{"id":"https://openalex.org/W4413776397","doi":"https://doi.org/10.1049/ipr2.70185","title":"MemAttn\u2010CL: Unified Memory, Attention, and Contrastive Learning for Enhanced Text\u2010to\u2010Image Generation","display_name":"MemAttn\u2010CL: Unified Memory, Attention, and Contrastive Learning for Enhanced Text\u2010to\u2010Image Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4413776397","doi":"https://doi.org/10.1049/ipr2.70185"},"language":"en","primary_location":{"id":"doi:10.1049/ipr2.70185","is_oa":true,"landing_page_url":"https://doi.org/10.1049/ipr2.70185","pdf_url":null,"source":{"id":"https://openalex.org/S83215360","display_name":"IET Image Processing","issn_l":"1751-9659","issn":["1751-9659","1751-9667"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311714","host_organization_name":"Institution of Engineering and Technology","host_organization_lineage":["https://openalex.org/P4310311714"],"host_organization_lineage_names":["Institution of Engineering and Technology"],"type":"journal"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IET Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1049/ipr2.70185","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100765792","display_name":"Md. Ahsan Habib","orcid":"https://orcid.org/0000-0002-5498-8339"},"institutions":[{"id":"https://openalex.org/I41173762","display_name":"Mawlana Bhashani Science and Technology University","ror":"https://ror.org/00gvj4587","country_code":"BD","type":"education","lineage":["https://openalex.org/I41173762"]},{"id":"https://openalex.org/I4210110242","display_name":"Digital Science (United States)","ror":"https://ror.org/020h4b682","country_code":"US","type":"company","lineage":["https://openalex.org/I4210110242","https://openalex.org/I4210112888","https://openalex.org/I4210118830"]}],"countries":["BD","US"],"is_corresponding":false,"raw_author_name":"Md. Ahsan Habib","raw_affiliation_strings":["Department of Computer Science and Engineering Mawlana Bhashani Science and Technology University, Santosh Tangail Bangladesh","Department of Software Engineering Gazipur Digital University Kaliakair Bangladesh"],"raw_orcid":"https://orcid.org/0000-0002-5498-8339","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering Mawlana Bhashani Science and Technology University, Santosh Tangail Bangladesh","institution_ids":["https://openalex.org/I41173762"]},{"raw_affiliation_string":"Department of Software Engineering Gazipur Digital University Kaliakair Bangladesh","institution_ids":["https://openalex.org/I4210110242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080809190","display_name":"Md. Anwar Hussen Wadud","orcid":"https://orcid.org/0000-0002-7344-0838"},"institutions":[{"id":"https://openalex.org/I3132915206","display_name":"Dagon University","ror":"https://ror.org/05rn78z96","country_code":"MM","type":"education","lineage":["https://openalex.org/I3132915206"]},{"id":"https://openalex.org/I41173762","display_name":"Mawlana Bhashani Science and Technology University","ror":"https://ror.org/00gvj4587","country_code":"BD","type":"education","lineage":["https://openalex.org/I41173762"]}],"countries":["BD","MM"],"is_corresponding":false,"raw_author_name":"Md. Anwar Hussen Wadud","raw_affiliation_strings":["Department of Computer Science and Engineering Mawlana Bhashani Science and Technology University, Santosh Tangail Bangladesh","Department of Computer Science and Engineering Sunamgonj Science and Technology University Sunamgonj Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering Mawlana Bhashani Science and Technology University, Santosh Tangail Bangladesh","institution_ids":["https://openalex.org/I41173762"]},{"raw_affiliation_string":"Department of Computer Science and Engineering Sunamgonj Science and Technology University Sunamgonj Bangladesh","institution_ids":["https://openalex.org/I3132915206"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072317896","display_name":"Mohammad Motiur Rahman","orcid":"https://orcid.org/0000-0003-4417-8276"},"institutions":[{"id":"https://openalex.org/I41173762","display_name":"Mawlana Bhashani Science and Technology University","ror":"https://ror.org/00gvj4587","country_code":"BD","type":"education","lineage":["https://openalex.org/I41173762"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Mohammad