{"id":"https://openalex.org/W4416554283","doi":"https://doi.org/10.1109/iccv51701.2025.01879","title":"ROVI: A VLM-LLM Re-Captioned Dataset for Open-Vocabulary Instance-Grounded Text-to-Image Generation","display_name":"ROVI: A VLM-LLM Re-Captioned Dataset for Open-Vocabulary Instance-Grounded Text-to-Image Generation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416554283","doi":"https://doi.org/10.1109/iccv51701.2025.01879"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01879","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01879","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.01008","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5105630882","display_name":"C. C. Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156066","display_name":"State Key Laboratory of Chemical Engineering","ror":"https://ror.org/05803vc71","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210156066"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Cihang Peng","raw_affiliation_strings":["State Key Lab of CAD & CG, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of CAD & CG, Zhejiang University","institution_ids":["https://openalex.org/I76130692","https://openalex.org/I4210156066"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113384605","display_name":"Qiming Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156066","display_name":"State Key Laboratory of Chemical Engineering","ror":"https://ror.org/05803vc71","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210156066"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiming Hou","raw_affiliation_strings":["State Key Lab of CAD & CG, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of CAD & CG, Zhejiang University","institution_ids":["https://openalex.org/I76130692","https://openalex.org/I4210156066"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102871117","display_name":"Zhong Ren","orcid":"https://orcid.org/0000-0002-6798-3035"},"institutions":[{"id":"https://openalex.org/I4210156066","display_name":"State Key Laboratory of Chemical Engineering","ror":"https://ror.org/05803vc71","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210156066"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong Ren","raw_affiliation_strings":["State Key Lab of CAD & CG, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of CAD & CG, Zhejiang University","institution_ids":["https://openalex.org/I76130692","https://openalex.org/I4210156066"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085836453","display_name":"Kun Zhou","orcid":"https://orcid.org/0000-0003-0623-2825"},"institutions":[{"id":"https://openalex.org/I4210156066","display_name":"State Key Laboratory of Chemical Engineering","ror":"https://ror.org/05803vc71","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210156066"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Zhou","raw_affiliation_strings":["State Key Lab of CAD & CG, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of CAD & CG, Zhejiang University","institution_ids":["https://openalex.org/I76130692","https://openalex.org/I4210156066"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5105630882"],"corresponding_institution_ids":["https://openalex.org/I4210156066","https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33709161,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20204","last_page":"20214"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9282000064849854,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9282000064849854,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.02800000086426735,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.007499999832361937,"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/pipeline","display_name":"Pipeline (software)","score":0.7702999711036682},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5615000128746033},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5024999976158142},{"id":"https://openalex.org/keywords/visual-inspection","display_name":"Visual inspection","score":0.4431999921798706},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.38940000534057617},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.3587000072002411},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3483000099658966},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.326200008392334}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7702999711036682},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7290999889373779},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6280999779701233},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5615000128746033},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5024999976158142},{"id":"https://openalex.org/C168820333","wikidata":"https://www.wikidata.org/wiki/Q448889","display_name":"Visual inspection","level":2,"score":0.4431999921798706},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.38940000534057617},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35740000009536743},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3547999858856201},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31709998846054077},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31119999289512634},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28769999742507935},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.27399998903274536},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25850000977516174}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01879","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01879","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.01008","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.01008","pdf_url":"https://arxiv.org/pdf/2508.01008","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2508.01008","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.01008","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.01008","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.01008","pdf_url":"https://arxiv.org/pdf/2508.01008","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"ROVI,":[2],"a":[3,22,32,52,67,111],"high-quality":[4],"synthetic":[5],"dataset":[6,132],"for":[7,58],"instance-grounded":[8],"text-to-image":[9,112],"generation,":[10],"created":[11],"by":[12,44],"labeling":[13],"1M":[14],"curated":[15],"web":[16],"images.":[17],"Our":[18,131],"key":[19],"innovation":[20],"is":[21],"strategy":[23],"called":[24],"re-captioning,":[25],"focusing":[26],"on":[27,116],"the":[28],"pre-detection":[29],"stage,":[30],"where":[31],"VLM":[33],"(Vision-Language":[34],"Model)":[35,49],"generates":[36],"comprehensive":[37],"visual":[38,78],"descriptions":[39],"that":[40,85],"are":[41,136],"then":[42],"processed":[43],"an":[45,105],"LLM":[46],"(Large":[47],"Language":[48],"to":[50,62,72],"extract":[51],"flat":[53],"list":[54],"of":[55,100],"potential":[56],"categories":[57,103],"OVDs":[59],"(Open-Vocabulary":[60],"Detectors)":[61],"detect.":[63],"This":[64],"approach":[65],"yields":[66],"global":[68],"prompt":[69,126],"inherently":[70],"linked":[71],"instance":[73,123],"annotations":[74],"while":[75,96],"capturing":[76],"secondary":[77],"elements":[79],"humans":[80],"typically":[81],"overlook.":[82],"Evaluations":[83],"show":[84],"ROVI":[86,117],"exceeds":[87],"existing":[88],"detection":[89],"datasets":[90],"in":[91,122],"image":[92],"quality":[93],"and":[94,128,133],"resolution":[95],"containing":[97],"two":[98],"orders":[99],"magnitude":[101],"more":[102],"with":[104],"open-vocabulary":[106],"nature.":[107],"For":[108],"demonstrative":[109],"purposes,":[110],"model":[113],"GLIGEN":[114],"trained":[115],"significantly":[118],"outperforms":[119],"state-of-the-art":[120],"alternatives":[121],"grounding":[124],"accuracy,":[125],"fidelity,":[127],"aesthetic":[129],"quality.":[130],"reproducible":[134],"pipeline":[135],"available":[137],"at":[138],"https://github.com/CihangPeng/ROVI.":[139]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}