{"id":"https://openalex.org/W4415539351","doi":"https://doi.org/10.1145/3746027.3755564","title":"DART: Dual Adaptive Refinement Transfer for Open-Vocabulary Multi-Label Recognition","display_name":"DART: Dual Adaptive Refinement Transfer for Open-Vocabulary Multi-Label Recognition","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539351","doi":"https://doi.org/10.1145/3746027.3755564"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755564","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-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/A5004929949","display_name":"Haijing Liu","orcid":"https://orcid.org/0009-0000-4772-9569"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haijing Liu","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-4772-9569","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085835397","display_name":"Tao Pu","orcid":"https://orcid.org/0000-0001-9564-8288"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Pu","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9564-8288","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061828638","display_name":"Hefeng Wu","orcid":"https://orcid.org/0000-0002-2132-6515"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hefeng Wu","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-2132-6515","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088124671","display_name":"Keze Wang","orcid":"https://orcid.org/0000-0002-7817-8306"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keze Wang","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7817-8306","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100412937","display_name":"Liang Lin","orcid":"https://orcid.org/0000-0003-2248-3755"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Lin","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2248-3755","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5004929949"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15608472,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4708","last_page":"4717"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9976999759674072,"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":0.9976999759674072,"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":0.996999979019165,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9909999966621399,"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/leverage","display_name":"Leverage (statistics)","score":0.725600004196167},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5956000089645386},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4927000105381012},{"id":"https://openalex.org/keywords/statistical-relational-learning","display_name":"Statistical relational learning","score":0.46779999136924744},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4194999933242798},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4032999873161316},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.40049999952316284},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.3984000086784363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7353000044822693},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.725600004196167},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5956000089645386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5852000117301941},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4927000105381012},{"id":"https://openalex.org/C177877439","wikidata":"https://www.wikidata.org/wiki/Q7604413","display_name":"Statistical relational learning","level":3,"score":0.46779999136924744},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4390000104904175},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4194999933242798},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.3806999921798706},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.3799000084400177},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.37709999084472656},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.3393999934196472},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2937999963760376},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2924000024795532},{"id":"https://openalex.org/C2779178101","wikidata":"https://www.wikidata.org/wiki/Q6987274","display_name":"Negative transfer","level":3,"score":0.273499995470047},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2590999901294708},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755564","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1972306304","https://openalex.org/W2413850928","https://openalex.org/W2531409750","https://openalex.org/W2943963440","https://openalex.org/W2946373483","https://openalex.org/W2962858109","https://openalex.org/W2982112268","https://openalex.org/W2998019206","https://openalex.org/W3082756280","https://openalex.org/W3109067582","https://openalex.org/W3194282644","https://openalex.org/W3216466215","https://openalex.org/W4288083516","https://openalex.org/W4313331808","https://openalex.org/W4382450414","https://openalex.org/W4386065742","https://openalex.org/W4386066076","https://openalex.org/W4388145549","https://openalex.org/W4390357571","https://openalex.org/W4390873312","https://openalex.org/W4396542738","https://openalex.org/W4402130813","https://openalex.org/W4412490704"],"related_works":[],"abstract_inverted_index":{"Open-Vocabulary":[0],"Multi-Label":[1],"Recognition":[2],"(OV-MLR)":[3],"aims":[4],"to":[5,21,28,55,155,168,171],"identify":[6],"multiple":[7],"seen":[8],"and":[9,24,52,150],"unseen":[10,68],"object":[11],"categories":[12],"within":[13],"an":[14,97,128],"image,":[15],"requiring":[16],"both":[17],"precise":[18],"intra-class":[19,95,186],"localization":[20,48,119],"pinpoint":[22],"objects":[23],"effective":[25],"inter-class":[26,126,180],"reasoning":[27],"model":[29],"complex":[30],"category":[31],"dependencies.":[32],"While":[33],"Vision-Language":[34],"Pre-training":[35],"(VLP)":[36],"models":[37],"offer":[38],"a":[39,85,108,134,145],"strong":[40],"open-vocabulary":[41],"foundation,":[42],"they":[43],"often":[44],"struggle":[45],"with":[46,107],"fine-grained":[47],"under":[49,188],"weak":[50,189],"supervision":[51,190],"typically":[53],"fail":[54],"explicitly":[56,172],"leverage":[57],"structured":[58,141],"relational":[59,158,176],"knowledge":[60,142,177],"beyond":[61],"basic":[62],"semantics,":[63],"limiting":[64],"performance":[65],"especially":[66],"for":[67,125,178,191],"classes.":[69],"To":[70],"overcome":[71],"these":[72],"limitations,":[73],"we":[74],"propose":[75],"the":[76,165],"Dual":[77],"Adaptive":[78,98,129],"Refinement":[79,99],"Transfer":[80,130],"(DART)":[81],"framework.":[82],"DART":[83,163,201],"enhances":[84],"frozen":[86],"VLP":[87],"backbone":[88],"via":[89],"two":[90],"synergistic":[91],"adaptive":[92,179,185],"modules.":[93],"For":[94],"refinement,":[96],"Module":[100,131],"(ARM)":[101],"refines":[102],"patch":[103],"features":[104],"adaptively,":[105],"coupled":[106],"novel":[109],"Weakly":[110],"Supervised":[111],"Patch":[112],"Selecting":[113],"(WPS)":[114],"loss":[115],"that":[116,199],"enables":[117],"discriminative":[118],"using":[120,140],"only":[121],"image-level":[122],"labels.":[123],"Concurrently,":[124],"transfer,":[127],"(ATM)":[132],"leverages":[133],"Class":[135],"Relationship":[136],"Graph":[137],"(CRG),":[138],"constructed":[139],"mined":[143],"from":[144],"Large":[146],"Language":[147],"Model":[148],"(LLM),":[149],"employs":[151],"graph":[152],"attention":[153],"network":[154],"adaptively":[156],"transfer":[157,181],"information":[159],"between":[160],"class":[161],"representations.":[162],"is":[164],"first":[166],"framework,":[167],"our":[169,200],"knowledge,":[170],"integrate":[173],"external":[174],"LLM-derived":[175],"while":[182],"simultaneously":[183],"performing":[184],"refinement":[187],"OV-MLR.":[192],"Extensive":[193],"experiments":[194],"on":[195],"challenging":[196],"benchmarks":[197],"demonstrate":[198],"achieves":[202],"new":[203],"state-of-the-art":[204],"performance,":[205],"validating":[206],"its":[207],"effectiveness.":[208]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-25T00:00:00"}