{"id":"https://openalex.org/W4386065936","doi":"https://doi.org/10.1109/cvpr52729.2023.02250","title":"DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment","display_name":"DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4386065936","doi":"https://doi.org/10.1109/cvpr52729.2023.02250"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52729.2023.02250","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.02250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"article","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/A5027453000","display_name":"Lewei Yao","orcid":null},"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/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["HK","SE"],"is_corresponding":true,"raw_author_name":"Lewei Yao","raw_affiliation_strings":["Hong Kong University of Science and Technology","Huawei Noah's Ark Lab"],"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/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100297958","display_name":"Jianhua Han","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Jianhua Han","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047878798","display_name":"Xiaodan Liang","orcid":"https://orcid.org/0000-0003-3213-3062"},"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":"Xiaodan Liang","raw_affiliation_strings":["Shenzhen Campus of Sun Yat-Sen University"],"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"},"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":"Dan Xu","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"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/A5100441569","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0002-1492-8286"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103196797","display_name":"Zhenguo Li","orcid":"https://orcid.org/0000-0002-8492-3069"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Zhenguo Li","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041457457","display_name":"Hang Xu","orcid":"https://orcid.org/0000-0003-3645-8972"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Hang Xu","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5027453000"],"corresponding_institution_ids":["https://openalex.org/I200769079","https://openalex.org/I4210159102"],"apc_list":null,"apc_paid":null,"fwci":7.1423,"has_fulltext":false,"cited_by_count":60,"citation_normalized_percentile":{"value":0.98033484,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"23497","last_page":"23506"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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":0.9959999918937683,"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/computer-science","display_name":"Computer science","score":0.8539212942123413},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6806195378303528},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6528377532958984},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6089299917221069},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6013855338096619},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5622938871383667},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5313658714294434},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48060891032218933},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.46685534715652466},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4609883427619934},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44451671838760376},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4176984429359436},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33945780992507935},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2185261845588684}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8539212942123413},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6806195378303528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6528377532958984},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6089299917221069},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6013855338096619},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5622938871383667},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5313658714294434},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48060891032218933},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.46685534715652466},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4609883427619934},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44451671838760376},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4176984429359436},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33945780992507935},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2185261845588684},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cvpr52729.2023.02250","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.02250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-132318","is_oa":false,"landing_page_url":"https://repository.hkust.edu.hk/ir/Record/1783.1-132318","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.800000011920929,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":89,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1514535095","https://openalex.org/W1861492603","https://openalex.org/W1933349210","https://openalex.org/W2745461083","https://openalex.org/W2886641317","https://openalex.org/W2886904239","https://openalex.org/W2896457183","https