{"id":"https://openalex.org/W4398233049","doi":"https://doi.org/10.1145/3652628.3652682","title":"CSF-GAN: A Text-to-Image generation method based on controllable semantic fusion","display_name":"CSF-GAN: A Text-to-Image generation method based on controllable semantic fusion","publication_year":2023,"publication_date":"2023-11-17","ids":{"openalex":"https://openalex.org/W4398233049","doi":"https://doi.org/10.1145/3652628.3652682"},"language":"en","primary_location":{"id":"doi:10.1145/3652628.3652682","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3652628.3652682","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Artificial Intelligence and Computer Engineering","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/A5103021668","display_name":"Xiaofeng He","orcid":"https://orcid.org/0009-0007-9616-1595"},"institutions":[{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng He","raw_affiliation_strings":["Dalian Minzu University, China"],"raw_orcid":"https://orcid.org/0009-0007-9616-1595","affiliations":[{"raw_affiliation_string":"Dalian Minzu University, China","institution_ids":["https://openalex.org/I61565387"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yangjihong Wang","orcid":"https://orcid.org/0009-0009-1789-7508"},"institutions":[{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangjihong Wang","raw_affiliation_strings":["Dalian Minzu University, China"],"raw_orcid":"https://orcid.org/0009-0009-1789-7508","affiliations":[{"raw_affiliation_string":"Dalian Minzu University, China","institution_ids":["https://openalex.org/I61565387"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103283555","display_name":"Mingwei Tong","orcid":"https://orcid.org/0009-0004-2895-3054"},"institutions":[{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingwei Tong","raw_affiliation_strings":["Dalian Minzu University, China"],"raw_orcid":"https://orcid.org/0009-0004-2895-3054","affiliations":[{"raw_affiliation_string":"Dalian Minzu University, China","institution_ids":["https://openalex.org/I61565387"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I61565387"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"326","last_page":"330"},"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":0.9970999956130981,"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":0.9970999956130981,"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":0.9901999831199646,"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":0.9872999787330627,"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":0.7324787974357605},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6279436349868774},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.5925173759460449},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5922666192054749},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5691603422164917},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.5485419631004333},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.543122410774231},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5070629119873047},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4953716993331909},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.48933547735214233},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4615575969219208},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.43528348207473755},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35256829857826233},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.22816842794418335},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13113906979560852}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7324787974357605},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6279436349868774},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.5925173759460449},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5922666192054749},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5691603422164917},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.5485419631004333},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.543122410774231},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5070629119873047},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4953716993331909},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.48933547735214233},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4615575969219208},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.43528348207473755},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35256829857826233},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.22816842794418335},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13113906979560852},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3652628.3652682","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3652628.3652682","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Artificial Intelligence and Computer Engineering","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":6,"referenced_works":["https://openalex.org/W3096831136","https://openalex.org/W4210736987","https://openalex.org/W4224861089","https://openalex.org/W4236965008","https://openalex.org/W4301409532","https://openalex.org/W4365421094"],"related_works":["https://openalex.org/W1568307077","https://openalex.org/W2788731446","https://openalex.org/W2204403038","https://openalex.org/W3152170969","https://openalex.org/W2379054866","https://openalex.org/W2549658594","https://openalex.org/W2095903272","https://openalex.org/W2370195708","https://openalex.org/W1490651872","https://openalex.org/W2139242969"],"abstract_inverted_index":{"To":[0],"address":[1],"the":[2,15,52,69,73,101,104,114,118,130,135,153,164,173],"challenge":[3],"of":[4,17,72,103,109,117,175],"insufficient":[5],"global":[6,90],"information":[7],"processing":[8],"capability":[9],"in":[10,14,122,168],"text-to-image":[11,23],"generation,":[12],"resulting":[13,121],"loss":[16],"image":[18],"details,":[19],"we":[20,77],"propose":[21],"a":[22,79,93],"generation":[24],"method":[25],"based":[26],"on":[27,129],"controllable":[28],"semantic":[29,124],"fusion,":[30],"known":[31],"as":[32],"CSF-GAN.":[33],"Our":[34,126],"approach":[35,99],"begins":[36],"by":[37,141,147],"introducing":[38],"an":[39,47],"Up":[40],"Semantic":[41],"Fusion":[42],"Module":[43,83],"(USFM)":[44],"that":[45,85,134,163],"leverages":[46],"attention":[48],"network":[49],"to":[50,152],"extract":[51],"target":[53],"generated":[54,74,105,119,176],"content":[55],"and":[56,89,144,159],"fuses":[57],"it":[58],"with":[59],"detailed":[60,115],"features":[61,71,91,116],"using":[62,92],"affine":[63],"parameters.":[64],"This":[65,98],"enhancement":[66],"significantly":[67],"improves":[68,138],"fine-grained":[70],"images.":[75,106,177],"Furthermore,":[76],"introduce":[78],"Global":[80],"Feature":[81],"Extraction":[82],"(GFEM)":[84],"captures":[86],"both":[87],"local":[88],"parallel-structured":[94],"null":[95],"gated":[96],"convolution.":[97],"increases":[100],"controllability":[102],"The":[107],"combination":[108],"these":[110],"two":[111],"modules":[112],"strengthens":[113],"images,":[120],"higher":[123],"consistency.":[125],"experimental":[127],"results":[128],"CUB":[131],"dataset":[132],"demonstrate":[133],"SFS-GAN":[136,165],"model":[137,166],"IS":[139],"metrics":[140,146],"approximately":[142],"3.54%":[143],"FID":[145],"about":[148],"4.80%":[149],"when":[150],"compared":[151],"prevailing":[154],"SSA-GAN":[155],"model.":[156],"Both":[157],"qualitative":[158],"quantitative":[160],"analyses":[161],"indicate":[162],"presented":[167],"this":[169],"paper":[170],"effectively":[171],"enhances":[172],"quality":[174]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}