{"id":"https://openalex.org/W4415536314","doi":"https://doi.org/10.1145/3746027.3755492","title":"Compositional Zero-Shot Learning with Contextualized Cues and Adaptive Contrastive Training","display_name":"Compositional Zero-Shot Learning with Contextualized Cues and Adaptive Contrastive Training","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536314","doi":"https://doi.org/10.1145/3746027.3755492"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755492","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755492","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":"conference-paper","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/A5057838181","display_name":"Yun Li","orcid":"https://orcid.org/0000-0003-4442-3825"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yun Li","raw_affiliation_strings":["CSIRO, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-4442-3825","affiliations":[{"raw_affiliation_string":"CSIRO, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I1292875679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052731721","display_name":"Lina Yao","orcid":"https://orcid.org/0000-0002-4149-839X"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lina Yao","raw_affiliation_strings":["CSIRO, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-4149-839X","affiliations":[{"raw_affiliation_string":"CSIRO, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I1292875679"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038805046","display_name":"Zhe Liu","orcid":"https://orcid.org/0000-0003-2692-2110"},"institutions":[{"id":"https://openalex.org/I1342911587","display_name":"Oracle (United States)","ror":"https://ror.org/006c77m33","country_code":"US","type":"company","lineage":["https://openalex.org/I1342911587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhe Liu","raw_affiliation_strings":["Oracle, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-2692-2110","affiliations":[{"raw_affiliation_string":"Oracle, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I1342911587"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.26881164,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4534","last_page":"4541"},"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":0.9909999966621399,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","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"}},{"id":"https://openalex.org/T12439","display_name":"Dental Research and COVID-19","score":0.9879999756813049,"subfield":{"id":"https://openalex.org/subfields/3500","display_name":"General Dentistry"},"field":{"id":"https://openalex.org/fields/35","display_name":"Dentistry"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4693000018596649},{"id":"https://openalex.org/keywords/linkage","display_name":"Linkage (software)","score":0.39959999918937683},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3961000144481659},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.3066999912261963},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.296099990606308},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.2728999853134155}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7573999762535095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5705000162124634},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4693000018596649},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.39959999918937683},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3961000144481659},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3734000027179718},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3222000002861023},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27239999175071716},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26109999418258667}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755492","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755492","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1948251820","https://openalex.org/W2982863468","https://openalex.org/W3158711590","https://openalex.org/W3162332195","https://openalex.org/W3198377975","https://openalex.org/W4312261477","https://openalex.org/W4385767718","https://openalex.org/W4387449204","https://openalex.org/W4390873732"],"related_works":[],"abstract_inverted_index":{"Compositional":[0],"Zero-Shot":[1],"Learning":[2],"(CZSL)":[3],"aims":[4],"to":[5,24,34],"recognize":[6],"unseen":[7],"combinations":[8],"of":[9],"seen":[10],"attributes":[11,30],"and":[12,27,31,52,55,68,79,93,114,136],"objects.":[13],"Current":[14],"CLIP-based":[15],"methods":[16],"in":[17,37,58,132],"CZSL,":[18,59],"despite":[19],"their":[20],"advancements,":[21],"often":[22],"fail":[23],"effectively":[25],"understand":[26],"link":[28],"the":[29,90,98],"objects":[32,82],"due":[33],"inherent":[35],"limitations":[36],"CLIP's":[38],"pretraining":[39],"mechanisms.":[40],"To":[41],"address":[42],"these":[43],"shortcomings,":[44],"this":[45],"paper":[46],"introduces":[47],"a":[48,103],"novel":[49],"framework,":[50],"Understanding":[51,66],"Linking":[53,91],"Attributes":[54,67,92],"Objects":[56,69,94],"(ULAO)":[57],"which":[60],"comprises":[61],"two":[62],"innovative":[63],"modules.":[64],"The":[65],"(UAO)":[70],"module":[71,96],"improves":[72,97],"primitive":[73,77],"understanding":[74,101],"by":[75,123],"sequential":[76],"prediction":[78],"leveraging":[80],"recognized":[81],"as":[83],"contextual":[84],"hints":[85],"for":[86],"attribute":[87],"classification.":[88],"Concurrently,":[89],"(LAO)":[95],"attribute-object":[99],"linkage":[100],"through":[102],"new":[104],"contrastive":[105],"learning":[106],"strategy":[107],"that":[108],"incorporates":[109],"tailored":[110],"hard":[111],"negative":[112],"generation":[113],"adaptive":[115],"loss":[116],"adjustments.":[117],"We":[118],"demonstrate":[119],"our":[120],"model's":[121],"superiority":[122],"showcasing":[124],"its":[125],"state-of-the-art":[126],"performance":[127],"across":[128],"three":[129],"benchmark":[130],"datasets":[131],"both":[133],"Closed-World":[134],"(CW)":[135],"Open-World":[137],"(OW)":[138],"scenarios.":[139]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}