{"id":"https://openalex.org/W7137802032","doi":"https://doi.org/10.1609/aaai.v40i4.37255","title":"Multivariate Diffusion Transformer with Decoupled Attention for High-Fidelity Mask-Text Collaborative Facial Generation","display_name":"Multivariate Diffusion Transformer with Decoupled Attention for High-Fidelity Mask-Text Collaborative Facial Generation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137802032","doi":"https://doi.org/10.1609/aaai.v40i4.37255"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i4.37255","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37255","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.v40i4.37255","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129737296","display_name":"Yushe Cao","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":true,"raw_author_name":"Yushe Cao","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128181832","display_name":"Dianxi Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dianxi Shi","raw_affiliation_strings":["Intelligent Game and Decision Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129694987","display_name":"Xing Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xing Fu","raw_affiliation_strings":["Ant Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035082721","display_name":"Xuechao Zou","orcid":"https://orcid.org/0000-0002-3743-7738"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuechao Zou","raw_affiliation_strings":["Beijing Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129706371","display_name":"Haikuo Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haikuo Peng","raw_affiliation_strings":["National University of Defense Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100453919","display_name":"Xueqi Li","orcid":"https://orcid.org/0000-0001-6396-0058"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xueqi Li","raw_affiliation_strings":["Intelligent Game and Decision Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129723783","display_name":"Chun Yu","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":"Chun Yu","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129742465","display_name":"Junliang Xing","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":"Junliang Xing","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5129737296"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01430615,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"4","first_page":"2670","last_page":"2679"},"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":0.782800018787384,"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":0.782800018787384,"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/T11448","display_name":"Face recognition and analysis","score":0.08609999716281891,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.024299999698996544,"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/transformer","display_name":"Transformer","score":0.47769999504089355},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.39559999108314514},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.3950999975204468},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.39320001006126404},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.36880001425743103},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.3490000069141388},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3393000066280365},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.33889999985694885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7854999899864197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5483999848365784},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.47769999504089355},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.39559999108314514},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.3950999975204468},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.39320001006126404},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.36880001425743103},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.30169999599456787},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28360000252723694},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.25589999556541443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i4.37255","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37255","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"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i4.37255","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37255","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"significant":[1],"progress":[2],"has":[3],"been":[4],"achieved":[5],"in":[6,117,148],"multimodal":[7,67],"facial":[8,152],"generation":[9,31],"using":[10],"semantic":[11,52],"masks":[12],"and":[13,54,97,107,112,154],"textual":[14],"descriptions,":[15],"conventional":[16],"feature":[17,68],"fusion":[18],"approaches":[19],"often":[20],"fail":[21],"to":[22,29,50],"enable":[23],"effective":[24],"cross-modal":[25],"interactions,":[26],"thereby":[27,123],"leading":[28],"suboptimal":[30],"outcomes.":[32],"To":[33],"address":[34],"this":[35],"challenge,":[36],"we":[37,83],"introduce":[38],"MDiTFace\u2014a":[39],"customized":[40],"diffusion":[41],"transformer":[42,75],"framework":[43,64],"that":[44,77,141],"employs":[45],"a":[46,85],"unified":[47],"tokenization":[48],"strategy":[49],"process":[51,78],"mask":[53,95,130],"text":[55],"inputs,":[56],"eliminating":[57],"discrepancies":[58],"between":[59,94],"heterogeneous":[60],"modality":[61],"representations.":[62],"The":[63],"facilitates":[65],"comprehensive":[66],"interaction":[69],"through":[70],"stacked,":[71],"newly":[72],"designed":[73],"multivariate":[74],"blocks":[76],"all":[79],"conditions":[80],"synchronously.":[81],"Additionally,":[82],"design":[84],"novel":[86],"decoupled":[87],"attention":[88],"mechanism":[89,101],"by":[90,129,132],"dissociating":[91],"implicit":[92],"dependencies":[93],"tokens":[96],"temporal":[98],"embeddings.":[99],"This":[100],"segregates":[102],"internal":[103],"computations":[104],"into":[105],"dynamic":[106],"static":[108,118],"pathways,":[109],"enabling":[110],"caching":[111],"reuse":[113],"of":[114,150],"features":[115],"computed":[116],"pathways":[119],"after":[120],"initial":[121],"calculation,":[122],"reducing":[124],"additional":[125],"computational":[126],"overhead":[127],"introduced":[128],"condition":[131],"over":[133],"94%":[134],"while":[135],"maintaining":[136],"performance.":[137],"Extensive":[138],"experiments":[139],"demonstrate":[140],"MDiTFace":[142],"significantly":[143],"outperforms":[144],"other":[145],"competing":[146],"methods":[147],"terms":[149],"both":[151],"fidelity":[153],"conditional":[155],"consistency.":[156]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-18T00:00:00"}