{"id":"https://openalex.org/W4405632022","doi":"https://doi.org/10.1109/tcsvt.2024.3520734","title":"DST-Det: Open-Vocabulary Object Detection via Dynamic Self-Training","display_name":"DST-Det: Open-Vocabulary Object Detection via Dynamic Self-Training","publication_year":2024,"publication_date":"2024-12-20","ids":{"openalex":"https://openalex.org/W4405632022","doi":"https://doi.org/10.1109/tcsvt.2024.3520734"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3520734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3520734","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-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/A5101846832","display_name":"Shilin Xu","orcid":"https://orcid.org/0009-0008-7178-5358"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shilin Xu","raw_affiliation_strings":["National Key Laboratory of General Artificial Intelligence, Peking University, Beijing, China","The National Key Laboratory of General Artificial Intelligence, Peking University, China"],"raw_orcid":"https://orcid.org/0009-0008-7178-5358","affiliations":[{"raw_affiliation_string":"National Key Laboratory of General Artificial Intelligence, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"The National Key Laboratory of General Artificial Intelligence, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089900108","display_name":"Xiangtai Li","orcid":"https://orcid.org/0000-0002-0550-8247"},"institutions":[{"id":"https://openalex.org/I2799854419","display_name":"Raffles Institution","ror":"https://ror.org/04yaxh485","country_code":"SG","type":"education","lineage":["https://openalex.org/I2799854419"]},{"id":"https://openalex.org/I4210115515","display_name":"Nanyang Institute of Technology","ror":"https://ror.org/0203c2755","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210115515"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Xiangtai Li","raw_affiliation_strings":["TikTok, Raffles Quay, Singapore","S-Lab, Nanyang Technological University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TikTok, Raffles Quay, Singapore","institution_ids":["https://openalex.org/I2799854419"]},{"raw_affiliation_string":"S-Lab, Nanyang Technological University, China","institution_ids":["https://openalex.org/I4210115515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101236497","display_name":"Size Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I4210115515","display_name":"Nanyang Institute of Technology","ror":"https://ror.org/0203c2755","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210115515"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Size Wu","raw_affiliation_strings":["S-Lab, Nanyang Technological University, Jurong West, Singapore","S-Lab, Nanyang Technological University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"S-Lab, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"S-Lab, Nanyang Technological University, China","institution_ids":["https://openalex.org/I4210115515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100709484","display_name":"Wenwei Zhang","orcid":"https://orcid.org/0000-0002-2748-4514"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210115515","display_name":"Nanyang Institute of Technology","ror":"https://ror.org/0203c2755","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210115515"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenwei Zhang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory, Shanghai, China","S-Lab, Nanyang Technological University, China"],"raw_orcid":"https://orcid.org/0000-0002-2748-4514","affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]},{"raw_affiliation_string":"S-Lab, Nanyang Technological University, China","institution_ids":["https://openalex.org/I4210115515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024097240","display_name":"Yunhai Tong","orcid":"https://orcid.org/0000-0001-8735-2516"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhai Tong","raw_affiliation_strings":["National Key Laboratory of General Artificial Intelligence, Peking University, Beijing, China","The National Key Laboratory of General Artificial Intelligence, Peking University, China"],"raw_orcid":"https://orcid.org/0000-0001-8735-2516","affiliations":[{"raw_affiliation_string":"National Key Laboratory of General Artificial Intelligence, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"The National Key Laboratory of General Artificial Intelligence, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005626854","display_name":"Chen Change Loy","orcid":"https://orcid.org/0000-0001-5345-1591"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I4210115515","display_name":"Nanyang Institute of Technology","ror":"https://ror.org/0203c2755","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210115515"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Chen