{"id":"https://openalex.org/W4414165866","doi":"https://doi.org/10.1109/tmm.2025.3607812","title":"Boosting Long-Tailed Recognition With Label Descriptor and Beyond","display_name":"Boosting Long-Tailed Recognition With Label Descriptor and Beyond","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414165866","doi":"https://doi.org/10.1109/tmm.2025.3607812"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3607812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3607812","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","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/A5101898915","display_name":"Zhengzhuo Xu","orcid":"https://orcid.org/0000-0003-4620-9187"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengzhuo Xu","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-4620-9187","affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036011791","display_name":"Ruikang Liu","orcid":"https://orcid.org/0000-0002-9828-5301"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruikang Liu","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003827815","display_name":"Zenghao Chai","orcid":"https://orcid.org/0000-0003-3709-4947"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zenghao Chai","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-3709-4947","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100683128","display_name":"Qi Yan","orcid":"https://orcid.org/0000-0002-5236-9673"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiyan Qi","raw_affiliation_strings":["International Digital Economy Academy, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Digital Economy Academy, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lei Li","orcid":"https://orcid.org/0000-0002-4514-3617"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Li","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-4514-3617","affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081662508","display_name":"Haiqin Yang","orcid":"https://orcid.org/0000-0001-5453-476X"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiqin Yang","raw_affiliation_strings":["Shenzhen Technology University, Shenzhen, China","International Digital Economy Academy, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-5453-476X","affiliations":[{"raw_affiliation_string":"Shenzhen Technology University, Shenzhen, China","institution_ids":["https://openalex.org/I4210152380"]},{"raw_affiliation_string":"International Digital Economy Academy, Shenzhen, China","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Chun Yuan","orcid":"https://orcid.org/0000-0002-3590-6676"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Yuan","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-3590-6676","affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1215457,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":null,"first_page":"8618","last_page":"8627"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.7876999974250793,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.7876999974250793,"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/T10820","display_name":"Fuzzy Logic and Control Systems","score":0.7398999929428101,"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/T10320","display_name":"Neural Networks and Applications","score":0.7073000073432922,"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/boosting","display_name":"Boosting (machine learning)","score":0.7340999841690063},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6269000172615051},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4440999925136566},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.4268999993801117},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41920000314712524},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4180999994277954},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41370001435279846},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.3691999912261963},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.3546000123023987},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3522999882698059}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8544999957084656},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.7340999841690063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7265999913215637},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6269000172615051},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5813000202178955},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4440999925136566},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.4268999993801117},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41920000314712524},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4180999994277954},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41370001435279846},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.31709998846054077},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.30959999561309814},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3052999973297119},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C6528762","wikidata":"https://www.wikidata.org/wiki/Q1574298","display_name":"Traffic sign recognition","level":4,"score":0.29809999465942383},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.27889999747276306},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2721000015735626},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2558000087738037},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3607812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3607812","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W153185079","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2610530220","https://openalex.org/W2616247523","https://openalex.org/W2732026016","https://openalex.org/W2797977484","https://openalex.org/W2962933664","https://openalex.org/W2963691377","https://openalex.org/W3000557356","https://openalex.org/W3096688134","https://openalex.org/W3128945844","https://openalex.org/W3174366534","https://openalex.org/W3176474016","https://openalex.org/W3177230409","https://openalex.org/W3194146976","https://openalex.org/W3198377975","https://openalex.org/W3201565470","https://openalex.org/W3204988419","https://openalex.org/W3215720729","https://openalex.org/W4214718285","https://openalex.org/W4225922615","https://openalex.org/W4283075937","https://openalex.org/W4285288414","https://openalex.org/W4285295127","https://openalex.org/W4285295719","https://openalex.org/W4312244159","https://openalex.org/W4312453657","https://openalex.org/W4312651322","https://openalex.org/W4312702685","https://openalex.org/W4312768099","https://openalex.org/W4312920106","https://openalex.org/W4312986563","https://openalex.org/W4313151233","https://openalex.org/W4313156423","https://openalex.org/W4386071547","https://openalex.org/W4386076553","https://openalex.org/W4386076681","https://openalex.org/W4386083102","https://openalex.org/W4386220752","https://openalex.org/W4386702786","https://openalex.org/W4390872508","https://openalex.org/W4402671127"],"related_works":[],"abstract_inverted_index":{"Long-Tailed":[0],"Recognition":[1],"(LTR)":[2],"poses":[3],"significant":[4],"challenges":[5,33],"due":[6],"to":[7,63,74,108,149,155,168],"the":[8,23,50,53,70,85,91,95,119,128,134,143,151,170,189],"heavily":[9],"imbalanced":[10],"nature":[11],"of":[12,26,49,55],"real-world":[13],"data,":[14],"which":[15],"severely":[16],"skews":[17],"data-driven":[18],"deep":[19],"neural":[20],"networks.":[21],"Despite":[22],"rapid":[24],"progress":[25],"Vision-Language":[27],"Models":[28],"(VLMs),":[29],"they":[30],"still":[31],"face":[32],"in":[34],"effectively":[35],"learning":[36],"from":[37],"long-tailed":[38],"visual":[39,138,158],"data.":[40],"In":[41],"this":[42,65],"paper,":[43],"we":[44,68,122,162],"present":[45],"a":[46,59,124,164,185],"comprehensive":[47],"analysis":[48],"reasons":[51],"behind":[52],"underperformance":[54],"VLMs":[56],"and":[57,83,97,132,192],"propose":[58,123,163],"hierarchical":[60,165],"inference":[61,166],"framework":[62],"address":[64,156],"issue.":[66],"Specifically,":[67],"prompt":[69,139],"large":[71],"language":[72],"models":[73],"generate":[75],"<italic":[76,101],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[77,102],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">sentence-level</i>":[78],"descriptors":[79],"for":[80],"class":[81],"labels":[82],"conduct":[84],"open":[86],"vocabulary":[87],"classification":[88],"by":[89,118,182],"computing":[90],"average":[92],"similarity":[93],"between":[94,153],"image":[96],"each":[98],"descriptor.":[99],"A":[100],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">reweighting</i>":[103],"mechanism":[104],"is":[105],"further":[106],"proposed":[107],"filter":[109],"out":[110],"uninformative":[111],"descriptors.":[112],"To":[113],"mitigate":[114],"model":[115,136],"bias":[116],"incurred":[117],"long-tail":[120],"distribution,":[121],"feature":[125,159],"adapter":[126],"with":[127],"logit":[129],"adjustment":[130],"technique":[131],"fine-tune":[133],"CLIP":[135],"via":[137],"tokens.":[140],"We":[141],"introduce":[142],"Shared":[144],"Feature":[145],"space":[146],"Mixup":[147],"(SFM)":[148],"enhance":[150],"interaction":[152],"modalities":[154],"tail":[157],"insufficiency.":[160],"Finally,":[161],"manner":[167],"combine":[169],"aforementioned":[171],"proposals.":[172],"Extensive":[173],"evaluations":[174],"demonstrate":[175],"that":[176],"our":[177],"approach":[178],"achieves":[179],"state-of-the-art":[180],"performance":[181],"fine-tuning":[183],"only":[184],"few":[186],"parameters":[187],"on":[188],"Places-LT,":[190],"ImageNet-LT,":[191],"iNaturalist":[193],"2018":[194],"benchmarks.":[195]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}