Motiur Rahman","raw_affiliation_strings":["Department of Computer Science and Engineering Mawlana Bhashani Science and Technology University, Santosh Tangail Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering Mawlana Bhashani Science and Technology University, Santosh Tangail Bangladesh","institution_ids":["https://openalex.org/I41173762"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071208302","display_name":"M. F. Mridha","orcid":"https://orcid.org/0000-0001-5738-1631"},"institutions":[{"id":"https://openalex.org/I103434671","display_name":"American International University-Bangladesh","ror":"https://ror.org/02j8ga255","country_code":"BD","type":"education","lineage":["https://openalex.org/I103434671"]}],"countries":["BD"],"is_corresponding":true,"raw_author_name":"M. F. Mridha","raw_affiliation_strings":["Department of Computer Science and Engineering American International University Dhaka Bangaladesh"],"raw_orcid":"https://orcid.org/0000-0001-5738-1631","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering American International University Dhaka Bangaladesh","institution_ids":["https://openalex.org/I103434671"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5071208302"],"corresponding_institution_ids":["https://openalex.org/I103434671"],"apc_list":{"value":2530,"currency":"USD","value_usd":2530},"apc_paid":{"value":2530,"currency":"USD","value_usd":2530},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17546372,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"19","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987999796867371,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987999796867371,"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/T10028","display_name":"Topic Modeling","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9937000274658203,"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":0.748601496219635},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5655562877655029},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5467374324798584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5367926359176636},{"id":"https://openalex.org/keywords/text-generation","display_name":"Text generation","score":0.44225138425827026},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3538029193878174},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33744359016418457}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.748601496219635},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5655562877655029},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5467374324798584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5367926359176636},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.44225138425827026},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3538029193878174},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33744359016418457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1049/ipr2.70185","is_oa":true,"landing_page_url":"https://doi.org/10.1049/ipr2.70185","pdf_url":null,"source":{"id":"https://openalex.org/S83215360","display_name":"IET Image Processing","issn_l":"1751-9659","issn":["1751-9659","1751-9667"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311714","host_organization_name":"Institution of Engineering and Technology","host_organization_lineage":["https://openalex.org/P4310311714"],"host_organization_lineage_names":["Institution of Engineering and Technology"],"type":"journal"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IET Image Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1049/ipr2.70185","is_oa":true,"landing_page_url":"https://doi.org/10.1049/ipr2.70185","pdf_url":null,"source":{"id":"https://openalex.org/S83215360","display_name":"IET Image Processing","issn_l":"1751-9659","issn":["1751-9659","1751-9667"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311714","host_organization_name":"Institution of Engineering and Technology","host_organization_lineage":["https://openalex.org/P4310311714"],"host_organization_lineage_names":["Institution of Engineering and Technology"],"type":"journal"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IET