{"id":"https://openalex.org/W3169149706","doi":"https://doi.org/10.1109/tmm.2021.3089017","title":"Disentangling Semantic-to-Visual Confusion for Zero-Shot Learning","display_name":"Disentangling Semantic-to-Visual Confusion for Zero-Shot Learning","publication_year":2021,"publication_date":"2021-06-14","ids":{"openalex":"https://openalex.org/W3169149706","doi":"https://doi.org/10.1109/tmm.2021.3089017","mag":"3169149706"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2021.3089017","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3089017","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.08605","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zihan Ye","orcid":"https://orcid.org/0000-0001-6462-6799"},"institutions":[{"id":"https://openalex.org/I308837","display_name":"Suzhou University of Science and Technology","ror":"https://ror.org/04en8wb91","country_code":"CN","type":"education","lineage":["https://openalex.org/I308837"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zihan Ye","raw_affiliation_strings":["Suzhou University of Science, and Technology, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"Suzhou University of Science, and Technology, Suzhou, China","institution_ids":["https://openalex.org/I308837"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fuyuan Hu","orcid":"https://orcid.org/0000-0002-6818-2221"},"institutions":[{"id":"https://openalex.org/I308837","display_name":"Suzhou University of Science and Technology","ror":"https://ror.org/04en8wb91","country_code":"CN","type":"education","lineage":["https://openalex.org/I308837"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuyuan Hu","raw_affiliation_strings":["Suzhou University of Science, and Technology, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"Suzhou University of Science, and Technology, Suzhou, China","institution_ids":["https://openalex.org/I308837"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fan Lyu","orcid":"https://orcid.org/0000-0002-0878-5485"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Lyu","raw_affiliation_strings":["Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Linyan Li","orcid":"https://orcid.org/0000-0001-6142-4139"},"institutions":[{"id":"https://openalex.org/I4210117682","display_name":"Suzhou Institute of Trade & Commerce","ror":"https://ror.org/02gdweq07","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210117682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linyan Li","raw_affiliation_strings":["Suzhou Institute of Trade, and Commerce, Suzhou, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"Suzhou Institute of Trade, and Commerce, Suzhou, Jiangsu, China","institution_ids":["https://openalex.org/I4210117682"]}]},{"author_position":"last","author":{"id":null,"display_name":"Kaizhu Huang","orcid":"https://orcid.org/0000-0002-3034-9639"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaizhu Huang","raw_affiliation_strings":["Department of Electrical, and Electronic Engineering, Xi&#x2019;an Jiaotong-Liverpool University, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"Department of Electrical, and Electronic Engineering, Xi&#x2019;an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I308837"],"apc_list":null,"apc_paid":null,"fwci":2.6592,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.91512515,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"24","issue":null,"first_page":"2828","last_page":"2840"},"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":0.4968999922275543,"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":0.4968999922275543,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.37209999561309814,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.03310000151395798,"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/discriminative-model","display_name":"Discriminative model","score":0.7687000036239624},{"id":"https://openalex.org/keywords/unavailability","display_name":"Unavailability","score":0.7002000212669373},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6104000210762024},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5950999855995178},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5929999947547913},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.548799991607666},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5236999988555908},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5042999982833862}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.76910001039505},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7687000036239624},{"id":"https://openalex.org/C2780505938","wikidata":"https://www.wikidata.org/wiki/Q17093282","display_name":"Unavailability","level":2,"score":0.7002000212669373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6761999726295471},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6104000210762024},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5950999855995178},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5929999947547913},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.548799991607666},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5236999988555908},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5042999982833862},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4968000054359436},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47780001163482666},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3935999870300293},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3634999990463257},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36090001463890076},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2856999933719635},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2021.3089017","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3089017","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2106.08605","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.08605","pdf_url":"https://arxiv.org/pdf/2106.08605","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2106.08605","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.08605","pdf_url":"https://arxiv.org/pdf/2106.08605","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2456155595","display_name":null,"funder_award_id":"61876155","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G254018693","display_name":null,"funder_award_id":"61801323","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2708528540","display_name":null,"funder_award_id":"BE2020006-4B","funder_id":"https://openalex.org/F4320327777","funder_display_name":"Jiangsu