{"id":"https://openalex.org/W4386526950","doi":"https://doi.org/10.1007/s11263-023-01876-w","title":"Transferring Vision-Language Models for Visual Recognition: A Classifier Perspective","display_name":"Transferring Vision-Language Models for Visual Recognition: A Classifier Perspective","publication_year":2023,"publication_date":"2023-09-07","ids":{"openalex":"https://openalex.org/W4386526950","doi":"https://doi.org/10.1007/s11263-023-01876-w"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-023-01876-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-023-01876-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-023-01876-w.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11263-023-01876-w.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015819673","display_name":"Wenhao Wu","orcid":"https://orcid.org/0000-0002-8511-743X"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Wenhao Wu","raw_affiliation_strings":["The University of Sydney, Darlington, Australia"],"raw_orcid":"https://orcid.org/0000-0002-8511-743X","affiliations":[{"raw_affiliation_string":"The University of Sydney, Darlington, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016846734","display_name":"Zhun Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhun Sun","raw_affiliation_strings":["Department of Computer Vision Technology, Baidu Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Vision Technology, Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101888535","display_name":"Yuxin Song","orcid":"https://orcid.org/0000-0002-4936-3473"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Song","raw_affiliation_strings":["Department of Computer Vision Technology, Baidu Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Vision Technology, Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075880303","display_name":"Jingdong Wang","orcid":"https://orcid.org/0000-0002-4888-4445"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingdong Wang","raw_affiliation_strings":["Department of Computer Vision Technology, Baidu Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Vision Technology, Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087818121","display_name":"Wanli Ouyang","orcid":"https://orcid.org/0000-0002-9163-2761"},"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/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":"Wanli Ouyang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5015819673"],"corresponding_institution_ids":["https://openalex.org/I129604602"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":{"value":2890,"currency":"EUR","value_usd":3690},"fwci":4.3075,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.954317,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"132","issue":"2","first_page":"392","last_page":"409"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998999834060669,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998999834060669,"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/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/T10812","display_name":"Human Pose and Action Recognition","score":0.9986000061035156,"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":0.8363921642303467},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7351816296577454},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6811918020248413},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5293717384338379},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49165040254592896},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.45996955037117004},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43462300300598145},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32141590118408203}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8363921642303467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7351816296577454},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6811918020248413},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5293717384338379},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49165040254592896},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.45996955037117004},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43462300300598145},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32141590118408203},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11263-023-01876-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-023-01876-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-023-01876-w.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11263-023-01876-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-023-01876-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-023-01876-w.