{"id":"https://openalex.org/W4402716321","doi":"https://doi.org/10.1109/cvpr52733.2024.01650","title":"Retrieval-Augmented Open-Vocabulary Object Detection","display_name":"Retrieval-Augmented Open-Vocabulary Object Detection","publication_year":2024,"publication_date":"2024-06-16","ids":{"openalex":"https://openalex.org/W4402716321","doi":"https://doi.org/10.1109/cvpr52733.2024.01650"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52733.2024.01650","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.01650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"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/A5011048461","display_name":"Jooyeon Kim","orcid":"https://orcid.org/0000-0001-8432-6056"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jooyeon Kim","raw_affiliation_strings":["Korea University,Department of Computer Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007257708","display_name":"Eulrang Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eulrang Cho","raw_affiliation_strings":["Samsung Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043210468","display_name":"Sehyung Kim","orcid":"https://orcid.org/0009-0003-6381-9291"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sehyung Kim","raw_affiliation_strings":["Korea University,Department of Computer Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084814930","display_name":"Hyunwoo J. Kim","orcid":"https://orcid.org/0000-0002-2181-9264"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunwoo J. Kim","raw_affiliation_strings":["Korea University,Department of Computer Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea University,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I197347611"]}]}],"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":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17427","last_page":"17436"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9969000220298767,"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":0.9950000047683716,"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/computer-science","display_name":"Computer science","score":0.8069790601730347},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6614687442779541},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5531380772590637},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5232476592063904},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4828348755836487},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4781276285648346},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4632384181022644},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.1679072082042694},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15797609090805054}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8069790601730347},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6614687442779541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5531380772590637},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5232476592063904},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4828348755836487},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4781276285648346},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4632384181022644},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.1679072082042694},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15797609090805054},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52733.2024.01650","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52733.2024.01650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2194775991","https://openalex.org/W2886641317","https://openalex.org/W2948672349","https://openalex.org/W2963150697","https://openalex.org/W3027879771","https://openalex.org/W3108984808","https://openalex.org/W3126337491","https://openalex.org/W3173859428","https://openalex.org/W3206072662","https://openalex.org/W3210146405","https://openalex.org/W4221143397","https://openalex.org/W4224035735","https://openalex.org/W4226058394","https://openalex.org/W4226452378","https://openalex.org/W4283397426","https://openalex.org/W4284961860","https://openalex.org/W4292779060","https://openalex.org/W4310418579","https://openalex.org/W4310557340","https://openalex.org/W4312563428","https://openalex.org/W4312747482","https://openalex.org/W4312773012","https://openalex.org/W4312890493","https://openalex.org/W4312920106","https://openalex.org/W4312960937","https://openalex.org/W4360887655","https://openalex.org/W4380352233","https://openalex.org/W4386066010","https://openalex.org/W4386076029","https://openalex.org/W4386076396","https://openalex.org/W4386566587","https://openalex.org/W4390871915","https://openalex.org/W6620707391","https://openalex.org/W6753938374","https://openalex.org/W6777615688","https://openalex.org/W6778883912","https://openalex.org/W6790019176","https://openalex.org/W6802517928","https://openalex.org/W6809396591","https://openalex.org/W6809885388","https://openalex.org/W6811433417","https://openalex.org/W6838901828","https://openalex.org/W6839701648","https://openalex.org/W6846977184","https://openalex.org/W6851016243","https://openalex.org/W6851351832","https://openalex.org/W6853690301"],"related_works":["https://openalex.org/W2349784553","https://openalex.org/W3022596247","https://openalex.org/W2601444686","https://openalex.org/W4307058054","https://openalex.org/W4292238148","https://openalex.org/W4323660495","https://openalex.org/W2385319785","https://openalex.org/W2900827440","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"Open-vocabulary":[0],"object":[1],"detection":[2],"(OVD)":[3],"has":[4],"been":[5],"stud-ied":[6],"with":[7,35,75,114,123],"Vision-Language":[8],"Models":[9],"(VLMs)":[10],"to":[11,25,150],"detect":[12],"novel":[13,157],"objects":[14],"beyond":[15],"the":[16,22,27,30,46,83,111,124,136,160,169],"pre-trained":[17],"categories.":[18],"Previous":[19],"ap-proaches":[20],"improve":[21],"generalization":[23],"ability":[24],"expand":[26],"knowledge":[28],"of":[29,78,94,138,159],"detector,":[31],"using":[32],"\u2018positive\u2019":[33],"pseudo-labels":[34],"additional":[36],"\u2018class'":[37],"names,":[38],"e.g.,":[39,80],"sock,":[40],"iPod,":[41],"and":[42,56,66,88,101,142,163],"alli-gator.":[43],"To":[44],"extend":[45],"previous":[47],"methods":[48],"in":[49],"two":[50,95,108],"aspects,":[51],"we":[52],"propose":[53],"Retrieval-Augmented":[54,102],"Losses":[55,99],"visual":[57,71,103,121],"Features":[58],"(RALF).":[59],"Our":[60,133],"method":[61],"retrieves":[62],"related":[63],"\u2018negative\u2019":[64],"classes":[65],"augments":[67,120],"loss":[68],"functions.":[69],"Also,":[70],"features":[72,122],"are":[73],"aug-mented":[74],"\u2018verbalized":[76],"concepts'":[77],"classes,":[79],"worn":[81],"on":[82,140,156,168],"feet,":[84],"handheld":[85],"music":[86],"player,":[87],"sharp":[89],"teeth.":[90],"Specif-ically,":[91],"RALF":[92,139],"consists":[93],"modules:":[96],"Retrieval":[97],"Aug-mented":[98],"(RAL)":[100],"Fea-tures":[104],"(RAF).":[105],"RAL":[106],"constitutes":[107],"losses":[109],"reflecting":[110],"se-mantic":[112],"similarity":[113],"negative":[115],"vocabularies.":[116],"In":[117],"addition,":[118],"RAF":[119],"verbalized":[125],"con-cepts":[126],"from":[127],"a":[128],"large":[129],"language":[130],"model":[131],"(LLM).":[132],"experiments":[134],"demonstrate":[135],"effectiveness":[137],"COCO":[141,161],"LVIS":[143,170],"benchmark":[144],"datasets.":[145],"We":[146],"achieve":[147],"improvement":[148],"up":[149],"3.4":[151],"box":[152],"APN<inf":[153],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[154],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">50</inf>":[155],"categories":[158],"dataset":[162],"3.6":[164],"mask":[165],"APr":[166],"gains":[167],"dataset.":[171],"Code":[172],"is":[173],"available":[174],"at":[175],"https://github.com/mlvlab/RALF.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}