{"id":"https://openalex.org/W4304098884","doi":"https://doi.org/10.1145/3503161.3548282","title":"Draw Your Art Dream: Diverse Digital Art Synthesis with Multimodal Guided Diffusion","display_name":"Draw Your Art Dream: Diverse Digital Art Synthesis with Multimodal Guided Diffusion","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304098884","doi":"https://doi.org/10.1145/3503161.3548282"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548282","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3548282","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548282","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548282","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081580834","display_name":"Nisha Huang","orcid":"https://orcid.org/0000-0002-1627-6584"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Nisha Huang","raw_affiliation_strings":["UCAS &amp; Institute of Automation, CAS, Beijing, China"],"affiliations":[{"raw_affiliation_string":"UCAS &amp; Institute of Automation, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112699696","display_name":"Fan Tang","orcid":"https://orcid.org/0000-0002-3975-2483"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Tang","raw_affiliation_strings":["Jilin University, Changchun, China"],"affiliations":[{"raw_affiliation_string":"Jilin University, Changchun, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069298091","display_name":"Weiming Dong","orcid":"https://orcid.org/0000-0001-6502-145X"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiming Dong","raw_affiliation_strings":["Institute of Automation, CAS &amp; UCAS, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, CAS &amp; UCAS, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022636178","display_name":"Changsheng Xu","orcid":"https://orcid.org/0000-0001-8343-9665"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changsheng Xu","raw_affiliation_strings":["Institute of Automation, CAS &amp; UCAS, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, CAS &amp; UCAS, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5081580834"],"corresponding_institution_ids":["https://openalex.org/I4210112150"],"apc_list":null,"apc_paid":null,"fwci":2.3339,"has_fulltext":true,"cited_by_count":39,"citation_normalized_percentile":{"value":0.92228531,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1085","last_page":"1094"},"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":0.9993000030517578,"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":0.9993000030517578,"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":0.9927999973297119,"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/T11309","display_name":"Music and Audio Processing","score":0.9810000061988831,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.7921394109725952},{"id":"https://openalex.org/keywords/digital-art","display_name":"Digital art","score":0.5286536812782288},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4853469431400299},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45758146047592163},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.4292377829551697},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.420170396566391},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3397735059261322},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33181482553482056}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7921394109725952},{"id":"https://openalex.org/C519222250","wikidata":"https://www.wikidata.org/wiki/Q860372","display_name":"Digital art","level":3,"score":0.5286536812782288},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4853469431400299},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45758146047592163},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.4292377829551697},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.420170396566391},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3397735059261322},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33181482553482056},{"id":"https://openalex.org/C554144382","wikidata":"https://www.wikidata.org/wiki/Q213156","display_name":"Performance art","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C52119013","wikidata":"https://www.wikidata.org/wiki/Q50637","display_name":"Art history","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548282","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3548282","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548282","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3503161.3548282","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3548282","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3548282","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2203821447","display_name":null,"funder_award_id":"U20B2070","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2300469989","display_name":null,"funder_award_id":"Nos. 61832016, U20B2070, 6210070958, 62102162","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3118788558","display_name":null,"funder_award_id":"61832016, U20B2070, 62100709","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G323530312","display_name":null,"funder_award_id":"6183201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3698283540","display_name":null,"funder_award_id":"6210070958","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4885365858","display_name":null,"funder_award_id":"62102162","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5760752404","display_name":null,"funder_award_id":"Projects","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6536340973","display_name":null,"funder_award_id":"U20B207","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6659031125","display_name":null,"funder_award_id":"No. 2020AAA0106200","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7596092009","display_name":null,"funder_award_id":"61832016","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/F4320326873","display_name":"National Laboratory of Pattern Recognition","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4304098884.pdf","grobid_xml":"https://content.openalex.org/works/W4304098884.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1901129140","https://openalex.org/W2001158314","https://openalex.org/W2156771019","https://openalex.org/W2253323104","https://openalex.org/W2331128040","https://openalex.org/W2603777577","https://openalex.org/W2769838727","https://openalex.org/W2888457764","https://openalex.org/W2914071594","https://openalex.org/W2939689347","https://openalex.org/W2962785568","https://openalex.org/W2962793481","https://openalex.org/W2963097270","https://openalex.org/W2963966654","https://openalex.org/W3049038876","https://openalex.org/W3086415202","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3092775865","https://openalex.org/W3093370337","https://openalex.org/W3094502228","https://openalex.org/W3109377857","https://openalex.org/W3135367836","https://openalex.org/W3152404362","https://openalex.org/W3180355996","https://openalex.org/W3182683290","https://openalex.org/W3183258422","https://openalex.org/W3202767484","https://openalex.org/W3204522981","https://openalex.org/W3207865986","https://openalex.org/W3209453723","https://openalex.org/W3211023586","https://openalex.org/W3216156094","https://openalex.org/W4200633008","https://openalex.org/W4214926101","https://openalex.org/W4281253515","https://openalex.org/W4283073926","https://openalex.org/W4285531802","https://openalex.org/W4286611278","https://openalex.org/W4312933868","https://openalex.org/W4313029666"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2110287964","https://openalex.org/W2167701463","https://openalex.org/W4307407935"],"abstract_inverted_index":{"Digital":[0],"art":[1,17,21,103],"synthesis":[2,22],"is":[3,57,83,119],"receiving":[4],"increasing":[5],"attention":[6],"in":[7],"the":[8,14,32,35,38,49,72,77,95,100,106,109,112],"multimedia":[9],"community":[10],"because":[11],"of":[12,34,40,99,108,111],"engaging":[13],"public":[15],"with":[16],"effectively.":[18],"Current":[19],"digital":[20,60,102],"methods":[23],"usually":[24],"use":[25],"single-modality":[26],"inputs":[27],"as":[28,68],"guidance,":[29],"thereby":[30],"limiting":[31],"expressiveness":[33],"model":[36,82,114],"and":[37,88,97,115],"diversity":[39],"generated":[41,101],"results.":[42],"To":[43],"solve":[44],"this":[45],"problem,":[46],"we":[47],"propose":[48],"multimodal":[50,66,116],"guided":[51],"artwork":[52,61],"diffusion":[53,74,113],"(MGAD)":[54],"model,":[55],"which":[56],"a":[58],"diffusion-based":[59],"generation":[62],"approach":[63],"that":[64],"utilizes":[65],"prompts":[67],"guidance":[69],"to":[70,85],"control":[71],"classifier-free":[73],"model.":[75],"Additionally,":[76],"contrastive":[78],"language-image":[79],"pretraining":[80],"(CLIP)":[81],"used":[84],"unify":[86],"text":[87],"image":[89],"modalities.":[90],"Extensive":[91],"experimental":[92],"results":[93],"on":[94],"quality":[96],"quantity":[98],"paintings":[104],"confirm":[105],"effectiveness":[107],"combination":[110],"guidance.":[117],"Code":[118],"available":[120],"at":[121],"https://github.com/haha-lisa/MGAD-multimodal-guided-artwork-diffusion.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":8}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}