Provincial Key Research and Development Program"},{"id":"https://openalex.org/G2758043104","display_name":null,"funder_award_id":"61876121","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8074345263","display_name":null,"funder_award_id":"62002254","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8955768672","display_name":null,"funder_award_id":"BE2017663","funder_id":"https://openalex.org/F4320327777","funder_display_name":"Jiangsu Provincial Key Research and Development Program"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327777","display_name":"Jiangsu Provincial Key Research and Development Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W652269744","https://openalex.org/W1492420801","https://openalex.org/W2032699694","https://openalex.org/W2044913453","https://openalex.org/W2050398567","https://openalex.org/W2096733369","https://openalex.org/W2098411764","https://openalex.org/W2099471712","https://openalex.org/W2128532956","https://openalex.org/W2171061940","https://openalex.org/W2194775991","https://openalex.org/W2289084343","https://openalex.org/W2334493732","https://openalex.org/W2398118205","https://openalex.org/W2400717490","https://openalex.org/W2405223529","https://openalex.org/W2407797316","https://openalex.org/W2435696002","https://openalex.org/W2464503653","https://openalex.org/W2596142952","https://openalex.org/W2611632661","https://openalex.org/W2621368668","https://openalex.org/W2799215068","https://openalex.org/W2883124384","https://openalex.org/W2886710928","https://openalex.org/W2887567284","https://openalex.org/W2889143422","https://openalex.org/W2899867883","https://openalex.org/W2912423076","https://openalex.org/W2937642574","https://openalex.org/W2962716320","https://openalex.org/W2962824231","https://openalex.org/W2963960318","https://openalex.org/W2964086552","https://openalex.org/W2965069339","https://openalex.org/W2982234480","https://openalex.org/W3024314529","https://openalex.org/W3034359780","https://openalex.org/W3034379915","https://openalex.org/W3034942609","https://openalex.org/W3035466936","https://openalex.org/W3035724178","https://openalex.org/W3089741414","https://openalex.org/W3121070744","https://openalex.org/W3143107425","https://openalex.org/W3174683988","https://openalex.org/W3182605419","https://openalex.org/W6640963894","https://openalex.org/W6675751002","https://openalex.org/W6678470764","https://openalex.org/W6682691769","https://openalex.org/W6741832134","https://openalex.org/W6749074686","https://openalex.org/W6762466240","https://openalex.org/W6766206147","https://openalex.org/W6779371956","https://openalex.org/W6917178471"],"related_works":[],"abstract_inverted_index":{"Using":[0],"generative":[1],"models":[2],"to":[3,17,31,54,80,160,163],"synthesize":[4],"visual":[5,34],"features":[6],"from":[7,36,134],"semantic":[8],"distribution":[9,144],"is":[10,28],"one":[11],"of":[12,57],"the":[13,44,55,102,122,135,164],"most":[14],"popular":[15],"solutions":[16],"ZSL":[18],"image":[19],"classification":[20],"in":[21,60,68,101,125],"recent":[22],"years.":[23],"The":[24],"triplet":[25,73],"loss":[26,74],"(TL)":[27],"popularly":[29],"used":[30],"generate":[32],"realistic":[33,143],"distributions":[35],"semantics":[37],"by":[38],"automatically":[39],"searching":[40],"discriminative":[41],"representations.":[42],"However,":[43],"traditional":[45],"TL":[46],"cannot":[47],"search":[48,81],"reliable":[49],"unseen":[50,58,149],"disentangled":[51,98,123,136],"representations":[52,100,124],"due":[53],"unavailability":[56],"classes":[59,91],"ZSL.":[61],"To":[62],"alleviate":[63],"this":[64,69],"drawback,":[65],"we":[66,106],"propose":[67],"work":[70],"a":[71,82,108,141],"multi-modal":[72,78],"(MMTL)":[75],"which":[76,94],"utilizes":[77],"information":[79],"<italic":[83],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[84],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">disentangled</i>":[85],"representation":[86],"space.":[87,104],"As":[88],"such,":[89],"all":[90],"can":[92,95,158],"interplay":[93],"benefit":[96],"learning":[97],"class":[99],"searched":[103],"Furthermore,":[105],"develop":[107],"novel":[109],"model":[110,157],"called":[111],"Disentangling":[112],"Class":[113],"Representation":[114],"Generative":[115],"Adversarial":[116],"Network":[117],"(DCR-GAN)":[118],"focusing":[119],"on":[120,166],"exploiting":[121],"training,":[126],"feature":[127],"synthesis,":[128],"and":[129,148],"final":[130],"recognition":[131],"stages.":[132],"Benefiting":[133],"representations,":[137],"DCR-GAN":[138],"could":[139],"fit":[140],"more":[142],"over":[145],"both":[146],"seen":[147],"features.":[150],"Extensive":[151],"experiments":[152],"show":[153],"that":[154],"our":[155],"proposed":[156],"lead":[159],"superior":[161],"performance":[162],"state-of-the-arts":[165],"four":[167],"benchmark":[168],"datasets.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2021-06-22T00:00:00"}