{"id":"https://openalex.org/W4408404750","doi":"https://doi.org/10.1007/s11263-025-02371-0","title":"Attribute-Centric Compositional Text-to-Image Generation","display_name":"Attribute-Centric Compositional Text-to-Image Generation","publication_year":2025,"publication_date":"2025-03-13","ids":{"openalex":"https://openalex.org/W4408404750","doi":"https://doi.org/10.1007/s11263-025-02371-0"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-025-02371-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02371-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02371-0.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02371-0.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100622051","display_name":"Yuren Cong","orcid":"https://orcid.org/0000-0001-7505-8563"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yuren Cong","raw_affiliation_strings":["Institute for Information Processing, Leibniz University Hanover, Hanover, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Information Processing, Leibniz University Hanover, Hanover, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065576006","display_name":"Martin Renqiang Min","orcid":"https://orcid.org/0000-0002-8563-6133"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin Renqiang Min","raw_affiliation_strings":["NEC Laboratories America, Princeton, USA"],"affiliations":[{"raw_affiliation_string":"NEC Laboratories America, Princeton, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053710007","display_name":"Li Erran Li","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Erran Li","raw_affiliation_strings":["AWS AI, Amazon, San Francisco, USA"],"affiliations":[{"raw_affiliation_string":"AWS AI, Amazon, San Francisco, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040412734","display_name":"Bodo Rosenhahn","orcid":"https://orcid.org/0000-0003-3861-1424"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bodo Rosenhahn","raw_affiliation_strings":["Institute for Information Processing, Leibniz University Hanover, Hanover, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Information Processing, Leibniz University Hanover, Hanover, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014321482","display_name":"Michael Ying Yang","orcid":"https://orcid.org/0000-0002-0649-9987"},"institutions":[{"id":"https://openalex.org/I51601045","display_name":"University of Bath","ror":"https://ror.org/002h8g185","country_code":"GB","type":"education","lineage":["https://openalex.org/I51601045"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Michael Ying Yang","raw_affiliation_strings":["Visual Computing Group, University of Bath, Bath, England"],"affiliations":[{"raw_affiliation_string":"Visual Computing Group, University of Bath, Bath, England","institution_ids":["https://openalex.org/I51601045"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100622051"],"corresponding_institution_ids":[],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":{"value":2890,"currency":"EUR","value_usd":3690},"fwci":3.9571,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.92883868,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"133","issue":"7","first_page":"4555","last_page":"4570"},"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":0.9958999752998352,"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":0.9958999752998352,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9908000230789185,"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":0.9898999929428101,"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/computer-science","display_name":"Computer science","score":0.61316978931427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5669187903404236},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5296242833137512},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5281602740287781},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.4455220103263855},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37873080372810364},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3483653962612152},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34565508365631104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.61316978931427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5669187903404236},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5296242833137512},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5281602740287781},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.4455220103263855},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37873080372810364},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3483653962612152},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34565508365631104}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11263-025-02371-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02371-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02371-0.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11263-025-02371-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02371-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02371-0.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G976325612","display_name":null,"funder_award_id":"101136006","funder_id":"https://openalex.org/F4320334322","funder_display_name":"HORIZON EUROPE Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4408404750.pdf"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W2398118205","https://openalex.org/W2612690371","https://openalex.org/W2911293880","https://openalex.org/W2962770929","https://openalex.org/W2962845008","https://openalex.org/W2963413689","https://openalex.org/W2963612019","https://openalex.org/W2963966654","https://openalex.org/W2963981733","https://openalex.org/W2965289598","https://openalex.org/W2966792645","https://openalex.org/W2990138404","https://openalex.org/W3029699545","https://openalex.org/W3034521057","https://openalex.org/W3034667500","https://openalex.org/W3035500781","https://openalex.org/W3035574324","https://openalex.org/W3135367836","https://openalex.org/W3141117710","https://openalex.org/W3165647589","https://openalex.org/W3174194560","https://openalex.org/W3174525637","https://openalex.org/W3176641147","https://openalex.org/W3207865986","https://openalex.org/W3207932648","https://openalex.org/W3212516020","https://openalex.org/W3214066627","https://openalex.org/W3215495615","https://openalex.org/W4214485011","https://openalex.org/W4283805041","https://openalex.org/W4298054444","https://openalex.org/W4312282373","https://openalex.org/W4312388283","https://openalex.org/W4312438583","https://openalex.org/W4312554034","https://openalex.org/W4312824283","https://openalex.org/W4312911498","https://openalex.org/W4312933868","https://openalex.org/W4312974539","https://openalex.org/W4312977351","https://openalex.org/W4313186669","https://openalex.org/W6638319203","https://openalex.org/W6767384525","https://openalex.org/W6790978476","https://openalex.org/W6799822499"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2779427294","https://openalex.org/W2775347418","https://openalex.org/W2625805835","https://openalex.org/W2079911747","https://openalex.org/W3116076068","https://openalex.org/W3003936178","https://openalex.org/W2145652935","https://openalex.org/W2563206327","https://openalex.org/W2069885731"],"abstract_inverted_index":{"Abstract":[0],"Despite":[1],"the":[2,15,92,101],"recent":[3],"impressive":[4],"breakthroughs":[5],"in":[6,13,114],"text-to-image":[7,47],"generation,":[8],"generative":[9],"models":[10,127],"have":[11],"difficulty":[12],"capturing":[14],"data":[16],"distribution":[17],"of":[18,104,116],"underrepresented":[19,71],"attribute":[20,25,85],"compositions":[21],"while":[22],"over-memorizing":[23],"overrepresented":[24,84],"compositions,":[26],"which":[27,62],"raises":[28],"public":[29],"concerns":[30],"about":[31],"their":[32],"robustness":[33],"and":[34,56,94,108,119,125],"fairness.":[35],"To":[36],"tackle":[37],"this":[38],"challenge,":[39],"we":[40],"propose":[41,75],"ACTIG":[42,105],",":[43],"an":[44,52,76],"attribute-centric":[45,53,77],"compositional":[46,102],"generation":[48],"framework.":[49],"We":[50,73,87],"present":[51],"feature":[54],"augmentation":[55],"a":[57],"novel":[58],"image-free":[59],"training":[60],"scheme,":[61],"greatly":[63],"improves":[64],"model\u2019s":[65],"ability":[66],"to":[67,80,83],"generate":[68],"images":[69],"with":[70],"attributes.":[72],"further":[74],"contrastive":[78],"loss":[79],"avoid":[81],"overfitting":[82],"compositions.":[86],"validate":[88],"our":[89,109],"framework":[90,110],"on":[91],"CelebA-HQ":[93],"CUB":[95],"datasets.":[96],"Extensive":[97],"experiments":[98],"show":[99],"that":[100],"generalization":[103],"is":[106],"outstanding,":[107],"outperforms":[111],"previous":[112],"works":[113],"terms":[115],"image":[117],"quality":[118],"text-image":[120],"consistency.":[121],"The":[122],"source":[123],"code":[124],"trained":[126],"are":[128],"publicly":[129],"available":[130],"at":[131],"https://github.com/yrcong/ACTIG":[132],".":[133]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}