{"id":"https://openalex.org/W7139055393","doi":"https://doi.org/10.5220/0014417600004084","title":"From Captions to Queries: A VLM Pipeline for Queryable Metadata in Synthetic Environments","display_name":"From Captions to Queries: A VLM Pipeline for Queryable Metadata in Synthetic Environments","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7139055393","doi":"https://doi.org/10.5220/0014417600004084"},"language":null,"primary_location":{"id":"doi:10.5220/0014417600004084","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0014417600004084","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computer Vision Theory and Applications","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0014417600004084","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102022677","display_name":"Christopher May","orcid":"https://orcid.org/0009-0003-2571-3461"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Christopher May","raw_affiliation_strings":["Institute for Factory Automation and Production Systems (FAPS), Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Egerlandstr. 7-9, 91058 Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Factory Automation and Production Systems (FAPS), Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Egerlandstr. 7-9, 91058 Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130087322","display_name":"Abhijith Shaji","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Abhijith Shaji","raw_affiliation_strings":["Institute for Factory Automation and Production Systems (FAPS), Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Egerlandstr. 7-9, 91058 Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Factory Automation and Production Systems (FAPS), Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Egerlandstr. 7-9, 91058 Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130125413","display_name":"J\u00f6rg Franke","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J\u00f6rg Franke","raw_affiliation_strings":["Institute for Factory Automation and Production Systems (FAPS), Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Egerlandstr. 7-9, 91058 Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Factory Automation and Production Systems (FAPS), Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Egerlandstr. 7-9, 91058 Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130029121","display_name":"Sebastian Reitelsh\u00f6fer","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Reitelsh\u00f6fer","raw_affiliation_strings":["Institute for Factory Automation and Production Systems (FAPS), Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Egerlandstr. 7-9, 91058 Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Factory Automation and Production Systems (FAPS), Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Egerlandstr. 7-9, 91058 Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102022677"],"corresponding_institution_ids":["https://openalex.org/I181369854"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94060172,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"538","last_page":"547"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.3375000059604645,"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"}},"topics":[{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.3375000059604645,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.08760000020265579,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12031","display_name":"Speech and dialogue systems","score":0.05649999901652336,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5877000093460083},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5547999739646912},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.3285999894142151},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.27950000762939453},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.26899999380111694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6305000185966492},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5877000093460083},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5547999739646912},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.42480000853538513},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.388700008392334},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3603000044822693},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.29190000891685486},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2648000121116638},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5220/0014417600004084","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0014417600004084","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computer Vision Theory and Applications","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.5220/0014417600004084","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0014417600004084","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computer Vision Theory and Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4227633476257324,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-03-20T20:54:20.808490","created_date":"2026-03-20T00:00:00"}
