{"id":"https://openalex.org/W4415309744","doi":"https://doi.org/10.1007/s11263-026-02874-4","title":"Semantic-Guided Fine-Tuning of Foundation Model for Long-Tailed Visual Recognition","display_name":"Semantic-Guided Fine-Tuning of Foundation Model for Long-Tailed Visual Recognition","publication_year":2026,"publication_date":"2026-06-18","ids":{"openalex":"https://openalex.org/W4415309744","doi":"https://doi.org/10.1007/s11263-026-02874-4"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-026-02874-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-026-02874-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-026-02874-4.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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11263-026-02874-4.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113021609","display_name":"Yufei Peng","orcid":"https://orcid.org/0009-0008-8890-5248"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yufei Peng","raw_affiliation_strings":["Department of Computer Science, Hong Kong Baptist University, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hong Kong Baptist University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100383751","display_name":"Yonggang Zhang","orcid":"https://orcid.org/0000-0003-4548-1111"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yonggang Zhang","raw_affiliation_strings":["Department of Computer Science, Hong Kong Baptist University, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hong Kong Baptist University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038516431","display_name":"Yiu\u2010ming Cheung","orcid":"https://orcid.org/0000-0001-7629-4648"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Yiu-ming Cheung","raw_affiliation_strings":["Department of Computer Science, Hong Kong Baptist University, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0001-7629-4648","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hong Kong Baptist University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I141568987"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5038516431"],"corresponding_institution_ids":["https://openalex.org/I141568987"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":{"value":2890,"currency":"EUR","value_usd":3690},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01425041,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"134","issue":"7","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.4433000087738037,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.4433000087738037,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.42089998722076416,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.3725999891757965,"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/semantics","display_name":"Semantics (computer science)","score":0.6151999831199646},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5920000076293945},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5131000280380249},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5034000277519226},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.45100000500679016},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.44859999418258667},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44339999556541443},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4156000018119812},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.36149999499320984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7777000069618225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6173999905586243},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6151999831199646},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5920000076293945},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5131000280380249},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5034000277519226},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.45100000500679016},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.44859999418258667},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44339999556541443},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43320000171661377},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4156000018119812},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36149999499320984},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3578999936580658},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C2777055276","wikidata":"https://www.wikidata.org/wiki/Q7936580","display_name":"Visual approach","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3000999987125397},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2971000075340271},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C168820333","wikidata":"https://www.wikidata.org/wiki/Q448889","display_name":"Visual inspection","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s11263-026-02874-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-026-02874-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-026-02874-4.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"},{"id":"pmh:oai:arXiv.org:2507.12807","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.12807","pdf_url":"https://arxiv.org/pdf/2507.12807","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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.2507.12807","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.12807","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1007/s11263-026-02874-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-026-02874-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-026-02874-4.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":[],"awards":[{"id":"https://openalex.org/G5559734815","display_name":null,"funder_award_id":"12202924","funder_id":"https://openalex.org/F4320329815","funder_display_name":"Hong Kong Government"},{"id":"https://openalex.org/G8090164539","display_name":null,"funder_award_id":"12202025","funder_id":"https://openalex.org/F4320329815","funder_display_name":"Hong Kong Government"},{"id":"https://openalex.org/G8154245037","display_name":null,"funder_award_id":"12201323","funder_id":"https://openalex.org/F4320329815","funder_display_name":"Hong Kong Government"}],"funders":[{"id":"https://openalex.org/F4320329815","display_name":"Hong Kong Government","ror":"https://ror.org/034179816"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415309744.pdf","grobid_xml":"https://content.openalex.org/works/W4415309744.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"The":[1,133],"variance":[2],"in":[3,12,15,48,252,255],"class-wise":[4],"sample":[5],"sizes":[6],"within":[7],"long-tailed":[8,49,96,256],"scenarios":[9],"often":[10],"results":[11],"degraded":[13],"performance":[14,179,254],"less":[16,187],"frequent":[17],"classes.":[18],"Fortunately,":[19],"foundation":[20,93],"models,":[21],"pre-trained":[22,46],"on":[23,45,149,228,242],"vast":[24],"open-world":[25],"datasets,":[26],"demonstrate":[27,245],"strong":[28],"potential":[29],"for":[30,95,181,189],"this":[31,76,202],"task":[32],"due":[33],"to":[34,125,146,163,185,216],"their":[35],"generalizable":[36],"representation,":[37],"which":[38,100,212],"promotes":[39],"the":[40,60,64,69,109,127,130,139,144,154,157,164,170,174,182,190,195,218,223,237,246,249],"development":[41],"of":[42,92,129,248],"adaptive":[43],"strategies":[44],"models":[47],"learning.":[50,257],"Advanced":[51],"fine-tuning":[52,91,111,128],"methods":[53],"typically":[54],"adjust":[55],"visual":[56,70,97,110,131,158],"encoders":[57],"while":[58],"neglecting":[59],"semantics":[61],"derived":[62,104],"from":[63,105],"frozen":[65],"text":[66],"encoder,":[67],"overlooking":[68],"and":[71,142,159,232],"textual":[72,106,160],"alignment.":[73],"To":[74,200],"strengthen":[75],"alignment,":[77],"we":[78,114,204],"propose":[79,205],"a":[80,85,206],"novel":[81,207],"approach,":[82],"S":[83],"em":[84],"ntic-":[86],"g":[87],"uid":[88],"e":[89],"d":[90],"model":[94,145],"recognition":[98],"(Sage),":[99],"incorporates":[101],"semantic":[102,123],"guidance":[103,124,135],"modality":[107],"into":[108,236],"process.":[112],"Specifically,":[113],"introduce":[115],"an":[116],"SG-Adapter":[117],"that":[118],"integrates":[119],"class":[120,184],"descriptions":[121],"as":[122],"guide":[126],"encoder.":[132],"introduced":[134],"is":[136,198,213,233],"passed":[137],"through":[138],"attention":[140],"mechanism":[141],"enables":[143],"focus":[147],"more":[148],"semantically":[150],"relevant":[151],"content,":[152],"strengthening":[153],"alignment":[155,197],"between":[156],"modalities.":[161],"Due":[162],"inconsistent":[165,225],"class-conditional":[166],"distributions":[167],"neglected":[168],"by":[169,222],"existing":[171],"loss":[172,238],"function,":[173],"resulting":[175],"prediction":[176,219],"bias":[177,220],"causes":[178],"improvements":[180],"tail":[183],"be":[186],"than":[188],"head":[191],"class,":[192],"even":[193],"when":[194],"multi-modal":[196],"enhanced.":[199],"address":[201],"challenge,":[203],"distribution":[208,226],"mismatch-aware":[209],"compensation":[210],"factor,":[211],"specifically":[214],"designed":[215],"rectify":[217],"caused":[221],"ignored":[224],"based":[227],"our":[229],"theoretical":[230],"analysis,":[231],"seamlessly":[234],"integrated":[235],"function.":[239],"Extensive":[240],"experiments":[241],"benchmark":[243],"datasets":[244],"effectiveness":[247],"proposed":[250],"Sage":[251],"enhancing":[253]},"counts_by_year":[],"updated_date":"2026-06-20T20:08:15.867695","created_date":"2025-10-18T00:00:00"}