{"id":"https://openalex.org/W4296605949","doi":"https://doi.org/10.48550/arxiv.2209.09407","title":"DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection","display_name":"DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection","publication_year":2022,"publication_date":"2022-09-20","ids":{"openalex":"https://openalex.org/W4296605949","doi":"https://doi.org/10.48550/arxiv.2209.09407"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2209.09407","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.09407","pdf_url":"https://arxiv.org/pdf/2209.09407","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2209.09407","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027453000","display_name":"Lewei Yao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Yao, Lewei","raw_affiliation_strings":["Hong Kong University of Science and Technology ,","Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology ,","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100297958","display_name":"Jianhua Han","orcid":"https://orcid.org/0009-0004-1559-657X","observed_orcids":["https://orcid.org/0009-0004-1559-657X"]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han, Jianhua","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100560210","display_name":"Youpeng Wen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen, Youpeng","raw_affiliation_strings":["Shenzhen Campus of Sun Yat-Sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Campus of Sun Yat-Sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047878798","display_name":"Xiaodan Liang","orcid":"https://orcid.org/0000-0003-3213-3062","observed_orcids":["https://orcid.org/0000-0003-3213-3062","https://orcid.org/0009-0002-1795-1948"]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang, Xiaodan","raw_affiliation_strings":["Shenzhen Campus of Sun Yat-Sen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Campus of Sun Yat-Sen University","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341938","display_name":"Dan Xu","orcid":"https://orcid.org/0000-0003-0136-9603","observed_orcids":["https://orcid.org/0000-0003-0136-9603","https://orcid.org/0000-0002-7718-6224"]},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xu, Dan","raw_affiliation_strings":["Hong Kong University of Science and Technology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology ,","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101899687","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0002-1492-8286","observed_orcids":["https://orcid.org/0000-0002-1492-8286","https://orcid.org/0000-0002-9719-554X","https://orcid.org/0000-0002-2169-8749"]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Wei","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103196797","display_name":"Zhenguo Li","orcid":"https://orcid.org/0000-0002-8492-3069","observed_orcids":["https://orcid.org/0000-0002-8492-3069"]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Zhenguo","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101082712","display_name":"Chunjing Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Chunjing","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066768790","display_name":"Hang Xu","orcid":"https://orcid.org/0000-0003-4176-0738","observed_orcids":["https://orcid.org/0000-0003-4176-0738"]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Hang","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":105,"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":0.6133000254631042,"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":0.6133000254631042,"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":0.31450000405311584,"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":0.05270000174641609,"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/open-world-object-detection","display_name":"open-world object detection","score":0.9950000047683716},{"id":"https://openalex.org/keywords/concept-dictionary","display_name":"concept dictionary","score":0.9769999980926514},{"id":"https://openalex.org/keywords/zero-shot-object-detection","display_name":"zero-shot detection","score":0.7839999794960022},{"id":"https://openalex.org/keywords/visual-grounding","display_name":"visual grounding","score":0.49799999594688416},{"id":"https://openalex.org/keywords/image-text-pairs","display_name":"image-text pairs","score":0.5569999814033508},{"id":"https://openalex.org/keywords/lymphovascular-invasion","display_name":"lymphovascular