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.75}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320966","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12"},{"id":"https://openalex.org/F4320321836","display_name":"Cooperative Research Centres, Australian Government Department of Industry","ror":"https://ror.org/04k59bg10"},{"id":"https://openalex.org/F4320325287","display_name":"SENSHIN Medical Research Foundation","ror":"https://ror.org/021tj4g88"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386526950.pdf"},"referenced_works_count":73,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W1836465849","https://openalex.org/W1927052826","https://openalex.org/W1977295328","https://openalex.org/W2017814585","https://openalex.org/W2047643928","https://openalex.org/W2108598243","https://openalex.org/W2108950639","https://openalex.org/W2126579184","https://openalex.org/W2138011018","https://openalex.org/W2155904486","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2337252826","https://openalex.org/W2533598788","https://openalex.org/W2770804203","https://openalex.org/W2883429621","https://openalex.org/W2887280559","https://openalex.org/W2904378456","https://openalex.org/W2955874753","https://openalex.org/W2962843773","https://openalex.org/W2963091558","https://openalex.org/W2963155035","https://openalex.org/W2963524571","https://openalex.org/W2963645879","https://openalex.org/W2963689837","https://openalex.org/W2963820951","https://openalex.org/W2964194231","https://openalex.org/W2980037812","https://openalex.org/W2981385151","https://openalex.org/W2984287396","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W2993751684","https://openalex.org/W2996901793","https://openalex.org/W3010010212","https://openalex.org/W3034572008","https://openalex.org/W3034658206","https://openalex.org/W3035254087","https://openalex.org/W3035524453","https://openalex.org/W3041133507","https://openalex.org/W3126337491","https://openalex.org/W3129873671","https://openalex.org/W3135367836","https://openalex.org/W3138516171","https://openalex.org/W3145450063","https://openalex.org/W3172942063","https://openalex.org/W3174568846","https://openalex.org/W3175528717","https://openalex.org/W3176125528","https://openalex.org/W3207340843","https://openalex.org/W4214612132","https://openalex.org/W4214614183","https://openalex.org/W4214746887","https://openalex.org/W4225414521","https://openalex.org/W4226058394","https://openalex.org/W4285606530","https://openalex.org/W4312254032","https://openalex.org/W4312266966","https://openalex.org/W4312302951","https://openalex.org/W4312310776","https://openalex.org/W4312420092","https://openalex.org/W4312480274","https://openalex.org/W4312558481","https://openalex.org/W4312560592","https://openalex.org/W4312614039","https://openalex.org/W4312658081","https://openalex.org/W4312818263","https://openalex.org/W4313136445","https://openalex.org/W4313156423","https://openalex.org/W6640300118","https://openalex.org/W6790690058","https://openalex.org/W6790978476"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W4205302943","https://openalex.org/W3201126466","https://openalex.org/W2119949815","https://openalex.org/W2561132942","https://openalex.org/W2142795561","https://openalex.org/W3155418658","https://openalex.org/W2979740303"],"abstract_inverted_index":{"Abstract":[0],"Transferring":[1],"knowledge":[2,58,115],"from":[3,96,116],"pre-trained":[4,29],"deep":[5],"models":[6],"for":[7,59],"downstream":[8,60],"tasks,":[9],"particularly":[10],"with":[11,34,93,114],"limited":[12],"labeled":[13],"samples,":[14,37],"is":[15],"a":[16,82,107],"fundamental":[17],"problem":[18],"in":[19,25,73],"computer":[20],"vision":[21],"research.":[22],"Recent":[23],"advances":[24],"large-scale,":[26],"task-agnostic":[27],"vision-language":[28],"models,":[30],"which":[31],"are":[32,91],"learned":[33],"billions":[35],"of":[36,69,88,134],"have":[38],"shed":[39],"new":[40,83],"light":[41],"on":[42],"this":[43,46],"problem.":[44],"In":[45,119],"study,":[47,122],"we":[48,109,123],"investigate":[49],"how":[50],"to":[51],"efficiently":[52],"transfer":[53,76,135],"aligned":[54],"visual":[55,61,148],"and":[56,79,100,131,158],"textual":[57,98],"recognition":[62],"tasks.":[63,137],"We":[64],"first":[65],"revisit":[66],"the":[67,70,74,86,89,97,112,120,129],"role":[68],"linear":[71],"classifier":[72,90,113],"vanilla":[75],"learning":[77,136],"framework,":[78],"then":[80],"propose":[81],"paradigm":[84,127],"where":[85],"parameters":[87],"initialized":[92],"semantic":[94],"targets":[95],"encoder":[99],"remain":[101],"fixed":[102],"during":[103],"optimization.":[104],"To":[105],"provide":[106],"comparison,":[108],"also":[110],"initialize":[111],"various":[117],"resources.":[118],"empirical":[121],"demonstrate":[124],"that":[125,150],"our":[126,142],"improves":[128],"performance":[130],"training":[132],"speed":[133],"With":[138],"only":[139],"minor":[140],"modifications,":[141],"approach":[143],"proves":[144],"effective":[145],"across":[146],"17":[147],"datasets":[149],"span":[151],"three":[152],"different":[153],"data":[154],"domains:":[155],"image,":[156],"video,":[157],"3D":[159],"point":[160],"cloud.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}