{"id":"https://openalex.org/W4415539521","doi":"https://doi.org/10.1145/3746027.3755208","title":"Compositional Zero-shot Learning via Progressive Language-based Observations","display_name":"Compositional Zero-shot Learning via Progressive Language-based Observations","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539521","doi":"https://doi.org/10.1145/3746027.3755208"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3755208","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755208","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/A5100412889","display_name":"Lin Li","orcid":"https://orcid.org/0000-0002-5678-4487"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Lin Li","raw_affiliation_strings":["AI Chip Center for Emerging Smart Systems, Hong Kong, China and The Hong Kong University of Science and Technology, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"AI Chip Center for Emerging Smart Systems, Hong Kong, China and The Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063404844","display_name":"Guikun Chen","orcid":"https://orcid.org/0000-0002-9227-007X"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guikun Chen","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100422460","display_name":"Zhen Wang","orcid":"https://orcid.org/0009-0008-1091-7994"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhen Wang","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101485989","display_name":"Jun Xiao","orcid":"https://orcid.org/0000-0002-6142-9914"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Xiao","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100336360","display_name":"Long Chen","orcid":"https://orcid.org/0000-0001-6148-9709"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Long Chen","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100412889"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":2.3568,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91575079,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3827","last_page":"3836"},"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":0.993399977684021,"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":0.993399977684021,"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/T11894","display_name":"Radiology practices and education","score":0.9702000021934509,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9641000032424927,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6470999717712402},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6133000254631042},{"id":"https://openalex.org/keywords/composition","display_name":"Composition (language)","score":0.38920000195503235},{"id":"https://openalex.org/keywords/series","display_name":"Series (stratigraphy)","score":0.3513000011444092},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.349700003862381}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6872000098228455},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6470999717712402},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6133000254631042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5651999711990356},{"id":"https://openalex.org/C40231798","wikidata":"https://www.wikidata.org/wiki/Q1333743","display_name":"Composition (language)","level":2,"score":0.38920000195503235},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3779999911785126},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32429999113082886},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2535000145435333}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3755208","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755208","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"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-167667","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-167667","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6689777572","display_name":null,"funder_award_id":"226-2025-00057","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8143213088","display_name":null,"funder_award_id":"2024YFB3312900","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W3088241548","https://openalex.org/W3198377975","https://openalex.org/W4382240738","https://openalex.org/W4386075969","https://openalex.org/W4386075985","https://openalex.org/W4386890345","https://openalex.org/W4400890495"],"related_works":[],"abstract_inverted_index":{"Compositional":[0],"zero-shot":[1],"learning":[2],"aims":[3],"to":[4,27,131,146,183],"recognize":[5],"unseen":[6],"stateobject":[7],"compositions":[8,29],"by":[9,90],"leveraging":[10],"known":[11],"primitives":[12,23],"(state":[13],"and":[14,24,41,173],"object)":[15],"during":[16],"training.":[17],"However,":[18],"effectively":[19],"modeling":[20],"interactions":[21],"between":[22],"generalizing":[25],"knowledge":[26],"novel":[28],"remains":[30],"a":[31,71,77,119,136,157,162,174],"perennial":[32],"challenge.":[33],"There":[34],"are":[35],"two":[36,155],"crucial":[37],"factors:":[38],"large":[39,179],"object-conditioned":[40],"state-conditioned":[42],"variance,":[43],"i.e.,":[44],"the":[45,63,110,129,148,167],"appearance":[46],"of":[47,112,121,169],"states":[48],"(or":[49,59],"objects)":[50],"can":[51,66,87,107],"vary":[52],"significantly":[53],"when":[54],"combined":[55],"with":[56,150,161],"different":[57],"objects":[58],"states).":[60],"For":[61],"instance,":[62],"state":[64],"\"old\"":[65],"signify":[67],"vintage":[68],"design":[69],"for":[70,76],"\"car\"":[72],"or":[73,124],"advanced":[74],"age":[75],"\"cat\".":[78],"In":[79],"this":[80],"paper,":[81],"we":[82,100],"argue":[83],"that":[84,127],"these":[85],"variances":[86],"be":[88],"mitigated":[89],"predicting":[91],"composition":[92],"categories":[93],"based":[94],"on":[95,190],"salient":[96],"observation":[97,113,151],"cues.":[98,114,187],"Therefore,":[99],"propose":[101],"Progressive":[102],"Language-based":[103],"Observations":[104],"(PLO),":[105],"which":[106],"automatically":[108],"determine":[109],"order":[111,168],"These":[115],"\"observation":[116],"cues\"":[117],"comprise":[118],"series":[120],"primitive":[122,170],"concepts":[123],"graduated":[125,185],"descriptions":[126],"allow":[128],"model":[130,149],"understand":[132],"image":[133],"content":[134],"in":[135,196],"step-by-step":[137],"manner.":[138],"Specifically,":[139],"PLO":[140],"adopts":[141],"pre-trained":[142],"vision-language":[143],"models":[144,181],"(VLMs)":[145],"empower":[147],"capabilities.We":[152],"further":[153],"devise":[154],"variants:":[156],"twostep":[158],"method":[159],"(PLO-VLM)":[160],"pre-observing":[163],"classifier":[164],"dynamically":[165],"selecting":[166],"concept-based":[171],"cues,":[172],"multistep":[175],"approach":[176],"(PLO-LLM)":[177],"using":[178],"language":[180],"(LLMs)":[182],"craft":[184],"description-based":[186],"Extensive":[188],"tests":[189],"three":[191],"datasets":[192],"show":[193],"PLO's":[194],"effectiveness":[195],"compositional":[197],"recognition.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-25T00:00:00"}