{"id":"https://openalex.org/W7131118729","doi":"https://doi.org/10.1109/iccvw69036.2025.00718","title":"Synthetic Captions for Open-Vocabulary Zero-Shot Segmentation","display_name":"Synthetic Captions for Open-Vocabulary Zero-Shot Segmentation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7131118729","doi":"https://doi.org/10.1109/iccvw69036.2025.00718"},"language":null,"primary_location":{"id":"doi:10.1109/iccvw69036.2025.00718","doi":"https://doi.org/10.1109/iccvw69036.2025.00718","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00718","pdf_url":null,"source":{"id":"https://openalex.org/S7407088950","display_name":"IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5067774307","display_name":"Tim Lebailly","orcid":"https://orcid.org/0000-0002-9814-7531","observed_orcids":["https://orcid.org/0000-0002-9814-7531"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tim Lebailly","raw_affiliation_strings":["Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080979919","display_name":"Vijay Veerabadran","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vijay Veerabadran","raw_affiliation_strings":["Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070914582","display_name":"Satwik Kottur","orcid":"https://orcid.org/0000-0003-0207-8680","observed_orcids":["https://orcid.org/0000-0003-0207-8680"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Satwik Kottur","raw_affiliation_strings":["Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047499478","display_name":"Karl Ridgeway","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karl Ridgeway","raw_affiliation_strings":["Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030257576","display_name":"Michael L. Iuzzolino","orcid":"https://orcid.org/0009-0006-6445-736X","observed_orcids":["https://orcid.org/0009-0006-6445-736X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Louis Iuzzolino","raw_affiliation_strings":["Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.57684845,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6948","last_page":"6959"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9883000254631042,"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":0.9883000254631042,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.006300000008195639,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.004100000020116568,"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/open-vocabulary-segmentation","display_name":"open-vocabulary segmentation","score":0.8299999833106995},{"id":"https://openalex.org/keywords/zero-shot-segmentation","display_name":"zero-shot segmentation","score":0.9789999723434448},{"id":"https://openalex.org/keywords/vision-language-alignment","display_name":"vision-language alignment","score":0.800000011920929},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.6380000114440918},{"id":"https://openalex.org/keywords/data-efficiency","display_name":"data efficiency","score":0.5569999814033508}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7329999804496765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7297999858856201},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7290999889373779},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6233999729156494},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5921000242233276},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.5659999847412109},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5289999842643738},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5073000192642212},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4828999936580658},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4408000111579895},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42559999227523804},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4154999852180481},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4020000100135803},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3833000063896179},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.36629998683929443},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.28049999475479126},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccvw69036.2025.00718","doi":"https://doi.org/10.1109/iccvw69036.2025.00718","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00718","pdf_url":null,"source":{"id":"https://openalex.org/S7407088950","display_name":"IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.7331549525260925,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2125215748","https://openalex.org/W2340897893","https://openalex.org/W2561196672","https://openalex.org/W2737258237","https://openalex.org/W2963150697","https://openalex.org/W3024705827","https://openalex.org/W3035524453","https://openalex.org/W3035703639","https://openalex.org/W3159481202","https://openalex.org/W3213454282","https://openalex.org/W4312980231","https://openalex.org/W4386065432","https://openalex.org/W4386075766","https://openalex.org/W4386075997","https://openalex.org/W4386076046","https://openalex.org/W4390873248","https://openalex.org/W4390873312","https://openalex.org/W4390873426","https://openalex.org/W4390874195","https://openalex.org/W4390874575","https://openalex.org/W4394593090","https://openalex.org/W4403878709","https://openalex.org/W4404690627"],"related_works":[],"abstract_inverted_index":{"Generative":[0],"vision-language":[1,39],"models":[2],"(VLMs)":[3],"exhibit":[4],"strong":[5],"high-level":[6,82],"image":[7],"understanding":[8,84],"but":[9],"lack":[10],"spatially":[11],"dense":[12,45,86],"alignment":[13,87],"between":[14],"vision":[15],"and":[16,72],"language":[17],"modalities,":[18],"as":[19],"our":[20,90],"findings":[21],"indicate.":[22],"Orthogonal":[23],"to":[24,74],"advancements":[25],"in":[26],"generative":[27],"VLMs,":[28],"another":[29],"line":[30],"of":[31,81],"research":[32],"has":[33],"focused":[34],"on":[35,95],"representation":[36],"learning":[37],"for":[38,44,85],"alignment,":[40],"targeting":[41],"zero-shot":[42,97],"inference":[43],"tasks":[46],"like":[47],"segmentation.":[48],"In":[49],"this":[50],"work,":[51],"we":[52],"bridge":[53],"these":[54],"two":[55],"directions":[56],"by":[57,65],"densely":[58],"aligning":[59],"images":[60],"with":[61],"synthetic":[62],"descriptions":[63],"generated":[64],"VLMs.":[66],"Synthetic":[67],"captions":[68],"are":[69],"inexpensive,":[70],"scalable,":[71],"easy":[73],"generate,":[75],"making":[76],"them":[77],"an":[78],"excellent":[79],"source":[80],"semantic":[83],"methods.":[88],"Empirically,":[89],"approach":[91],"outperforms":[92],"prior":[93],"work":[94],"standard":[96],"open-vocabulary":[98],"segmentation":[99],"benchmarksldatasets,":[100],"while":[101],"also":[102],"being":[103],"more":[104],"data-efficient.":[105]},"counts_by_year":[],"updated_date":"2026-10-05T09:50:58.205359","created_date":"2026-02-24T00:00:00"}