Image Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2533598788","https://openalex.org/W2546696630","https://openalex.org/W2559655401","https://openalex.org/W2962845008","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W2964295005","https://openalex.org/W2965289598","https://openalex.org/W2966792645","https://openalex.org/W2990138404","https://openalex.org/W3021593901","https://openalex.org/W3126750203","https://openalex.org/W3128979644","https://openalex.org/W3174525637","https://openalex.org/W4214490042","https://openalex.org/W4281969232","https://openalex.org/W4312933868","https://openalex.org/W4312977351","https://openalex.org/W4366598160","https://openalex.org/W4389747902","https://openalex.org/W4402660147","https://openalex.org/W4402713110","https://openalex.org/W4411245279"],"related_works":["https://openalex.org/W4389009515","https://openalex.org/W3194553618","https://openalex.org/W3211013666","https://openalex.org/W4366557471","https://openalex.org/W2066972210","https://openalex.org/W4210453527","https://openalex.org/W4247507802","https://openalex.org/W3169121507","https://openalex.org/W4285816941","https://openalex.org/W4256240022"],"abstract_inverted_index":{"ABSTRACT":[0],"Generating":[1],"photo\u2010realistic":[2],"images":[3,27,69,110],"from":[4],"natural":[5,16],"language":[6,17],"descriptions":[7],"is":[8,155],"a":[9,29,84,103,126,137,200,238],"challenging":[10],"task":[11],"at":[12],"the":[13,34,38,63,80,113,123,178,208,219,230],"intersection":[14],"of":[15,37,191,197,205,234],"processing":[18],"and":[19,56,67,77,96,120,149,162,175,199,214,232],"computer":[20],"vision.":[21],"Text\u2010to\u2010image":[22],"synthesis":[23],"involves":[24],"generating":[25],"visual":[26,164],"in":[28,48,54,79,102],"way":[30],"which":[31],"naturally":[32],"matches":[33],"semantic":[35,59,151,157],"meaning":[36],"input":[39],"text.":[40],"Recent":[41],"diffusion\u2010based":[42],"models":[43],"have":[44],"demonstrated":[45],"strong":[46,213],"performance":[47,216],"image":[49,160],"fidelity":[50],"but":[51],"are":[52],"slow":[53],"inference":[55],"exhibit":[57],"coarse":[58],"alignment.":[60],"To":[61],"overcome":[62],"two":[64],"problems":[65],"above":[66],"allow":[68],"to":[70,75,145],"be":[71],"more":[72],"faithful":[73],"(realistic)":[74],"texts":[76],"semantics":[78],"wild,":[81],"we":[82,106],"propose":[83],"novel":[85],"hybrid":[86],"architecture":[87],"called":[88],"DM\u2010GAN+ATT+CL":[89,180],"(dynamic":[90],"memory":[91],"GAN":[92],"+":[93],"contrastive":[94],"learning":[95,132],"attention":[97,118],"mechanisms).":[98],"Our":[99],"method":[100],"proceeds":[101],"two\u2010step":[104],"manner:":[105],"first":[107],"produce":[108],"low\u2010resolution":[109],"based":[111],"on":[112,136,207],"DM\u2010GAN":[114],"model":[115],"with":[116,140,211],"dual":[117],"modules":[119],"then":[121,134],"refine":[122],"results":[124,168],"through":[125],"memory\u2010based":[127],"feature":[128,147],"refinement":[129],"mechanism.":[130],"Contrastive":[131],"was":[133],"utilized":[135],"separate":[138],"dataset":[139],"high":[141],"resolution":[142],"image\u2010text":[143],"pairs":[144],"enhance":[146],"discrimination":[148],"strengthen":[150],"consistency.":[152],"The":[153],"result":[154],"richer":[156],"relevance,":[158],"stronger":[159],"variation":[161],"better":[163,239],"quality.":[165],"Extensive":[166],"experimental":[167],"across":[169,218],"multiple":[170],"benchmark":[171],"datasets\u2014CUB,":[172],"Oxford\u2010102,":[173],"MS\u2010COCO,":[174],"MM\u2010CelebA\u2010HQ\u2014demonstrate":[176],"that":[177,225],"proposed":[179],"framework":[181],"consistently":[182],"outperforms":[183],"state\u2010of\u2010the\u2010art":[184],"baselines.":[185],"Notably,":[186],"it":[187],"achieved":[188],"an":[189,193],"R\u2010precision":[190],"95.24,":[192],"inception":[194,202],"score":[195],"(IS)":[196],"38.43,":[198],"Fr\u00e9chet":[201],"distance":[203],"(FID)":[204],"11.30":[206],"MS\u2010COCO":[209],"dataset,":[210],"similarly":[212],"consistent":[215],"observed":[217],"other":[220],"datasets.":[221],"These":[222],"findings":[223],"indicate":[224],"our":[226],"approach":[227],"substantially":[228],"enriches":[229],"diversity":[231],"reality":[233],"synthetic":[235],"images,":[236],"promising":[237],"future":[240],"for":[241],"text\u2010image":[242],"matching.":[243]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}