{"id":"https://openalex.org/W4408355890","doi":"https://doi.org/10.1109/icassp49660.2025.10888654","title":"Dual-Modality Guided Artistic Style Transfer with Pre-trained Diffusion Models","display_name":"Dual-Modality Guided Artistic Style Transfer with Pre-trained Diffusion Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355890","doi":"https://doi.org/10.1109/icassp49660.2025.10888654"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888654","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888654","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5111346994","display_name":"Jiaxiong Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxiong Liu","raw_affiliation_strings":["Southwest University,College of Computer and Information Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest University,College of Computer and Information Science,China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101363220","display_name":"Xiaolong Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolong Xiong","raw_affiliation_strings":["Southwest University,College of Computer and Information Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest University,College of Computer and Information Science,China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063215334","display_name":"Jun Zhou","orcid":"https://orcid.org/0000-0003-4353-1621"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Zhou","raw_affiliation_strings":["Southwest University,College of Computer and Information Science,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest University,College of Computer and Information Science,China","institution_ids":["https://openalex.org/I142108993"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.03063511,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9936000108718872,"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":0.9936000108718872,"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/T11309","display_name":"Music and Audio Processing","score":0.9434000253677368,"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"}},{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9273999929428101,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7563233375549316},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6863035559654236},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6169463992118835},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.6121436953544617},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5072557330131531},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.46641337871551514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3580489754676819},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3447378873825073},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.09550735354423523},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.08941057324409485},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07635340094566345},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.06462568044662476}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7563233375549316},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6863035559654236},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6169463992118835},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6121436953544617},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5072557330131531},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.46641337871551514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3580489754676819},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3447378873825073},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.09550735354423523},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.08941057324409485},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07635340094566345},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.06462568044662476},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"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:10.1109/icassp49660.2025.10888654","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888654","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1982471090","https://openalex.org/W2017897462","https://openalex.org/W3202767484","https://openalex.org/W3216156094","https://openalex.org/W4304098884","https://openalex.org/W4312933868","https://openalex.org/W4386071613","https://openalex.org/W4386076532","https://openalex.org/W4390871856","https://openalex.org/W4390872351","https://openalex.org/W4390872387","https://openalex.org/W4390873539","https://openalex.org/W4390874199","https://openalex.org/W4393159527","https://openalex.org/W4402667886","https://openalex.org/W4404984122","https://openalex.org/W4412352576","https://openalex.org/W6791353385","https://openalex.org/W6795288823","https://openalex.org/W6810940779","https://openalex.org/W6840815571","https://openalex.org/W6841366371","https://openalex.org/W6843978401","https://openalex.org/W6849286980","https://openalex.org/W6860729961"],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2530972254","https://openalex.org/W2356229341","https://openalex.org/W2374013449","https://openalex.org/W73545470","https://openalex.org/W2349768204","https://openalex.org/W2364381299","https://openalex.org/W2374430585","https://openalex.org/W3144423903","https://openalex.org/W2377397762"],"abstract_inverted_index":{"Artistic":[0,59],"style":[1,9,40,113,130],"transfer":[2],"aims":[3],"to":[4,72,106,123],"replicate":[5],"an":[6,108],"artist\u2019s":[7],"painting":[8],"in":[10,137],"a":[11],"different":[12],"image.":[13],"While":[14],"existing":[15,135],"pre-trained":[16],"model-based":[17],"methods":[18],"can":[19],"generate":[20],"high-quality":[21],"stylized":[22,81],"images,":[23],"they":[24],"often":[25],"lack":[26],"precise":[27],"control":[28,122],"over":[29],"stylistic":[30],"elements.":[31],"Recent":[32],"approaches":[33],"incorporating":[34],"textual":[35],"inversion":[36,119],"offer":[37],"more":[38,111],"accurate":[39,125],"representations,":[41],"but":[42],"significant":[43],"information":[44,71,102],"loss":[45],"occurs":[46],"when":[47],"transitioning":[48],"between":[49],"modalities.":[50],"To":[51],"address":[52],"these":[53],"issues,":[54],"we":[55],"propose":[56],"Dual-Modality":[57],"Guided":[58,96],"Style":[60,92],"Transfer":[61],"(DMG),":[62],"which":[63],"makes":[64],"full":[65],"use":[66],"of":[67,80,87,127,139],"text":[68],"and":[69,77,95,110,120,129,142],"image":[70],"enhance":[73],"the":[74],"visual":[75,140],"effect":[76],"content":[78,128,143],"consistency":[79],"results.":[82],"Our":[83,132],"approach":[84,133],"primarily":[85],"consists":[86],"two":[88],"key":[89],"modules:":[90],"Enhanced":[91],"Encoding":[93],"(ESE)":[94],"Diffusion":[97],"Generation":[98],"(GDG).":[99],"ESE":[100],"processes":[101],"from":[103],"both":[104],"modalities":[105],"obtain":[107],"optimized":[109],"comprehensive":[112],"representation.":[114],"Subsequently,":[115],"GDG":[116],"employs":[117],"stochastic":[118],"attention":[121],"ensure":[124],"delivery":[126],"information.":[131],"outperforms":[134],"techniques":[136],"terms":[138],"quality":[141],"consistency.":[144]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}