{"id":"https://openalex.org/W7138018603","doi":"https://doi.org/10.1609/aaai.v40i3.37185","title":"SCORE: Semantic Collage by Optimizing Rendered Elements","display_name":"SCORE: Semantic Collage by Optimizing Rendered Elements","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138018603","doi":"https://doi.org/10.1609/aaai.v40i3.37185"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i3.37185","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i3.37185","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i3.37185","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129746105","display_name":"Zefan Shao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zefan Shao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129651686","display_name":"Jin Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129736014","display_name":"Hongliang Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongliang Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129716472","display_name":"Pengfei Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengfei Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.2542735,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"3","first_page":"2038","last_page":"2046"},"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":0.5874000191688538,"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":0.5874000191688538,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.14749999344348907,"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"}},{"id":"https://openalex.org/T10789","display_name":"Interactive and Immersive Displays","score":0.05180000141263008,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/leverage","display_name":"Leverage (statistics)","score":0.737500011920929},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5472000241279602},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5285999774932861},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5092999935150146},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.42719998955726624},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4156999886035919},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.39559999108314514},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.3855000138282776},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.3589000105857849}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8047000169754028},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.737500011920929},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5472000241279602},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5285999774932861},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5092999935150146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4918999969959259},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.42719998955726624},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4156999886035919},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.39559999108314514},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.3855000138282776},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.3589000105857849},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34529998898506165},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3312000036239624},{"id":"https://openalex.org/C174998907","wikidata":"https://www.wikidata.org/wiki/Q357662","display_name":"Work in process","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3257000148296356},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.29260000586509705},{"id":"https://openalex.org/C72010251","wikidata":"https://www.wikidata.org/wiki/Q5265688","display_name":"Determinantal point process","level":4,"score":0.2906000018119812},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.2635999917984009}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i3.37185","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i3.37185","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37185","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i3.37185","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i3.37185","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6106023788452148,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Collage":[0,41],"is":[1,64,147,174],"a":[2,21,46,77,85,116,150,175,196],"powerful":[3,198],"medium":[4],"for":[5,200],"visual":[6,28,202],"expression,":[7],"traditionally":[8],"demanding":[9],"significant":[10],"artistic":[11],"expertise":[12],"and":[13,26,57,98,166,183,194],"manual":[14],"effort.":[15],"Existing":[16],"methods":[17],"often":[18],"struggle":[19],"with":[20,124,160],"trade-off":[22],"between":[23],"semantic":[24,113,158],"expression":[25,193],"the":[27,31,52,67,72,92,120,125,134,137,156,189],"fidelity":[29],"of":[30,54,100,136,172],"constituent":[32],"images.":[33],"To":[34],"address":[35],"this,":[36],"we":[37,80],"introduce":[38],"SCORE":[39,173],"(Semantic":[40],"by":[42,140,149],"Optimizing":[43],"Rendered":[44],"Elements),":[45],"novel":[47],"text-driven":[48],"framework":[49],"that":[50,154,163,179],"automates":[51],"creation":[53],"semantically":[55],"rich":[56],"structurally":[58],"sound":[59],"collages.":[60],"Our":[61,186],"key":[62],"innovation":[63],"to":[65,91,110,191],"shift":[66],"optimization":[68],"process":[69],"entirely":[70],"into":[71],"image":[73,102],"space.":[74],"By":[75],"employing":[76],"differentiable":[78],"renderer,":[79],"can":[81],"backpropagate":[82],"gradients":[83],"from":[84,115],"powerful,":[86],"pre-trained":[87],"text-to-image":[88],"model":[89],"directly":[90],"spatial":[93],"parameters,":[94],"including":[95],"position,":[96],"rotation,":[97],"scale,":[99],"each":[101],"element.":[103],"We":[104],"leverage":[105],"Variational":[106],"Score":[107],"Distillation":[108],"(VSD)":[109],"provide":[111],"robust":[112],"guidance":[114],"text":[117],"prompt,":[118],"ensuring":[119],"final":[121],"layout":[122,146],"aligns":[123],"desired":[126],"concept.":[127],"Crucially,":[128],"our":[129],"''minimal":[130],"editing''":[131],"principle":[132],"preserves":[133],"integrity":[135],"original":[138],"elements":[139],"forgoing":[141],"any":[142],"content-level":[143],"modifications.":[144],"The":[145,170],"refined":[148],"joint":[151],"loss":[152,159],"function":[153],"combines":[155],"VSD-based":[157],"structural":[161],"regularizers":[162],"penalize":[164],"overlap":[165],"enforce":[167],"boundary":[168],"constraints.":[169],"output":[171],"parametric,":[176],"structured":[177],"representation":[178],"allows":[180],"further":[181],"editing":[182],"downstream":[184],"use.":[185],"work":[187],"reduces":[188],"barrier":[190],"creative":[192],"provides":[195],"new,":[197],"paradigm":[199],"organizing":[201],"contents.":[203]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2026-03-18T00:00:00"}
