{"id":"https://openalex.org/W7126060464","doi":"https://doi.org/10.1016/j.imavis.2026.105923","title":"Object-level semantic alignment for enhancing fidelity in text-to-image generation with diffusion models","display_name":"Object-level semantic alignment for enhancing fidelity in text-to-image generation with diffusion models","publication_year":2026,"publication_date":"2026-01-29","ids":{"openalex":"https://openalex.org/W7126060464","doi":"https://doi.org/10.1016/j.imavis.2026.105923"},"language":"en","primary_location":{"id":"doi:10.1016/j.imavis.2026.105923","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.imavis.2026.105923","pdf_url":null,"source":{"id":"https://openalex.org/S177430994","display_name":"Image and Vision Computing","issn_l":"0262-8856","issn":["0262-8856","1872-8138"],"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":"Image and Vision Computing","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/A5121577113","display_name":"Wenna Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I143413998","display_name":"Qingdao University of Science and Technology","ror":"https://ror.org/041j8js14","country_code":"CN","type":"education","lineage":["https://openalex.org/I143413998"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenna Liu","raw_affiliation_strings":["College of Automation and Electronic Engineering, Qingdao University of Science and Technology, Qingdao Shandong 266061, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Automation and Electronic Engineering, Qingdao University of Science and Technology, Qingdao Shandong 266061, China","institution_ids":["https://openalex.org/I143413998"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121531484","display_name":"Na Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I143413998","display_name":"Qingdao University of Science and Technology","ror":"https://ror.org/041j8js14","country_code":"CN","type":"education","lineage":["https://openalex.org/I143413998"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Na Tian","raw_affiliation_strings":["College of Automation and Electronic Engineering, Qingdao University of Science and Technology, Qingdao Shandong 266061, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Automation and Electronic Engineering, Qingdao University of Science and Technology, Qingdao Shandong 266061, China","institution_ids":["https://openalex.org/I143413998"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036263965","display_name":"Youjia Shao","orcid":"https://orcid.org/0000-0003-4981-9247"},"institutions":[{"id":"https://openalex.org/I143413998","display_name":"Qingdao University of Science and Technology","ror":"https://ror.org/041j8js14","country_code":"CN","type":"education","lineage":["https://openalex.org/I143413998"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youjia Shao","raw_affiliation_strings":["College of Automation and Electronic Engineering, Qingdao University of Science and Technology, Qingdao Shandong 266061, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Automation and Electronic Engineering, Qingdao University of Science and Technology, Qingdao Shandong 266061, China","institution_ids":["https://openalex.org/I143413998"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102927959","display_name":"Wencang Zhao","orcid":"https://orcid.org/0000-0002-4420-3825"},"institutions":[{"id":"https://openalex.org/I143413998","display_name":"Qingdao University of Science and Technology","ror":"https://ror.org/041j8js14","country_code":"CN","type":"education","lineage":["https://openalex.org/I143413998"]},{"id":"https://openalex.org/I4210109160","display_name":"Institute of Space Sciences","ror":null,"country_code":"ES","type":null,"lineage":["https://openalex.org/I4210109160"]}],"countries":["CN","ES"],"is_corresponding":true,"raw_author_name":"Wencang Zhao","raw_affiliation_strings":["College of Automation and Electronic Engineering, Qingdao University of Science and Technology, Qingdao Shandong 266061, China","Qingdao Institute of Intelligent Navigation and Control, Qingdao Shandong 266071, China","Shandong Key Laboratory of Autonomous Landing for Deep Space Exploration, Qingdao Shandong 266061, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Automation and Electronic Engineering, Qingdao University of Science and Technology, Qingdao Shandong 266061, China","institution_ids":["https://openalex.org/I143413998"]},{"raw_affiliation_string":"Qingdao Institute of Intelligent Navigation and Control, Qingdao Shandong 266071, China","institution_ids":[]},{"raw_affiliation_string":"Shandong Key Laboratory of Autonomous Landing for Deep Space Exploration, Qingdao Shandong 266061, China","institution_ids":["https://openalex.org/I4210109160"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102927959"],"corresponding_institution_ids":["https://openalex.org/I143413998","https://openalex.org/I4210109160"],"apc_list":{"value":2270,"currency":"USD","value_usd":2270},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15794823,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"167","issue":null,"first_page":"105923","last_page":"105923"},"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":0.8525999784469604,"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":0.8525999784469604,"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":0.05939999967813492,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.005200000014156103,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7907000184059143},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7091000080108643},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5196999907493591},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4916999936103821},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4535999894142151},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4390999972820282},{"id":"https://openalex.org/keywords/semantic-matching","display_name":"Semantic matching","score":0.39579999446868896},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.3537999987602234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8565000295639038},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7907000184059143},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7091000080108643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6144999861717224},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5196999907493591},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4916999936103821},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.486299991607666},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4535999894142151},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4390999972820282},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.39579999446868896},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3537999987602234},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3346000015735626},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2856999933719635},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2833000123500824},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.2824999988079071},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2653999924659729}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.imavis.2026.105923","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.imavis.2026.105923","pdf_url":null,"source":{"id":"https://openalex.org/S177430994","display_name":"Image and Vision Computing","issn_l":"0262-8856","issn":["0262-8856","1872-8138"],"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":"Image and Vision Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.4452720284461975,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2948978827","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W2985068832","https://openalex.org/W3035574324","https://openalex.org/W4285981780","https://openalex.org/W4312933868","https://openalex.org/W4385270985","https://openalex.org/W4386072096","https://openalex.org/W4390874566","https://openalex.org/W4399034461","https://openalex.org/W4399914133","https://openalex.org/W4401505917","https://openalex.org/W4402290942","https://openalex.org/W4403289620","https://openalex.org/W4404635257","https://openalex.org/W4407954321"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2026-01-30T00:00:00"}