://openalex.org/W2948672349","https://openalex.org/W2952688802","https://openalex.org/W2962766617","https://openalex.org/W2963037989","https://openalex.org/W2963603913","https://openalex.org/W2964067226","https://openalex.org/W2966926453","https://openalex.org/W2982770724","https://openalex.org/W2983943451","https://openalex.org/W3021542222","https://openalex.org/W3030520226","https://openalex.org/W3034329658","https://openalex.org/W3035003500","https://openalex.org/W3035318183","https://openalex.org/W3035396860","https://openalex.org/W3040002795","https://openalex.org/W3091588028","https://openalex.org/W3092462694","https://openalex.org/W3120055985","https://openalex.org/W3124149278","https://openalex.org/W3126337491","https://openalex.org/W3126792443","https://openalex.org/W3138516171","https://openalex.org/W3159619744","https://openalex.org/W3166396011","https://openalex.org/W3171660447","https://openalex.org/W3172507542","https://openalex.org/W3176641147","https://openalex.org/W3194038966","https://openalex.org/W3204392079","https://openalex.org/W3206072662","https://openalex.org/W3212248244","https://openalex.org/W3212456749","https://openalex.org/W4221143499","https://openalex.org/W4226182655","https://openalex.org/W4282919422","https://openalex.org/W4283009931","https://openalex.org/W4287353120","https://openalex.org/W4292779060","https://openalex.org/W4293060547","https://openalex.org/W4293138060","https://openalex.org/W4296605949","https://openalex.org/W4310486995","https://openalex.org/W4310557340","https://openalex.org/W4312424618","https://openalex.org/W4312563428","https://openalex.org/W4312691946","https://openalex.org/W4312956471","https://openalex.org/W6620707391","https://openalex.org/W6630875275","https://openalex.org/W6639102338","https://openalex.org/W6753610190","https://openalex.org/W6754778999","https://openalex.org/W6755207826","https://openalex.org/W6756800942","https://openalex.org/W6775970589","https://openalex.org/W6776778719","https://openalex.org/W6778485988","https://openalex.org/W6778883912","https://openalex.org/W6779101013","https://openalex.org/W6780006332","https://openalex.org/W6784094891","https://openalex.org/W6789705400","https://openalex.org/W6789753369","https://openalex.org/W6789992408","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6802009570","https://openalex.org/W6802517928","https://openalex.org/W6803953248","https://openalex.org/W6804065392","https://openalex.org/W6809576537","https://openalex.org/W6809783041","https://openalex.org/W6810309399","https://openalex.org/W6810876946","https://openalex.org/W6811013733","https://openalex.org/W6839220867","https://openalex.org/W6839745749","https://openalex.org/W6841673407","https://openalex.org/W6842303585","https://openalex.org/W6842874653"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W1997182898"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"DetCLIPv2,":[3],"an":[4,56,114],"efficient":[5],"and":[6,71,101,117,130,146,183],"scalable":[7],"training":[8,112,144],"framework":[9],"that":[10,25],"incorporates":[11],"large-scale":[12],"imagetext":[13],"pairs":[14,38,54,138,152],"to":[15,74,83],"achieve":[16],"open-vocabulary":[17,158],"object":[18],"detection":[19,159],"(OVD).":[20],"Unlike":[21],"previous":[22,176],"OVD":[23],"frameworks":[24],"typically":[26],"rely":[27],"on":[28,170],"a":[29,40,64,95,106,142,190],"pre-trained":[30],"vision-language":[31],"model":[32,82],"(e.g.,":[33],"CLIP)":[34],"or":[35],"exploit":[36],"image-text":[37,53,102,122,126,137,151],"via":[39],"pseudo":[41],"labeling":[42],"process,":[43],"DetCLIPv2":[44,91,124,132,155,162],"directly":[45],"learns":[46],"the":[47,76,81,171],"fine-grained":[48],"word-region":[49,66],"alignment":[50],"from":[51,98],"massive":[52],"in":[55],"end-to-end":[57],"manner.":[58],"To":[59,79],"accomplish":[60],"this,":[61],"we":[62],"employ":[63],"maximum":[65],"similarity":[67],"between":[68],"region":[69],"proposals":[70],"textual":[72],"words":[73],"guide":[75],"contrastive":[77],"objective.":[78],"enable":[80],"gain":[84],"localization":[85],"capability":[86],"while":[87],"learning":[88],"broad":[89],"concepts,":[90],"is":[92],"trained":[93],"with":[94,113,141,163],"hybrid":[96],"supervision":[97],"detection,":[99],"grounding":[100],"pair":[103,127],"data":[104,108,128],"under":[105],"unified":[107],"formulation.":[109],"By":[110],"jointly":[111],"alternating":[115],"scheme":[116],"adopting":[118],"low-resolution":[119],"input":[120],"for":[121,153],"pairs,":[123],"exploits":[125],"efficiently":[129],"effectively:":[131],"utilizes":[133],"13":[134],"\u00d7":[135],"more":[136],"than":[139],"DetCLIP":[140],"similar":[143],"time":[145],"improves":[147],"performance.":[148],"With":[149],"13M":[150],"pre-training,":[154],"demonstrates":[156],"superior":[157],"performance,":[160],"e.g.,":[161],"Swin-T":[164],"backbone":[165],"achieves":[166],"40.4%":[167],"zero-shot":[168],"AP":[169],"LVIS":[172],"benchmark,":[173],"which":[174],"outperforms":[175],"works":[177],"GLIP/GLIPv2/DetCLIP":[178],"by":[179,189],"14.4/11.4/4.5%":[180],"AP,":[181],"respectively,":[182],"even":[184],"beats":[185],"its":[186],"fully-supervised":[187],"counterpart":[188],"large":[191],"margin.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":35},{"year":2023,"cited_by_count":4}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}