{"id":"https://openalex.org/W4402979069","doi":"https://doi.org/10.1109/icme57554.2024.10688100","title":"Visual Feature Disentanglement for Zero-Shot Learning","display_name":"Visual Feature Disentanglement for Zero-Shot Learning","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979069","doi":"https://doi.org/10.1109/icme57554.2024.10688100"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688100","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5114236907","display_name":"Qingzhi He","orcid":null},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingzhi He","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics,College of Computer Science and Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics,College of Computer Science and Technology,Nanjing,China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113794447","display_name":"Rong Quan","orcid":null},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Quan","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics,College of Computer Science and Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics,College of Computer Science and Technology,Nanjing,China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101481133","display_name":"Weifeng Yang","orcid":"https://orcid.org/0000-0002-4833-7185"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weifeng Yang","raw_affiliation_strings":["Nanjing Chenguang Group Co., Ltd,Department of Servo Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing Chenguang Group Co., Ltd,Department of Servo Technology,Nanjing,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061215231","display_name":"Jie Qin","orcid":"https://orcid.org/0000-0002-0306-534X"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Qin","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics,College of Computer Science and Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics,College of Computer Science and Technology,Nanjing,China","institution_ids":["https://openalex.org/I9842412"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9958000183105469,"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":0.9958000183105469,"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":0.9503999948501587,"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/shot","display_name":"Shot (pellet)","score":0.7139298915863037},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6580819487571716},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6248098611831665},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5924911499023438},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.544305145740509},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3886866867542267},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37292706966400146},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.0843016505241394}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.7139298915863037},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6580819487571716},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6248098611831665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5924911499023438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.544305145740509},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3886866867542267},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37292706966400146},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0843016505241394},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10688100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688100","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"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":35,"referenced_works":["https://openalex.org/W2070148066","https://openalex.org/W2128532956","https://openalex.org/W2171061940","https://openalex.org/W2398118205","https://openalex.org/W2523479226","https://openalex.org/W2533598788","https://openalex.org/W2762085884","https://openalex.org/W2924476266","https://openalex.org/W2948162522","https://openalex.org/W2962824231","https://openalex.org/W2963283377","https://openalex.org/W2963499153","https://openalex.org/W2963960318","https://openalex.org/W2964105864","https://openalex.org/W2979571231","https://openalex.org/W2982407353","https://openalex.org/W3000538487","https://openalex.org/W3009454144","https://openalex.org/W3034359780","https://openalex.org/W3035297600","https://openalex.org/W3097309192","https://openalex.org/W3109728025","https://openalex.org/W3143107425","https://openalex.org/W3171926364","https://openalex.org/W3176646400","https://openalex.org/W4214849833","https://openalex.org/W4226221010","https://openalex.org/W4226458340","https://openalex.org/W4229482837","https://openalex.org/W6600609147","https://openalex.org/W6675751002","https://openalex.org/W6678470764","https://openalex.org/W6687045409","https://openalex.org/W6779459370","https://openalex.org/W6802136708"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W4386159726"],"abstract_inverted_index":{"Generative":[0],"model-based":[1],"zero-shot":[2],"learning":[3,11],"(ZSL)":[4],"approaches":[5],"usually":[6],"transform":[7],"ZSL":[8,29,129,140],"to":[9,72,93,104],"supervised":[10],"by":[12,46],"generating":[13],"full":[14],"visual":[15,44,94],"features":[16,45,75,89,114],"for":[17,28],"unseen":[18],"classes,":[19],"which":[20],"may":[21,125],"contain":[22],"redundant":[23,122],"or":[24],"noisy":[25],"information":[26,123],"harmful":[27],"classification.":[30,130],"In":[31,64],"this":[32],"work,":[33],"we":[34,66,98],"propose":[35,67],"a":[36,100],"novel":[37],"generative":[38],"framework":[39,71],"that":[40,76,90,124],"fully":[41],"exploits":[42],"the":[43,106,109,116,121,127,143],"disentangling":[47],"them":[48],"into":[49],"three":[50],"distinct":[51],"components,":[52],"i.e.,":[53],"semantically":[54],"correlative":[55],"(SC),":[56],"visually":[57],"discriminative":[58,110],"(VD),":[59],"and":[60,112,115],"residual":[61,117],"features,":[62],"respectively.":[63],"particular,":[65],"an":[68],"encoder-decoder":[69],"disentanglement":[70],"learn":[73],"SC":[74],"align":[77],"closely":[78],"with":[79],"their":[80],"corresponding":[81],"semantic":[82],"label":[83],"embeddings,":[84],"as":[85,87],"well":[86],"VD":[88],"contribute":[91],"significantly":[92],"classification":[95],"accuracy.":[96],"Additionally,":[97],"introduce":[99],"mutual":[101],"information-based":[102],"loss":[103],"disperse":[105],"distributions":[107],"between":[108],"(SC":[111],"VD)":[113],"ones,":[118],"thereby":[119],"eliminating":[120],"hinder":[126],"final":[128],"Our":[131],"proposed":[132],"method":[133],"is":[134,153],"extensively":[135],"evaluated":[136],"on":[137],"four":[138],"popular":[139],"benchmarks,":[141],"where":[142],"experimental":[144],"results":[145],"demonstrate":[146],"its":[147],"superiority":[148],"over":[149],"existing":[150],"counterparts.":[151],"Code":[152],"available":[154],"at":[155],"https://github.com/RowenaHe/VFD-ZSL.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}