{"id":"https://openalex.org/W4386065859","doi":"https://doi.org/10.1109/cvpr52729.2023.01470","title":"Learning Attention as Disentangler for Compositional Zero-Shot Learning","display_name":"Learning Attention as Disentangler for Compositional Zero-Shot Learning","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4386065859","doi":"https://doi.org/10.1109/cvpr52729.2023.01470"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52729.2023.01470","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.01470","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5085898591","display_name":"Shaozhe Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Shaozhe Hao","raw_affiliation_strings":["The University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056485902","display_name":"Kai Han","orcid":"https://orcid.org/0000-0002-7995-9999"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kai Han","raw_affiliation_strings":["The University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109582975","display_name":"Kenneth K. Wong","orcid":"https://orcid.org/0000-0001-8560-9007"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kwan-Yee K. Wong","raw_affiliation_strings":["The University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5085898591"],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":7.3835,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.97874923,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"15315","last_page":"15324"},"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":0.9998000264167786,"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":0.9998000264167786,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9695000052452087,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.958899974822998,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.7514675855636597},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6169720888137817},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5905190706253052},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5742506980895996},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5444059371948242},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5162396430969238},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47539815306663513},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.46453744173049927},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4339362382888794},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4229849874973297}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7514675855636597},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6169720888137817},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5905190706253052},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5742506980895996},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5444059371948242},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5162396430969238},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47539815306663513},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.46453744173049927},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4339362382888794},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4229849874973297},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52729.2023.01470","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.01470","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W88868203","https://openalex.org/W652269744","https://openalex.org/W1522301498","https://openalex.org/W1948251820","https://openalex.org/W1967686239","https://openalex.org/W1969616664","https://openalex.org/W1996309403","https://openalex.org/W2063386797","https://openalex.org/W2088227600","https://openalex.org/W2093848332","https://openalex.org/W2098411764","https://openalex.org/W2108598243","https://openalex.org/W2109586012","https://openalex.org/W2124033848","https://openalex.org/W2125560515","https://openalex.org/W2150295085","https://openalex.org/W2155241336","https://openalex.org/W2157423479","https://openalex.org/W2194775991","https://openalex.org/W2328725012","https://openalex.org/W2520762063","https://openalex.org/W2594270457","https://openalex.org/W2596142952","https://openalex.org/W2736809457","https://openalex.org/W2889167066","https://openalex.org/W2905449860","https://openalex.org/W2963091558","https://openalex.org/W2963518342","https://openalex.org/W2963960318","https://openalex.org/W2982863468","https://openalex.org/W2986385672","https://openalex.org/W3035084814","https://openalex.org/W3037198159","https://openalex.org/W3143107425","https://openalex.org/W3158711590","https://openalex.org/W3159481202","https://openalex.org/W3162332195","https://openalex.org/W3164354101","https://openalex.org/W3166396011","https://openalex.org/W3170971074","https://openalex.org/W4226464635","https://openalex.org/W4281722009","https://openalex.org/W4287022992","https://openalex.org/W4294170691","https://openalex.org/W4312400874","https://openalex.org/W4312539810","https://openalex.org/W4312578829","https://openalex.org/W4320013936","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6676497082","https://openalex.org/W6678360021","https://openalex.org/W6678800043","https://openalex.org/W6682222085","https://openalex.org/W6682691769","https://openalex.org/W6726923123","https://openalex.org/W6739901393","https://openalex.org/W6753898501","https://openalex.org/W6780184713","https://openalex.org/W6791353385","https://openalex.org/W6796334092","https://openalex.org/W6796967493","https://openalex.org/W6800217721"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W1482441085","https://openalex.org/W2966858528","https://openalex.org/W2151687600"],"abstract_inverted_index":{"Compositional":[0],"zero-shot":[1],"learning":[2,6,28],"(CZSL)":[3],"aims":[4],"at":[5,97],"visual":[7],"concepts":[8],"(i.e.,":[9],"attributes":[10],"and":[11,16,70,78,128,156],"objects)":[12],"from":[13,74,120],"seen":[14],"compositions":[15],"combining":[17,134],"concept":[18,49,68,72,90,121,136],"knowledge":[19],"into":[20],"unseen":[21,59],"compositions.":[22],"The":[23],"key":[24],"to":[25,40,46,56,87],"CZSL":[26,142],"is":[27],"the":[29,32,66,85,89,98,104,115,125,130],"disentanglement":[30],"of":[31,91],"attribute-object":[33],"composition.":[34],"To":[35,82],"this":[36],"end,":[37],"we":[38,54,63,93,102,123],"propose":[39],"exploit":[41],"cross-attentions":[42],"as":[43,109],"compositional":[44],"disentanglers":[45,86],"learn":[47,65,88],"disentangled":[48],"embeddings.":[50],"For":[51],"example,":[52],"if":[53],"want":[55],"recognize":[57],"an":[58],"composition":[60],"\u201cyellow":[61],"flower\u201d,":[62],"can":[64],"attribute":[67],"\u201cyellow\u201d":[69],"object":[71],"\u201cflower\u201d":[73],"different":[75,79],"yellow":[76],"objects":[77],"flowers":[80],"respectively.":[81],"further":[83],"constrain":[84],"interest,":[92],"employ":[94],"a":[95,110,160],"regularization":[96],"attention":[99],"level.":[100],"Specifically,":[101],"adapt":[103],"earth":[105],"mover's":[106],"distance":[107],"(EMD)":[108],"feature":[111],"similarity":[112],"metric":[113],"in":[114,153],"cross-attention":[116],"module.":[117],"Moreover,":[118],"benefiting":[119],"disentanglement,":[122],"improve":[124],"inference":[126],"process":[127],"tune":[129],"prediction":[131],"score":[132],"by":[133],"multiple":[135],"probabilities.":[137],"Comprehensive":[138],"experiments":[139],"on":[140],"three":[141],"benchmark":[143],"datasets":[144],"demonstrate":[145],"that":[146],"our":[147],"method":[148],"significantly":[149],"outperforms":[150],"previous":[151],"works":[152],"both":[154],"closed-":[155],"open-world":[157],"settings,":[158],"establishing":[159],"new":[161],"state-of-the-art.":[162],"Project":[163],"page:":[164],"https://haoosz.github.io/ade-czsl/":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":18}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}