{"id":"https://openalex.org/W4312505667","doi":"https://doi.org/10.1109/mmsp55362.2022.9948764","title":"Approaching Zero-shot Learning from a Text-to-Image GAN perspective","display_name":"Approaching Zero-shot Learning from a Text-to-Image GAN perspective","publication_year":2022,"publication_date":"2022-09-26","ids":{"openalex":"https://openalex.org/W4312505667","doi":"https://doi.org/10.1109/mmsp55362.2022.9948764"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp55362.2022.9948764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp55362.2022.9948764","pdf_url":null,"source":{"id":"https://openalex.org/S4363605768","display_name":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","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/A5065636501","display_name":"Ayman Talkani","orcid":"https://orcid.org/0000-0002-5458-8159"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Ayman Talkani","raw_affiliation_strings":["School of Computing National University of Singapore,Singapore","School of Computing National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-5458-8159","affiliations":[{"raw_affiliation_string":"School of Computing National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"School of Computing National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071812191","display_name":"Anand Bhojan","orcid":"https://orcid.org/0000-0001-8105-1739"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Anand Bhojan","raw_affiliation_strings":["School of Computing National University of Singapore,Singapore","School of Computing National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-8105-1739","affiliations":[{"raw_affiliation_string":"School of Computing National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"School of Computing National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065636501"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.1789,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.52576661,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9977999925613403,"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/T10028","display_name":"Topic Modeling","score":0.9666000008583069,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7064315676689148},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.584805965423584},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.563342273235321},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5588991045951843},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5534668564796448},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5432133078575134},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5299732685089111},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5190406441688538},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4743596017360687},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.45817825198173523},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4325598180294037},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.392039030790329},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3559347093105316},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1447242796421051}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7064315676689148},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.584805965423584},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.563342273235321},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5588991045951843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5534668564796448},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5432133078575134},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5299732685089111},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5190406441688538},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4743596017360687},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.45817825198173523},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4325598180294037},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.392039030790329},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3559347093105316},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1447242796421051},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp55362.2022.9948764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp55362.2022.9948764","pdf_url":null,"source":{"id":"https://openalex.org/S4363605768","display_name":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W652269744","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W2044913453","https://openalex.org/W2171061940","https://openalex.org/W2289084343","https://openalex.org/W2462457117","https://openalex.org/W2566618089","https://openalex.org/W2596142952","https://openalex.org/W2603705233","https://openalex.org/W2799215068","https://openalex.org/W2899867883","https://openalex.org/W2924476266","https://openalex.org/W2962845008","https://openalex.org/W2963163163","https://openalex.org/W2963779825","https://openalex.org/W2963955958","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W3011456022","https://openalex.org/W3084840705","https://openalex.org/W3109728025","https://openalex.org/W3113432867","https://openalex.org/W3165647589","https://openalex.org/W4320013936","https://openalex.org/W4385245566","https://openalex.org/W6730746255","https://openalex.org/W6739901393","https://openalex.org/W6796242362"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2380075625","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W4390718435","https://openalex.org/W2013985456","https://openalex.org/W2951564084","https://openalex.org/W4302984940","https://openalex.org/W2776807270","https://openalex.org/W2392685819"],"abstract_inverted_index":{"With":[0],"the":[1,26,67,80,110,118,132,142,156,174,203,213,219,222,234,240,243,266,285,288,297,303,338,350],"recent":[2],"research":[3,18],"advancements":[4],"in":[5,22,35,48,115,128,309,337],"generative":[6],"adversarial":[7],"networks,":[8],"synthesizing":[9],"images":[10,36],"from":[11,146],"textual":[12,56],"descriptions":[13],"has":[14],"become":[15],"an":[16,38,95,101],"active":[17],"area.":[19],"Their":[20],"applications":[21,50],"fields":[23],"such":[24],"as":[25,268,324],"use":[27],"of":[28,41,83,117,218,242,252,284,287],"localizing":[29],"phrases":[30],"to":[31,69,78,92,121,130,141,164,168,194,202,245,264,282,317],"identify":[32],"unseen":[33],"objects":[34],"is":[37,97,255],"important":[39],"part":[40],"image":[42,96,122],"understanding":[43],"and":[44,57,216,299,305,340,345],"can":[45,199],"be":[46,70,200],"useful":[47],"many":[49],"that":[51,139,161,198],"rely":[52],"on":[53,100,173,238,296],"mappings":[54],"between":[55],"visual":[58,72],"information.":[59],"Although":[60],"most":[61],"zero":[62,289],"shot":[63],"learning":[64,176,290,343],"algorithms":[65],"consider":[66],"problem":[68,157],"a":[71,105,150,169,181],"semantic":[73],"embedding":[74],"one,":[75],"we":[76,153],"attempt":[77],"utilize":[79],"demonstrative":[81],"capability":[82],"Generative":[84],"Adversarial":[85],"network":[86,133],"[7]":[87],"for":[88,227,326,349],"ZSL":[89,204],"tasks,":[90],"similar":[91],"[20],":[93],"where":[94],"generated":[98],"based":[99],"object":[102],"description":[103],"utilizing":[104],"GAN":[106,112,183],"architecture":[107,179,184,333],"inspired":[108,185],"by":[109,186,258,315],"cascaded":[111,151,182],"structure":[113],"used":[114],"state":[116,283],"art":[119,286],"text":[120,145],"frameworks":[123],"[10],":[124,190],"[16],":[125,191],"[18],":[126,192],"[19]":[127,193],"order":[129],"help":[131],"generate":[134,195,246],"more":[135,170,247],"accurate":[136,248],"feature":[137,196,232],"vectors":[138,197],"relate":[140],"noisy":[143,320],"input":[144,325],"wikipedia.":[147],"By":[148],"using":[149],"structure,":[152],"essentially":[154],"divide":[155],"into":[158],"consequent":[159],"sub-problems":[160],"are":[162,225],"easier":[163],"solve,":[165],"thus":[166],"leading":[167],"positive":[171],"result":[172],"zero-shot":[175],"task.":[177],"Our":[178],"utilizes":[180],"text-to-image":[187],"generators":[188],"like":[189],"applied":[201],"task":[205],"at":[206],"various":[207],"stages,":[208],"with":[209,271,302,334],"each":[210,253,327],"stage":[211,254],"increasing":[212,239],"dimension":[214,230],"size":[215],"complexity":[217,241],"vector.":[220],"While":[221],"initial":[223],"stages":[224,236],"responsible":[226],"generating":[228],"low":[229],"primitive":[231],"vectors,":[233],"later":[235],"focus":[237],"vector":[244,267],"outputs.":[249],"The":[250],"output":[251],"also":[256,318],"guided":[257],"it's":[259,272],"respective":[260],"discriminator,":[261],"which":[262,311],"tries":[263],"classify":[265],"real/fake,":[269],"along":[270],"corresponding":[273],"class":[274],"label.":[275],"We":[276,329],"will":[277],"empirically":[278],"compare":[279,331],"our":[280,332],"model":[281],"models":[291],"[6],":[292,310],"[9],":[293],"[12],":[294],"[20]":[295],"CUB":[298],"NAB":[300],"datasets":[301],"SCS":[304],"SCE":[306],"splits":[307],"introduced":[308],"have":[312],"been":[313],"modified":[314],"[6]":[316],"include":[319],"Wikipedia":[321],"article":[322],"texts":[323],"class.":[328],"then":[330],"state-of-the-art":[335],"methods":[336],"Zero-shot-recognition":[339],"Generalized":[341],"Zero-shot":[342],"tasks":[344],"present":[346],"quantitative":[347],"results":[348],"same.":[351]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}