{"id":"https://openalex.org/W7116897444","doi":"https://doi.org/10.1109/tvcg.2025.3647628","title":"ArtCrafter: Text-Image Aligning Artistic Attribute Transfer via Embedding Reframing","display_name":"ArtCrafter: Text-Image Aligning Artistic Attribute Transfer via Embedding Reframing","publication_year":2025,"publication_date":"2025-12-23","ids":{"openalex":"https://openalex.org/W7116897444","doi":"https://doi.org/10.1109/tvcg.2025.3647628","pmid":"https://pubmed.ncbi.nlm.nih.gov/41433188"},"language":"en","primary_location":{"id":"doi:10.1109/tvcg.2025.3647628","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2025.3647628","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5081580834","display_name":"Nisha Huang","orcid":"https://orcid.org/0000-0002-1627-6584"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nisha Huang","raw_affiliation_strings":["Tsinghua International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-1627-6584","affiliations":[{"raw_affiliation_string":"Tsinghua International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022860753","display_name":"Kaer Huang","orcid":"https://orcid.org/0009-0003-5728-0058"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaer Huang","raw_affiliation_strings":["Lenovo, Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lenovo, Inc., Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121043341","display_name":"Yifan Pu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Pu","raw_affiliation_strings":["Tsinghua International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-0404-1737","affiliations":[{"raw_affiliation_string":"Tsinghua International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121029865","display_name":"Jiangshan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangshan Wang","raw_affiliation_strings":["Tsinghua International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121066226","display_name":"Jie Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Guo","raw_affiliation_strings":["Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101236085","display_name":"Yiqiang Yan","orcid":"https://orcid.org/0009-0008-7709-0602"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqiang Yan","raw_affiliation_strings":["Lenovo, Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lenovo, Inc., Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051737698","display_name":"Xiu Li","orcid":"https://orcid.org/0009-0006-8822-5280"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiu Li","raw_affiliation_strings":["Tsinghua International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-0403-1923","affiliations":[{"raw_affiliation_string":"Tsinghua International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112345354","display_name":"TONG-YEE LEE","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tong-Yee Lee","raw_affiliation_strings":["National Cheng Kung University, Tainan, Taiwan"],"raw_orcid":"https://orcid.org/0000-0001-6699-2944","affiliations":[{"raw_affiliation_string":"National Cheng Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":0.5076781,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":"7","first_page":"4959","last_page":"4972"},"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":0.9733999967575073,"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":0.9733999967575073,"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/T12650","display_name":"Aesthetic Perception and Analysis","score":0.00570000009611249,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.002199999988079071,"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/embedding","display_name":"Embedding","score":0.6371999979019165},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.5092999935150146},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.47369998693466187},{"id":"https://openalex.org/keywords/cognitive-reframing","display_name":"Cognitive reframing","score":0.46209999918937683},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4449000060558319},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3912000060081482},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.37209999561309814},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3693000078201294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.822700023651123},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6371999979019165},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.5092999935150146},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.47369998693466187},{"id":"https://openalex.org/C187029079","wikidata":"https://www.wikidata.org/wiki/Q958679","display_name":"Cognitive