{"id":"https://openalex.org/W7125648395","doi":"https://doi.org/10.1016/j.patcog.2026.113158","title":"S2I-DiT: Unlocking the semantic-to-image transferability by fine-tuning large diffusion transformer models","display_name":"S2I-DiT: Unlocking the semantic-to-image transferability by fine-tuning large diffusion transformer models","publication_year":2026,"publication_date":"2026-01-25","ids":{"openalex":"https://openalex.org/W7125648395","doi":"https://doi.org/10.1016/j.patcog.2026.113158"},"language":"en","primary_location":{"id":"doi:10.1016/j.patcog.2026.113158","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.patcog.2026.113158","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition","raw_type":"journal-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/A5123815084","display_name":"Gang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN","SE"],"is_corresponding":false,"raw_author_name":"Gang Li","raw_affiliation_strings":["Huawei Noah\u2019s Ark Lab, Hong Kong, 999077, China","Institute of Software, Chinese Academy of Science, Beijing, 101408, China","University of Chinese Academy of Sciences, Beijing, 101408, China"],"raw_orcid":"https://orcid.org/0000-0001-9520-0141","affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Lab, Hong Kong, 999077, China","institution_ids":["https://openalex.org/I4210159102"]},{"raw_affiliation_string":"Institute of Software, Chinese Academy of Science, Beijing, 101408, China","institution_ids":["https://openalex.org/I4210128818"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, 101408, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Enze Xie","orcid":"https://orcid.org/0000-0001-6890-1049"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Enze Xie","raw_affiliation_strings":["Huawei Noah\u2019s Ark Lab, Hong Kong, 999077, China"],"raw_orcid":"https://orcid.org/0000-0001-6890-1049","affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Lab, Hong Kong, 999077, China","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chongjian Ge","orcid":"https://orcid.org/0000-0003-2746-2216"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chongjian Ge","raw_affiliation_strings":["The University of Hong Kong, Hong Kong, 999077, China"],"raw_orcid":"https://orcid.org/0000-0003-2746-2216","affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong, 999077, China","institution_ids":["https://openalex.org/I177725633","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123785399","display_name":"Xiang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]},{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["CN","SE"],"is_corresponding":false,"raw_author_name":"Xiang Li","raw_affiliation_strings":["Huawei Noah\u2019s Ark Lab, Hong Kong, 999077, China","Nankai University, Tianjin, 300071, China"],"raw_orcid":"https://orcid.org/0000-0002-4996-7365","affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Lab, Hong Kong, 999077, China","institution_ids":["https://openalex.org/I4210159102"]},{"raw_affiliation_string":"Nankai University, Tianjin, 300071, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123811581","display_name":"Lingyu Si","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingyu Si","raw_affiliation_strings":["Institute of Software, Chinese Academy of Science, Beijing, 101408, China"],"raw_orcid":"https://orcid.org/0000-0002-7735-6676","affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Science, Beijing, 101408, China","institution_ids":["https://openalex.org/I4210128818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123816485","display_name":"Changwen Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changwen Zheng","raw_affiliation_strings":["Institute of Software, Chinese Academy of Science, Beijing, 101408, China","University of Chinese Academy of Sciences, Beijing, 101408, China"],"raw_orcid":"https://orcid.org/0000-0002-2311-6757","affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Science, Beijing, 101408, China","institution_ids":["https://openalex.org/I4210128818"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, 101408, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079358572","display_name":"Z. Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Zhenguo Li","raw_affiliation_strings":["Huawei Noah\u2019s Ark Lab, Hong Kong, 999077, China"],"raw_orcid":"https://orcid.org/0000-0002-8492-3069","affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Lab, Hong Kong, 999077, China","institution_ids":["https://openalex.org/I4210159102"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2710,"currency":"USD","value_usd":2710},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08623722,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"176","issue":null,"first_page":"113158","last_page":"113158"},"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":0.745199978351593,"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":0.745199978351593,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.03220000118017197,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11019","display_name":"Image Enhancement Techniques","score":0.025499999523162842,"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/transferability","display_name":"Transferability","score":0.7469000220298767},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5920000076293945},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.564300000667572},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5404000282287598},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.3686000108718872},{"id":"https://openalex.org/keywords/de-facto","display_name":"De facto","score":0.34150001406669617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.776199996471405},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.7469000220298767},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5920000076293945},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.564300000667572},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5404000282287598},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.448199987411499},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3831000030040741},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35429999232292175},{"id":"https://openalex.org/C2992317946","wikidata":"https://www.wikidata.org/wiki/Q712144","display_name":"De facto","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34130001068115234},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3206000030040741},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28850001096725464},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.patcog.2026.113158","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.patcog.2026.113158","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pattern Recognition","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2117539524","https://openalex.org/W4297322797","https://openalex.org/W4364355572","https://openalex.org/W4400799775","https://openalex.org/W4404626758"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2026-01-26T00:00:00"}
