{"id":"https://openalex.org/W4415540256","doi":"https://doi.org/10.1145/3746027.3755280","title":"MPPR: Memory-Prior-based Prompt Refinement in Continuous Space for Advanced Text-to-Image Generation","display_name":"MPPR: Memory-Prior-based Prompt Refinement in Continuous Space for Advanced Text-to-Image Generation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540256","doi":"https://doi.org/10.1145/3746027.3755280"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755280","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5025624210","display_name":"Z. Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhibing Zhang","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0009-0003-9558-4917","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101419029","display_name":"Jiantao Lin","orcid":"https://orcid.org/0000-0001-5705-2299"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiantao Lin","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-5705-2299","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021000274","display_name":"Cangqi Zhou","orcid":"https://orcid.org/0000-0003-0528-8202"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cangqi Zhou","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0003-0528-8202","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035534911","display_name":"Rui Xia","orcid":"https://orcid.org/0000-0002-0621-1058"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Xia","raw_affiliation_strings":["Nanjing University of Science and Technology, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0002-0621-1058","affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9978","last_page":"9986"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","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/T11105","display_name":"Advanced Image Processing Techniques","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/T11019","display_name":"Image Enhancement Techniques","score":0.9984999895095825,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9977999925613403,"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/generative-grammar","display_name":"Generative grammar","score":0.7396000027656555},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.5855000019073486},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5746999979019165},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.49309998750686646},{"id":"https://openalex.org/keywords/continuous-optimization","display_name":"Continuous optimization","score":0.439300000667572},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.4189999997615814},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.3986000120639801}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7484999895095825},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7396000027656555},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.5855000019073486},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5746999979019165},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.49309998750686646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4821999967098236},{"id":"https://openalex.org/C92995354","wikidata":"https://www.wikidata.org/wiki/Q5165499","display_name":"Continuous optimization","level":4,"score":0.439300000667572},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.4189999997615814},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3986000120639801},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.3637999892234802},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2964000105857849},{"id":"https://openalex.org/C184408114","wikidata":"https://www.wikidata.org/wiki/Q1502022","display_name":"Generative Design","level":3,"score":0.29190000891685486},{"id":"https://openalex.org/C115952470","wikidata":"https://www.wikidata.org/wiki/Q332172","display_name":"Process optimization","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.26190000772476196}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755280","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G74079944","display_name":null,"funder_award_id":"62476134","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W3199400376","https://openalex.org/W4312933868","https://openalex.org/W4379466097"],"related_works":[],"abstract_inverted_index":{"Refining":[0],"user-provided":[1],"natural":[2],"language":[3],"prompts":[4,27,35,125,159],"allows":[5],"users":[6],"to":[7,51,75,80,153,163,171,209,223],"more":[8,131,173],"easily":[9],"obtain":[10],"their":[11],"desired":[12],"outputs":[13],"in":[14,126,166,182,205],"text-to-image":[15],"generation.":[16],"Existing":[17],"automatic":[18],"prompt":[19,88],"refinement":[20],"methods":[21],"predominantly":[22],"take":[23],"discrete,":[24],"human-engineered":[25,34],"high-quality":[26,107,158],"as":[28,109,120,142,160],"the":[29,53,67,71,76,98,110,114,134,143,189,200,206,210,224],"final":[30,144],"optimization":[31,64,89,104,121,165],"target.":[32],"However,":[33],"are":[36],"based":[37],"on":[38],"human":[39,56,101,192],"intuition":[40],"and":[41,58,112,138,194],"derived":[42],"through":[43],"limited":[44],"interaction":[45],"with":[46,94,133],"generative":[47,77,95,118,211],"models,":[48,96],"which":[49],"fails":[50],"bridge":[52],"gap":[54,190],"between":[55,191],"preferences":[57,193],"model":[59,195],"preferences.":[60],"Additionally,":[61],"this":[62],"discrete":[63],"target":[65,111],"limits":[66],"information":[68,204],"capacity":[69],"of":[70,117,157,202],"conditional":[72],"inputs":[73,207],"fed":[74],"model,":[78],"leading":[79],"suboptimal":[81],"outcomes.":[82],"Therefore,":[83],"we":[84],"propose":[85],"an":[86],"end-to-end":[87],"method":[90,218],"that":[91,129,216],"interacts":[92],"directly":[93],"eliminating":[97],"need":[99],"for":[100],"involvement.":[102],"The":[103],"process":[105,137],"takes":[106],"images":[108],"uses":[113],"internal":[115],"states":[116],"models":[119],"signals.":[122],"This":[123,175],"optimizes":[124],"a":[127,150],"way":[128],"aligns":[130],"naturally":[132],"model's":[135],"generation":[136],"producing":[139],"continuous":[140,167,183],"representations":[141],"refined":[145],"prompt.":[146],"We":[147],"also":[148,198],"introduce":[149],"memory":[151],"module":[152],"store":[154],"common":[155],"features":[156],"prior":[161],"knowledge":[162],"guide":[164],"space,":[168],"enabling":[169],"it":[170],"be":[172],"efficient.":[174],"memory-p":[176],"rior-based":[177],"p":[178],"rompt":[179],"r":[180],"efinement":[181],"space":[184],"(MPPR)":[185],"not":[186],"only":[187],"bridges":[188],"preferences,":[196],"but":[197],"resolves":[199],"issue":[201],"insufficient":[203],"provided":[208],"model.":[212],"Extensive":[213],"experiments":[214],"show":[215],"our":[217],"achieves":[219],"better":[220],"performance":[221],"compared":[222],"state-of-the-art":[225],"baselines.":[226]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}