{"id":"https://openalex.org/W4405030479","doi":"https://doi.org/10.1109/wacv61042.2026.00617","title":"QUOTA: Quantifying Objects with Text-to-Image Models for Any Domain","display_name":"QUOTA: Quantifying Objects with Text-to-Image Models for Any Domain","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4405030479","doi":"https://doi.org/10.1109/wacv61042.2026.00617"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00617","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.19534","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102866876","display_name":"Wenfang Sun","orcid":"https://orcid.org/0009-0006-5929-8819"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Wenfang Sun","raw_affiliation_strings":["University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110365747","display_name":"Yingjun Du","orcid":null},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Yingjun Du","raw_affiliation_strings":["University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102946362","display_name":"Gaowen Liu","orcid":"https://orcid.org/0000-0002-6520-5547"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gaowen Liu","raw_affiliation_strings":["Cisco Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cisco Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yefeng Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yefeng Zheng","raw_affiliation_strings":["Westlake University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Westlake University","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"last","author":{"id":null,"display_name":"Cees G. M. Snoek","orcid":null},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Cees G. M. Snoek","raw_affiliation_strings":["University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6381","last_page":"6390"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9731000065803528,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9731000065803528,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9200000166893005,"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":0.9171000123023987,"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/image","display_name":"Image (mathematics)","score":0.6464080810546875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5812461972236633},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5526762008666992},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40695980191230774},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3614886999130249},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.255110502243042},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.05941513180732727}],"concepts":[{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6464080810546875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5812461972236633},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5526762008666992},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40695980191230774},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3614886999130249},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.255110502243042},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.05941513180732727}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00617","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2411.19534","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.19534","pdf_url":"https://arxiv.org/pdf/2411.19534","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.19534","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.19534","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.19534","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.19534","pdf_url":"https://arxiv.org/pdf/2411.19534","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"We":[0,49],"tackle":[1],"the":[2,6,39],"problem":[3,44],"of":[4,8,26,125],"quantifying":[5],"number":[7],"objects":[9],"by":[10,80],"a":[11,19,46,70,76,110,154],"generative":[12],"text-to-image":[13,56,135,161],"model.":[14],"Rather":[15],"than":[16],"retraining":[17],"such":[18],"model":[20],"for":[21,55,99,116,157,163],"each":[22],"new":[23,111,155],"image":[24],"domain":[25,88,120],"interest,":[27],"which":[28],"leads":[29],"to":[30,41,74],"high":[31],"computational":[32],"costs":[33],"and":[34,87,95,129,150,159],"limited":[35],"scalability,":[36],"we":[37,108],"are":[38],"first":[40],"consider":[42],"this":[43],"from":[45],"domain-agnostic":[47],"perspective.":[48],"propose":[50],"QUOTA,":[51],"an":[52],"optimization":[53],"framework":[54],"models":[57,144],"that":[58,140],"enables":[59],"effective":[60],"object":[61,100,117,126,147],"quantification":[62,118,127,148],"across":[63,131],"unseen":[64,132],"domains":[65,133],"without":[66],"retraining.":[67],"It":[68],"leverages":[69],"dual-loop":[71],"meta-learning":[72],"strategy":[73],"optimize":[75],"domain-invariant":[77],"prompt.":[78],"Further,":[79],"integrating":[81],"prompt":[82],"learning":[83],"with":[84],"learnable":[85],"counting":[86],"tokens,":[89],"our":[90],"method":[91],"captures":[92],"stylistic":[93],"variations":[94],"maintains":[96],"accuracy,":[97],"even":[98],"classes":[101],"not":[102],"encountered":[103],"during":[104],"training.":[105],"For":[106],"evaluation,":[107],"adopt":[109],"benchmark":[112,156],"QUANT-Bench":[113],"specifically":[114],"designed":[115],"in":[119,134,145],"generalization,":[121],"enabling":[122],"rigorous":[123],"assessment":[124],"accuracy":[128,149],"adaptability":[130],"generation.":[136],"Extensive":[137],"experiments":[138],"demonstrate":[139],"QUOTA":[141],"outperforms":[142],"conventional":[143],"both":[146],"semantic":[151],"consistency,":[152],"setting":[153],"efficient":[158],"scalable":[160],"generation":[162],"any":[164],"domain.":[165]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}