{"id":"https://openalex.org/W7164344765","doi":"https://doi.org/10.48550/arxiv.2606.11546","title":"VL-DINO: Leveraging CLIP Vision-Language Knowledge for Open-Vocabulary Object Detectio","display_name":"VL-DINO: Leveraging CLIP Vision-Language Knowledge for Open-Vocabulary Object Detectio","publication_year":2026,"publication_date":"2026-06-10","ids":{"openalex":"https://openalex.org/W7164344765","doi":"https://doi.org/10.48550/arxiv.2606.11546"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.11546","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11546","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.11546","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138421567","display_name":"Hao Zhang (15339)","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128040279","display_name":"Qinran Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Qinran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138435524","display_name":"Linqi Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Linqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138470813","display_name":"Yong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9584000110626221,"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":0.9584000110626221,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.009499999694526196,"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":0.0052999998442828655,"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/object","display_name":"Object (grammar)","score":0.6514000296592712},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6327999830245972},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6114000082015991},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5223000049591064},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.48339998722076416},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4341000020503998},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.38109999895095825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8181999921798706},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6514000296592712},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6327999830245972},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6114000082015991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5631999969482422},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5223000049591064},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4927999973297119},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.48339998722076416},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4341000020503998},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.38109999895095825},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3797999918460846},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3723999857902527},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3492000102996826},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.2705000042915344},{"id":"https://openalex.org/C73752529","wikidata":"https://www.wikidata.org/wiki/Q79872","display_name":"Object-oriented programming","level":2,"score":0.2621000111103058}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.11546","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11546","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":"doi:10.48550/arxiv.2606.11546","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11546","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.8204087615013123,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-language":[0],"models":[1],"like":[2],"CLIP":[3,101],"can":[4],"provide":[5],"rich":[6],"semantic":[7],"priors":[8],"for":[9,110],"open-vocabulary":[10,33],"object":[11],"detection.":[12],"However,":[13],"jointly":[14],"integrating":[15],"both":[16],"textual":[17,86,135,139],"and":[18,129,146,150,168],"visual":[19,102],"knowledge":[20,87,103],"into":[21,104],"detection":[22],"architectures":[23],"remains":[24],"challenging.":[25],"In":[26,141],"this":[27],"paper,":[28],"we":[29],"propose":[30],"VL-DINO,":[31],"an":[32,119],"detector":[34],"that":[35],"enhances":[36],"DINO":[37,66],"through":[38],"more":[39,79],"effective":[40],"exploitation":[41],"of":[42,171],"CLIP's":[43],"vision-language":[44,80],"knowledge.":[45],"Specifically,":[46],"a":[47],"Query-guided":[48],"Positive":[49],"Sample":[50],"Construction":[51],"(QPSC)":[52],"module":[53,95,124],"is":[54,96],"first":[55],"developed":[56],"to":[57,68,99],"construct":[58],"additional":[59],"high-quality":[60],"positive":[61],"samples,":[62],"enabling":[63],"the":[64,116,133,142,154,166,172],"vanilla":[65],"framework":[67],"better":[69],"accommodate":[70],"mixed":[71],"training":[72],"across":[73],"heterogeneous":[74],"data":[75],"sources":[76],"while":[77],"providing":[78],"alignment":[81],"signals,":[82],"thereby":[83],"incorporating":[84,138],"richer":[85],"during":[88],"training.":[89],"A":[90],"Visual":[91],"Semantic":[92,121],"Encoder":[93],"(VSE)":[94],"then":[97],"introduced":[98],"distill":[100],"backbone-extracted":[105],"features,":[106,118],"producing":[107],"fused":[108,117],"features":[109,128],"subsequent":[111],"encoder":[112],"refinement.":[113],"Based":[114],"on":[115,153],"Object-Region":[120],"Alignment":[122],"(ORSA)":[123],"extracts":[125],"object-centric":[126],"region":[127],"aligns":[130],"them":[131],"with":[132],"corresponding":[134],"embeddings,":[136],"further":[137],"cues.":[140],"zero-shot":[143],"setting,":[144],"VL-DINO-T":[145],"VL-DINO-L":[147],"achieve":[148],"36.3":[149],"38.1":[151],"AP":[152],"LVIS":[155],"benchmark,":[156],"respectively,":[157],"consistently":[158],"outperforming":[159],"prior":[160],"advanced":[161],"approaches.":[162],"Extensive":[163],"experiments":[164],"demonstrate":[165],"effectiveness":[167],"competitive":[169],"performance":[170],"proposed":[173],"design.":[174]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-12T00:00:00"}