{"id":"https://openalex.org/W7137878640","doi":"https://doi.org/10.1609/aaai.v40i8.37600","title":"Dual-Phase Visual-Language Pretraining and Adaptation for Long-Tailed Multi-Label Recognition","display_name":"Dual-Phase Visual-Language Pretraining and Adaptation for Long-Tailed Multi-Label Recognition","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137878640","doi":"https://doi.org/10.1609/aaai.v40i8.37600"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i8.37600","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37600","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i8.37600","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047297105","display_name":"Yinjin Li","orcid":"https://orcid.org/0000-0003-4224-8728"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongcheng Li","raw_affiliation_strings":["Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129741489","display_name":"Xuekuan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuekuan Wang","raw_affiliation_strings":["Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129719292","display_name":"Zhifei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifei Zhang","raw_affiliation_strings":["Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064237960","display_name":"Cairong Zhao","orcid":"https://orcid.org/0000-0001-6745-9674"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cairong Zhao","raw_affiliation_strings":["Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"8","first_page":"6690","last_page":"6698"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.8432000279426575,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.8432000279426575,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.03370000049471855,"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/T10028","display_name":"Topic Modeling","score":0.01769999973475933,"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/adaptation","display_name":"Adaptation (eye)","score":0.7305999994277954},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6757000088691711},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5608999729156494},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.4350000023841858},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.4092999994754791},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.3824999928474426},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.35499998927116394},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.35429999232292175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7559000253677368},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7305999994277954},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6757000088691711},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5807999968528748},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5608999729156494},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4431000053882599},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4350000023841858},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.4092999994754791},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.3824999928474426},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3474000096321106},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29829999804496765},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C2777317252","wikidata":"https://www.wikidata.org/wiki/Q18393516","display_name":"Rare events","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.25850000977516174}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i8.37600","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37600","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37600","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i8.37600","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37600","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7573803067207336}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Long-Tailed":[0],"Multi-Label":[1],"Recognition":[2],"(LTML)":[3],"is":[4,97],"a":[5,44,63,82,116],"critical":[6],"yet":[7],"challenging":[8],"task":[9],"due":[10],"to":[11,35,68,109,111],"two":[12],"core":[13],"issues:":[14],"the":[15,26,53,89,107,122,124],"severe":[16],"scarcity":[17],"of":[18,146],"training":[19],"samples":[20],"for":[21,130],"rare":[22],"\"tail\"":[23],"classes,":[24],"and":[25,49,77,84,137,148,158],"complex":[27],"co-occurrence":[28,131],"patterns":[29],"among":[30],"labels":[31],"that":[32,72],"often":[33],"lead":[34],"biased":[36],"models.":[37],"To":[38],"address":[39],"this,":[40],"we":[41,93],"propose":[42],"DP-VLPA,":[43],"novel":[45],"Dual-Phase":[46],"Visual-Language":[47],"Pretraining":[48],"Adaptation":[50],"framework.":[51],"In":[52,88],"first":[54],"phase,":[55,92],"our":[56],"Structured":[57],"Tail-Aware":[58],"Generation":[59],"(STAG)":[60],"module":[61],"employs":[62],"Large":[64],"Language":[65],"Model":[66],"(LLM)":[67],"create":[69],"detailed":[70],"descriptions":[71],"explicitly":[73,120],"emphasize":[74],"tail":[75],"classes":[76],"their":[78],"contextual":[79],"relationships,":[80],"providing":[81],"strong":[83],"less-biased":[85],"feature":[86],"foundation.":[87],"second":[90],"adaptation":[91],"ensure":[94],"this":[95],"knowledge":[96],"applied":[98],"effectively.":[99],"A":[100],"Dynamic":[101],"Query":[102],"Reweighting":[103],"(DQR)":[104],"mechanism":[105],"forces":[106],"model":[108,123],"attend":[110],"crucial":[112],"tail-class":[113],"evidence.":[114],"Simultaneously,":[115],"Co-occurrence-Aware":[117],"(COA)":[118],"loss":[119],"teaches":[121],"statistical":[125],"dependencies":[126],"between":[127],"labels,":[128],"correcting":[129],"biases.":[132],"Extensive":[133],"experiments":[134],"on":[135],"VOC-LT":[136],"COCO-LT":[138],"datasets":[139],"demonstrate":[140],"state-of-the-art":[141],"performance,":[142],"achieving":[143],"mAP":[144],"scores":[145],"90.72%":[147],"74.42%":[149],"respectively":[150],"-":[151],"surpassing":[152],"previous":[153],"best":[154],"methods":[155],"by":[156],"2.84%":[157],"8.23%.":[159]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}