{"id":"https://openalex.org/W4410772208","doi":"https://doi.org/10.1145/3724122","title":"Picasso: Analyzing Prompt Design for Text-to-Image Generative Diffusion Models from a Temporal-Spatial Perspective","display_name":"Picasso: Analyzing Prompt Design for Text-to-Image Generative Diffusion Models from a Temporal-Spatial Perspective","publication_year":2025,"publication_date":"2025-05-27","ids":{"openalex":"https://openalex.org/W4410772208","doi":"https://doi.org/10.1145/3724122"},"language":"en","primary_location":{"id":"doi:10.1145/3724122","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3724122","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-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/A5028643558","display_name":"Haoyu Cai","orcid":"https://orcid.org/0000-0002-5010-3396"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyu Cai","raw_affiliation_strings":["The School of Computer Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-5010-3396","affiliations":[{"raw_affiliation_string":"The School of Computer Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034765006","display_name":"Wenqi Lou","orcid":"https://orcid.org/0000-0002-2240-6672"},"institutions":[{"id":"https://openalex.org/I308837","display_name":"Suzhou University of Science and Technology","ror":"https://ror.org/04en8wb91","country_code":"CN","type":"education","lineage":["https://openalex.org/I308837"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenqi Lou","raw_affiliation_strings":["The School of Software Engineering, University of Science and Technology of China, Hefei, China and the Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-2240-6672","affiliations":[{"raw_affiliation_string":"The School of Software Engineering, University of Science and Technology of China, Hefei, China and the Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, China","institution_ids":["https://openalex.org/I308837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011884768","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0002-9403-5575"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["The School of Computer Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-9403-5575","affiliations":[{"raw_affiliation_string":"The School of Computer Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077322091","display_name":"Xuehai Zhou","orcid":"https://orcid.org/0000-0002-8360-3143"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuehai Zhou","raw_affiliation_strings":["The School of Computer Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-8360-3143","affiliations":[{"raw_affiliation_string":"The School of Computer Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09862074,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":"11","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12650","display_name":"Aesthetic Perception and Analysis","score":0.9750999808311462,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12650","display_name":"Aesthetic Perception and Analysis","score":0.9750999808311462,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12496","display_name":"Color perception and design","score":0.9736999869346619,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14254","display_name":"Digital Media and Visual Art","score":0.9678999781608582,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8670898675918579},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.7806177139282227},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6392620205879211},{"id":"https://openalex.org/keywords/generative-design","display_name":"Generative Design","score":0.5469056963920593},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5275435447692871},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.46656811237335205},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4562999904155731},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4320821166038513},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3588786721229553},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3292350172996521},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3220469057559967}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8670898675918579},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.7806177139282227},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6392620205879211},{"id":"https://openalex.org/C184408114","wikidata":"https://www.wikidata.org/wiki/Q1502022","display_name":"Generative Design","level":3,"score":0.5469056963920593},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5275435447692871},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.46656811237335205},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4562999904155731},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4320821166038513},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3588786721229553},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3292350172996521},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3220469057559967},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3724122","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3724122","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G461544363","display_name":null,"funder_award_id":"BK20241818","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G6284701254","display_name":null,"funder_award_id":"Y2021121","funder_id":"https://openalex.org/F4320322847","funder_display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences"},{"id":"https://openalex.org/G6472083938","display_name":null,"funder_award_id":"62172380","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/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2113076747","https://openalex.org/W2764024122","https://openalex.org/W2939869194","https://openalex.org/W3035653890","https://openalex.org/W3096831136","https://openalex.org/W3171125843","https://openalex.org/W3174422331","https://openalex.org/W3216352822","https://openalex.org/W4226211505","https://openalex.org/W4281485151","https://openalex.org/W4283705858","https://openalex.org/W4283820492","https://openalex.org/W4285124635","https://openalex.org/W4288073028","https://openalex.org/W4312933868","https://openalex.org/W4323924854","https://openalex.org/W4386072096","https://openalex.org/W4386076425","https://openalex.org/W4386076532","https://openalex.org/W4388196927","https://openalex.org/W4390873054"],"related_works":["https://openalex.org/W4301024388","https://openalex.org/W775311126","https://openalex.org/W4300030714","https://openalex.org/W4391334978","https://openalex.org/W1517876498","https://openalex.org/W4365211920","https://openalex.org/W3021262926","https://openalex.org/W4317695495","https://openalex.org/W4388137171","https://openalex.org/W1967909251"],"abstract_inverted_index":{"Visual":[0,17],"Concept":[1,18],"Implantation":[2],"(VCI)":[3],"is":[4],"essential":[5],"in":[6,12,31,63,75,124,142],"text-to-image":[7],"fields.":[8],"While":[9],"VCI":[10,32],"methods":[11],"diffusion":[13,64],"models":[14,65],"have":[15],"matured,":[16],"Disentanglement":[19],"(VCD)":[20],"remains":[21],"an":[22],"unexplored":[23],"area.":[24],"VCD":[25,62,74,123],"involves":[26],"analyzing":[27],"Prompt":[28,47,95,102,109],"Spaces":[29,96],"trained":[30],"to":[33,46],"produce":[34],"disentangled":[35],"SubPrompts":[36],"or":[37],"SubCones":[38,86],"for":[39,61,70,88,101,122],"exploring":[40],"interpretability.":[41],"However,":[42],"challenges":[43],"arise":[44],"due":[45],"Space":[48,103],"design":[49,155],"complexity":[50],"and":[51,128,147],"feature":[52],"information":[53],"extraction.":[54],"We":[55],"propose":[56],"Picasso,":[57],"a":[58,78,106,119],"unified":[59,89],"framework":[60,90],"(DM).":[66],"Our":[67,116],"contributions":[68],"include:":[69],"performance":[71],"evaluation:":[72],"Transforming":[73],"DM":[76],"into":[77],"regular":[79],"clustering":[80],"task":[81],"by":[82],"Visualization":[83],"based":[84,112],"on":[85,113],"(VbSC);":[87],"design:":[91],"Picasso":[92,157],"processes":[93],"diverse":[94],"using":[97],"spatially":[98],"clusterable":[99],"features;":[100],"exploration:":[104],"Introducing":[105],"temporal-spatial":[107],"SOTA":[108],"Design":[110],"subset":[111],"temporal":[114],"features.":[115],"method":[117,141],"provides":[118],"feasible":[120],"mechanism":[121],"DM.":[125],"Through":[126],"functional":[127],"interpretability":[129],"validation":[130],"methods,":[131],"we":[132],"will":[133,158],"comprehensively":[134],"evaluate":[135],"the":[136,149,152],"effectiveness":[137],"of":[138,151],"our":[139],"proposed":[140],"visual":[143],"concept":[144],"implantation":[145],"tasks":[146],"verify":[148],"correctness":[150],"parameter":[153],"space":[154],"principles.":[156],"be":[159],"released":[160],"at":[161],"https://haoyu-cai.github.io/our_picasso":[162],".":[163]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