reframing","level":2,"score":0.46209999918937683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4496999979019165},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4449000060558319},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4009999930858612},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.37209999561309814},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3693000078201294},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3481999933719635},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.26489999890327454},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.26170000433921814},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.257099986076355}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tvcg.2025.3647628","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2025.3647628","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},{"id":"pmid:41433188","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41433188","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on visualization and computer graphics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.4056486487388611}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W845365781","https://openalex.org/W1901129140","https://openalex.org/W2145023731","https://openalex.org/W2955639361","https://openalex.org/W2962785568","https://openalex.org/W3167568784","https://openalex.org/W3216352822","https://openalex.org/W4312933868","https://openalex.org/W4385245566","https://openalex.org/W4385805200","https://openalex.org/W4386071613","https://openalex.org/W4386075890","https://openalex.org/W4386076215","https://openalex.org/W4388189411","https://openalex.org/W4390190975","https://openalex.org/W4390692030","https://openalex.org/W4390872905","https://openalex.org/W4390873054","https://openalex.org/W4390873195","https://openalex.org/W4393159527","https://openalex.org/W4400573550","https://openalex.org/W4402667886","https://openalex.org/W4402703076","https://openalex.org/W4402703083","https://openalex.org/W4402716004","https://openalex.org/W4402753498","https://openalex.org/W4402754248","https://openalex.org/W4402816803","https://openalex.org/W4403943792","https://openalex.org/W4404582704","https://openalex.org/W4410719651","https://openalex.org/W4414265888","https://openalex.org/W4415795194","https://openalex.org/W7133183123","https://openalex.org/W7133250524"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2],"witnessed":[3],"significant":[4],"advancements":[5],"in":[6,14,20,94,227],"text-guided":[7],"style":[8,33,67,115],"transfer,":[9,60],"primarily":[10],"attributed":[11],"to":[12,27,55,80,120,144,167,215],"innovations":[13],"diffusion":[15],"models.":[16],"These":[17],"models":[18],"excel":[19],"conditional":[21],"guidance,":[22],"utilizing":[23],"text":[24,172],"or":[25],"images":[26],"direct":[28],"the":[29,63,71,122,138,165,213],"sampling":[30],"process.":[31],"Traditional":[32],"transfer":[34,68,72,106],"focuses":[35],"on":[36],"low-level":[37],"visual":[38,74,228],"features,":[39],"such":[40,85],"as":[41,86],"brushstroke":[42],"textures":[43],"and":[44,47,78,89,171,238],"color":[45,77],"distributions,":[46],"appears":[48],"more":[49,95],"like":[50],"applying":[51],"an":[52,56,101,113,128,195,208],"artistic":[53,104,124,234],"filter":[54],"image.":[57,129],"Artistic":[58],"attribute":[59,105,125,235],"however,":[61],"transcends":[62],"limitations":[64],"of":[65,73,140,233],"traditional":[66],"by":[69],"achieving":[70],"concepts":[75],"from":[76],"brushstrokes":[79],"high":[81],"level":[82],"aesthetic":[83],"attributes":[84],"composition,":[87],"pose,":[88],"key":[90],"semantic":[91],"elements,":[92],"resulting":[93],"natural":[96],"outcomes.":[97],"Therefore,":[98],"we":[99,111,149,193],"propose":[100],"innovative":[102],"text-to-image":[103],"framework":[107],"named":[108],"ArtCrafter.":[109],"Specifically,":[110],"introduce":[112],"attention-based":[114],"extraction":[116],"module,":[117],"meticulously":[118],"engineered":[119],"capture":[121],"subtle":[123],"elements":[126],"within":[127],"This":[130],"module":[131],"features":[132],"a":[133,151,175],"multi-layer":[134],"architecture":[135],"that":[136,157,185,198,222],"leverages":[137],"capabilities":[139],"perceiver":[141],"attention":[142,183],"mechanisms":[143],"integrate":[145],"fine-grained":[146],"information.":[147],"Additionally,":[148],"present":[150],"novel":[152],"text-image":[153],"aligning":[154],"augmentation":[155],"component":[156],"adeptly":[158],"balances":[159],"control":[160],"over":[161],"both":[162],"modalities,":[163],"enabling":[164],"model":[166,214],"efficiently":[168],"map":[169],"image":[170],"embeddings":[173,203,206],"into":[174],"shared":[176],"feature":[177],"space.":[178],"We":[179],"achieve":[180],"this":[181],"through":[182,207],"operations":[184],"enable":[186],"smooth":[187],"information":[188],"flow":[189],"between":[190],"modalities.":[191],"Lastly,":[192],"incorporate":[194],"explicit":[196],"modulation":[197],"seamlessly":[199],"blends":[200],"multimodal":[201],"enhanced":[202],"with":[204],"original":[205],"embedding":[209],"reframing":[210],"design,":[211],"empowering":[212],"generate":[216],"diverse":[217],"outputs.":[218],"Extensive":[219],"experiments":[220],"demonstrate":[221],"ArtCrafter":[223],"yields":[224],"impressive":[225],"results":[226],"stylization,":[229],"exhibiting":[230],"exceptional":[231],"levels":[232],"intensity,":[236],"controllability,":[237],"diversity.":[239]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-12-23T00:00:00"}