Change Loy","raw_affiliation_strings":["S-Lab, Nanyang Technological University, Jurong West, Singapore","S-Lab, Nanyang Technological University, China"],"raw_orcid":"https://orcid.org/0000-0001-5345-1591","affiliations":[{"raw_affiliation_string":"S-Lab, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"S-Lab, Nanyang Technological University, China","institution_ids":["https://openalex.org/I4210115515"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9449,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.88531781,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"35","issue":"5","first_page":"5037","last_page":"5050"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9728000164031982,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9728000164031982,"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":0.7044757008552551},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5835686326026917},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5111847519874573},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5068138241767883},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4966948628425598},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4708862900733948},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.45685014128685},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33597397804260254},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.27905040979385376},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12590017914772034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7044757008552551},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5835686326026917},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5111847519874573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5068138241767883},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4966948628425598},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4708862900733948},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.45685014128685},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33597397804260254},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27905040979385376},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12590017914772034},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcsvt.2024.3520734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3520734","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/217687","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/217687","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"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":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6899999976158142}],"awards":[{"id":"https://openalex.org/G1321115147","display_name":null,"funder_award_id":"MOE-T2EP20120-0001","funder_id":"https://openalex.org/F4320324070","funder_display_name":"Ministry of Education and Research, Romania"},{"id":"https://openalex.org/G426021697","display_name":null,"funder_award_id":"No.2023YFC3807603","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7881794397","display_name":null,"funder_award_id":"2023YFC3807603","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320324070","display_name":"Ministry of Education and Research, Romania","ror":"https://ror.org/00dh5gw98"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":102,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W2616247523","https://openalex.org/W2948672349","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2964254867","https://openalex.org/W3034369739","https://openalex.org/W3034933032","https://openalex.org/W3034971973","https://openalex.org/W3035396860","https://openalex.org/W3035552357","https://openalex.org/W3092663126","https://openalex.org/W3093220398","https://openalex.org/W3096609285","https://openalex.org/W3108105109","https://openalex.org/W3110002552","https://openalex.org/W3166228617","https://openalex.org/W3166596953","https://openalex.org/W3172752666","https://openalex.org/W3172971995","https://openalex.org/W3173859428","https://openalex.org/W3216939881","https://openalex.org/W4226058394","https://openalex.org/W4290994873","https://openalex.org/W4296899977","https://openalex.org/W4310557340","https://openalex.org/W4312424618","https://openalex.org/W4312559104","https://openalex.org/W4312563428","https://openalex.org/W4312599396","https://openalex.org/W4312747482","https://openalex.org/W4312773012","https://openalex.org/W4312890493","https://openalex.org/W4312912313","https://openalex.org/W4312956471","https://openalex.org/W4312960937","https://openalex.org/W4313139298","https://openalex.org/W4323338702","https://openalex.org/W4360892253","https://openalex.org/W4361996346","https://openalex.org/W4366503872","https://openalex.org/W4366966982","https://openalex.org/W4377079900","https://openalex.org/W4380607092","https://openalex.org/W4380905880","https://openalex.org/W4381199011","https://openalex.org/W4383337818","https://openalex.org/W4385569616","https://openalex.org/W4386066010","https://openalex.org/W4386071614","https://openalex.org/W4386071855","https://openalex.org/W4386075819","https://openalex.org/W4386076029","https://openalex.org/W4386076084","https://openalex.org/W4386076396","https://openalex.org/W4387010134","https://openalex.org/W4387609225","https://openalex.org/W4387623951","https://openalex.org/W4387831758","https://openalex.org/W4387968307","https://openalex.org/W4390871915","https://openalex.org/W4390872357","https://openalex.org/W4390873092","https://openalex.org/W4390873343","https://openalex.org/W4390874575","https://openalex.org/W4391547487","https://openalex.org/W4402727672","https://openalex.org/W4402727806","https://openalex.org/W4402733565","https://openalex.org/W6620707391","https://openalex.org/W6760424586","https://openalex.org/W6779101013","https://openalex.org/W6780957418","https://openalex.org/W6784094891","https://openalex.org/W6789753369","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6802517928","https://openalex.org/W6810334672","https://openalex.org/W6811013733","https://openalex.org/W6811230874","https://openalex.org/W6838901828","https://openalex.org/W6839632867","https://openalex.org/W6839701648","https://openalex.org/W6845484831","https://openalex.org/W6846977184","https://openalex.org/W6851065504","https://openalex.org/W6851143279","https://openalex.org/W6851351832","https://openalex.org/W6853690301","https://openalex.org/W6853781193","https://openalex.org/W6855205047","https://openalex.org/W6856473036","https://openalex.org/W6856905403","https://openalex.org/W6857911570","https://openalex.org/W6858693146","https://openalex.org/W6947681574"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"Open-vocabulary":[0],"object":[1,51],"detection":[2],"(OVOD)":[3],"aims":[4],"to":[5,33,49,87,110,166],"detect":[6,50],"the":[7,10,55,61,91,147,173,184,189,216,220],"objects":[8],"beyond":[9],"set":[11],"of":[12,74],"classes":[13,37,82,101],"observed":[14],"during":[15,83,157],"training.":[16,84,132],"This":[17],"work":[18],"introduces":[19],"a":[20,44,72,180],"straightforward":[21],"and":[22,53,77,97,107,120,128,141,229],"efficient":[23,127],"strategy":[24],"that":[25,57],"utilizes":[26],"pre-trained":[27],"vision-language":[28],"models":[29,230],"(VLM),":[30],"like":[31],"CLIP,":[32],"identify":[34],"potential":[35],"novel":[36,81,100,198],"through":[38],"zero-shot":[39],"classification.":[40],"Previous":[41],"methods":[42],"use":[43],"class-agnostic":[45],"region":[46],"proposal":[47],"network":[48],"proposals":[52,56,76],"consider":[54],"do":[58],"not":[59,117],"match":[60],"ground":[62],"truth":[63],"as":[64,80,90],"background.":[65],"Unlike":[66],"these":[67],"methods,":[68,113],"our":[69,114,164,177,193,227],"method":[70,165,178,191,194],"selects":[71],"subset":[73],"background":[75],"treats":[78],"them":[79],"We":[85,209,225],"refer":[86],"this":[88],"approach":[89,115],"self-training":[92],"strategy,":[93],"which":[94,124],"enhances":[95],"recall":[96],"accuracy":[98],"for":[99,207],"without":[102,150,203],"requiring":[103],"extra":[104,205],"annotations,":[105],"datasets,":[106,137],"re-training.":[108],"Compared":[109],"previous":[111,174],"pseudo":[112],"does":[116],"require":[118],"re-training":[119],"offline":[121],"labeling":[122],"processing,":[123],"is":[125],"more":[126],"effective":[129],"in":[130,219],"one-shot":[131],"Empirical":[133],"evaluations":[134],"on":[135,183,201],"three":[136],"including":[138],"LVIS,":[139],"V3Det,":[140],"COCO,":[142],"demonstrate":[143],"significant":[144],"improvements":[145],"over":[146,212,215],"baseline":[148,218],"performance":[149],"incurring":[151],"additional":[152],"parameters":[153],"or":[154],"computational":[155],"costs":[156],"inference.":[158],"In":[159,169],"addition,":[160],"we":[161],"also":[162,195,210],"apply":[163],"various":[167],"baselines.":[168],"particular,":[170],"compared":[171],"with":[172,188],"method,":[175],"F-VLM,":[176],"achieves":[179,196],"2.5%":[181],"improvement":[182,214],"LVIS":[185],"dataset.":[186,224],"Combined":[187],"recent":[190,221],"CLIPSelf,":[192],"46.7":[197],"class":[199],"AP":[200],"COCO":[202],"introducing":[204],"data":[206],"pertaining.":[208],"achieve":[211],"6.5%":[213],"F-VLM":[217],"challenging":[222],"V3Det":[223],"release":[226],"code":[228],"at":[231],"<uri":[232],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[233],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/xushilin1/dst-det</uri>.":[234]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}