{"id":"https://openalex.org/W4416513274","doi":"https://doi.org/10.1109/tvcg.2025.3633870","title":"OW-CLIP: Data-Efficient Visual Supervision for Open-World Object Detection via Human-AI Collaboration","display_name":"OW-CLIP: Data-Efficient Visual Supervision for Open-World Object Detection via Human-AI Collaboration","publication_year":2025,"publication_date":"2025-11-21","ids":{"openalex":"https://openalex.org/W4416513274","doi":"https://doi.org/10.1109/tvcg.2025.3633870","pmid":"https://pubmed.ncbi.nlm.nih.gov/41269819"},"language":"en","primary_location":{"id":"doi:10.1109/tvcg.2025.3633870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2025.3633870","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5103209723","display_name":"Junwen Duan","orcid":"https://orcid.org/0000-0003-4955-9270"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junwen Duan","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, China"],"raw_orcid":"https://orcid.org/0000-0003-4955-9270","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115010729","display_name":"Wei Xue","orcid":"https://orcid.org/0000-0003-3614-6194"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xue","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ziyao Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyao Kang","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shixia Liu","orcid":"https://orcid.org/0000-0003-4499-6420"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shixia Liu","raw_affiliation_strings":["School of Software, Tsinghua University, China"],"raw_orcid":"https://orcid.org/0000-0003-4499-6420","affiliations":[{"raw_affiliation_string":"School of Software, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079986783","display_name":"Jiazhi Xia","orcid":"https://orcid.org/0000-0003-4629-6268"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiazhi Xia","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, China"],"raw_orcid":"https://orcid.org/0000-0003-4629-6268","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, China","institution_ids":["https://openalex.org/I139660479"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.32478191,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":"1","first_page":"68","last_page":"78"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.49549999833106995,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.49549999833106995,"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":0.396699994802475,"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":0.023600000888109207,"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/leverage","display_name":"Leverage (statistics)","score":0.6841999888420105},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.6668000221252441},{"id":"https://openalex.org/keywords/visual-analytics","display_name":"Visual analytics","score":0.5284000039100647},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5099999904632568},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4993000030517578},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4799000024795532},{"id":"https://openalex.org/keywords/data-visualization","display_name":"Data visualization","score":0.4724000096321106},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4523000121116638},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.39899998903274536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8831999897956848},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6841999888420105},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.6668000221252441},{"id":"https://openalex.org/C59732488","wikidata":"https://www.wikidata.org/wiki/Q2528440","display_name":"Visual analytics","level":3,"score":0.5284000039100647},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5099999904632568},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5052000284194946},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4993000030517578},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4799000024795532},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.4724000096321106},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4523000121116638},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4115000069141388},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.39899998903274536},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3921000063419342},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.3450999855995178},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.3237999975681305},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.3215999901294708},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3019999861717224},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2800999879837036},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.26269999146461487},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.25200000405311584},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.250900000333786}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tvcg.2025.3633870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2025.3633870","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},{"id":"pmid:41269819","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41269819","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on