated":[84,138,147,175],"images.":[85,139,161],"Furthermore,":[86],"it":[87],"enhances":[88,150],"controllability":[90],"influences":[93],"by":[97],"using":[98],"masks":[99],"precisely":[101],"target":[102],"areas":[103],"for":[107],"facilitate":[110],"deeper":[111],"fusion":[112],"information,":[117],"introduce":[119],"multimodal":[121],"pre-trained":[122],"model":[123],"CoCa,":[124],"extract":[126],"joint":[127],"representations":[128],"images":[130,148,176],"text,":[132],"enhancing":[133],"detailed":[135],"expression":[136],"improves":[141],"correlation":[143,173],"precision":[153],"within":[154],"diffusion":[156],"model,":[157,170],"resulting":[158],"high-quality":[160],"Experimental":[162],"results":[163],"validate":[164],"advantages":[166],"demonstrating":[171],"higher":[172],"as":[180,182],"well":[181],"more":[183],"accurate":[184],"text-guided":[187],"editing,":[189],"underscoring":[190],"its":[191],"practical":[192],"value.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