invasion","score":0.6430000066757202}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7702297568321228},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5938202142715454},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5772624015808105},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5599636435508728},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5375800728797913},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.49052494764328003},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.47079697251319885},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.457154244184494},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44811493158340454},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4229833483695984},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.379863977432251},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3680691421031952},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35368430614471436},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11728304624557495},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09433728456497192},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2209.09407","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.09407","pdf_url":"https://arxiv.org/pdf/2209.09407","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2209.09407","doi":"https://doi.org/10.48550/arxiv.2209.09407","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2209.09407","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2209.09407","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.09407","pdf_url":"https://arxiv.org/pdf/2209.09407","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4296605949.pdf","grobid_xml":"https://content.openalex.org/works/W4296605949.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W2950141105","https://openalex.org/W2964121744","https://openalex.org/W2968124245","https://openalex.org/W3092462694","https://openalex.org/W3127023342","https://openalex.org/W3189827190","https://openalex.org/W3206072662","https://openalex.org/W3211483028","https://openalex.org/W4226167525","https://openalex.org/W4226182655","https://openalex.org/W4310557340","https://openalex.org/W4312691946","https://openalex.org/W4312747482","https://openalex.org/W4312890493","https://openalex.org/W4319779677","https://openalex.org/W7133187299","https://openalex.org/W7133227958"],"related_works":["https://openalex.org/W4386065936","https://openalex.org/W7222958337","https://openalex.org/W4403908341","https://openalex.org/W7164344765","https://openalex.org/W4390872357","https://openalex.org/W7163917366","https://openalex.org/W7106270182","https://openalex.org/W7164323132","https://openalex.org/W7113086682","https://openalex.org/W7160435958"],"abstract_inverted_index":{"Open-world":[0],"object":[1],"detection,":[2,94],"as":[3,28,214],"a":[4,29,54,68,79,104,199],"more":[5],"general":[6],"and":[7,13,96,112,162,197],"challenging":[8],"goal,":[9],"aims":[10],"to":[11,44,64,88,115,137,149,163,206],"recognize":[12],"localize":[14],"objects":[15,167],"described":[16],"by":[17,32,62,194],"arbitrary":[18],"category":[19,35,48],"names.":[20,49],"The":[21,142,177],"recent":[22],"work":[23],"GLIP":[24],"formulates":[25],"this":[26],"problem":[27,31],"grounding":[30],"concatenating":[33],"all":[34],"names":[36],"of":[37,157,173],"detection":[38,61,113,183],"datasets":[39,92,114],"into":[40],"sentences,":[41],"which":[42],"leads":[43],"inefficient":[45],"interaction":[46],"between":[47],"This":[50],"paper":[51],"presents":[52],"DetCLIP,":[53],"paralleled":[55,81],"visual-concept":[56],"pre-training":[57],"method":[58],"for":[59,99,119,154,166],"open-world":[60],"resorting":[63],"knowledge":[65,118],"enrichment":[66],"from":[67,108],"designed":[69],"concept":[70,82,105,144],"dictionary.":[71],"To":[72],"achieve":[73],"better":[74,89],"learning":[75],"efficiency,":[76],"we":[77,129],"propose":[78],"novel":[80],"formulation":[83],"that":[84],"extracts":[85],"concepts":[86,125,136,153],"separately":[87],"utilize":[90],"heterogeneous":[91],"(i.e.,":[93],"grounding,":[95],"image-text":[97,174],"pairs)":[98],"training.":[100],"We":[101],"further":[102,147],"design":[103],"dictionary~(with":[106],"descriptions)":[107],"various":[109,135],"online":[110],"sources":[111],"provide":[116,150],"prior":[117],"each":[120],"concept.":[121],"By":[122],"enriching":[123],"the":[124,132,139,155,158,187,207,211],"with":[126,168,210],"their":[127],"descriptions,":[128],"explicitly":[130],"build":[131],"relationships":[133],"among":[134],"facilitate":[138],"open-domain":[140],"learning.":[141],"proposed":[143,178],"dictionary":[145],"is":[146],"used":[148],"sufficient":[151],"negative":[152],"construction":[156],"word-region":[159],"alignment":[160],"loss\\,":[161],"complete":[164],"labels":[165],"missing":[169],"descriptions":[170],"in":[171],"captions":[172],"pair":[175],"data.":[176],"framework":[179],"demonstrates":[180],"strong":[181],"zero-shot":[182],"performances,":[184],"e.g.,":[185],"on":[186,202],"LVIS":[188],"dataset,":[189],"our":[190],"DetCLIP-T":[191],"outperforms":[192],"GLIP-T":[193],"9.9%":[195],"mAP":[196],"obtains":[198],"13.5%":[200],"improvement":[201],"rare":[203],"categories":[204],"compared":[205],"fully-supervised":[208],"model":[209],"same":[212],"backbone":[213],"ours.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":29},{"year":2024,"cited_by_count":55},{"year":2023,"cited_by_count":18}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2022-09-23T00:00:00"}