visualization and computer graphics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2042553169","display_name":null,"funder_award_id":"62372471","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G921486363","display_name":null,"funder_award_id":"U23A20313","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1791587663","https://openalex.org/W1861492603","https://openalex.org/W1917989004","https://openalex.org/W2031489346","https://openalex.org/W2037227137","https://openalex.org/W2117539524","https://openalex.org/W2157289187","https://openalex.org/W2333322610","https://openalex.org/W2558809543","https://openalex.org/W2883725317","https://openalex.org/W2904982178","https://openalex.org/W2954929116","https://openalex.org/W2972458663","https://openalex.org/W3174770825","https://openalex.org/W3176709420","https://openalex.org/W3198377975","https://openalex.org/W3204809439","https://openalex.org/W3204925778","https://openalex.org/W3216551675","https://openalex.org/W3217535672","https://openalex.org/W4200283487","https://openalex.org/W4205991051","https://openalex.org/W4214687390","https://openalex.org/W4223646441","https://openalex.org/W4226058394","https://openalex.org/W4312238419","https://openalex.org/W4312310776","https://openalex.org/W4312651322","https://openalex.org/W4318621382","https://openalex.org/W4366989525","https://openalex.org/W4367188881","https://openalex.org/W4386066015","https://openalex.org/W4386071547","https://openalex.org/W4386072441","https://openalex.org/W4386075561","https://openalex.org/W4387831758","https://openalex.org/W4387885644","https://openalex.org/W4389520264","https://openalex.org/W4390831550","https://openalex.org/W4390872835","https://openalex.org/W4390874134","https://openalex.org/W4393160296","https://openalex.org/W4396605295","https://openalex.org/W4402727877","https://openalex.org/W4404199641","https://openalex.org/W4404534210"],"related_works":[],"abstract_inverted_index":{"Open-world":[0],"object":[1,6],"detection":[2,7],"(OWOD)":[3],"extends":[4],"traditional":[5],"to":[8,32,43,52,95,137],"identifying":[9],"both":[10],"known":[11],"and":[12,47,72,89,120,126,139,147,190],"unknown":[13],"object,":[14],"necessitating":[15],"continuous":[16],"model":[17,54,76],"adaptation":[18],"as":[19],"new":[20],"annotations":[21],"emerge.":[22],"Current":[23],"approaches":[24],"face":[25],"significant":[26],"limitations:":[27],"1)":[28],"data-hungry":[29],"training":[30,107],"due":[31,51],"reliance":[33],"on":[34],"a":[35,64,91,131],"large":[36,117],"number":[37],"of":[38,161,186,195],"crowdsourced":[39],"annotations,":[40],"2)":[41],"susceptibility":[42],"\"partial":[44],"feature":[45,98,145],"overfitting,\"":[46],"3)":[48],"limited":[49],"flexibility":[50],"required":[53],"architecture":[55],"modifications.":[56],"To":[57,100],"tackle":[58],"these":[59],"issues,":[60],"we":[61,109,129],"present":[62],"OW-CLIP,":[63],"visual":[65,144],"analytics":[66],"system":[67],"that":[68,115,134,154],"provides":[69],"curated":[70],"data":[71,103,112,124,178],"enables":[73,135],"data-efficient":[74],"OWOD":[75,87],"incremental":[77],"training.":[78],"OW-CLIP":[79,155],"implements":[80],"plug-and-play":[81],"multimodal":[82],"prompt":[83],"tuning":[84],"tailored":[85],"for":[86,105,123],"settings":[88],"introduces":[90],"novel":[92],"\"Crop-Smoothing\"":[93],"technique":[94],"mitigate":[96],"partial":[97],"overfitting.":[99],"meet":[101],"the":[102,106,184,187,191],"requirements":[104],"methodology,":[108],"propose":[110],"dual-modal":[111],"refinement":[113],"methods":[114],"leverage":[116],"language":[118],"models":[119],"cross-modal":[121],"similarity":[122],"generation":[125],"filtering.":[127],"Simultaneously,":[128],"develope":[130],"visualization":[132,197],"interface":[133],"users":[136],"explore":[138],"deliver":[140],"high-quality":[141],"annotations-including":[142],"class-specific":[143],"phrases":[146],"fine-grained":[148],"differentiated":[149],"images.":[150],"Quantitative":[151],"evaluation":[152],"demonstrates":[153],"achieves":[156],"competitive":[157],"performance":[158,163],"at":[159],"89%":[160],"state-of-the-art":[162],"while":[164,170],"requiring":[165],"only":[166],"3.8%":[167],"self-generated":[168],"data,":[169],"outperforming":[171],"SOTA":[172],"approach":[173],"when":[174],"trained":[175],"with":[176],"equivalent":[177],"volumes.":[179],"A":[180],"case":[181],"study":[182],"shows":[183],"effectiveness":[185],"developed":[188],"method":[189],"improved":[192],"annotation":[193],"quality":[194],"our":[196],"system.":[198]},"counts_by_year":[],"updated_date":"2026-02-09T05:59:30.833894","created_date":"2025-11-23T00:00:00"}