{"id":"https://openalex.org/W4387968058","doi":"https://doi.org/10.1145/3581783.3613435","title":"Zero-Shot Learning for Computer Vision Applications","display_name":"Zero-Shot Learning for Computer Vision Applications","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968058","doi":"https://doi.org/10.1145/3581783.3613435"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3613435","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3613435","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5017150634","display_name":"Sandipan Sarma","orcid":"https://orcid.org/0000-0003-4619-3058"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sandipan Sarma","raw_affiliation_strings":["Indian Institute of Technology, Guwahati, Guwahati, India"],"raw_orcid":"https://orcid.org/0000-0003-4619-3058","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Guwahati, Guwahati, India","institution_ids":["https://openalex.org/I1317621060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5017150634"],"corresponding_institution_ids":["https://openalex.org/I1317621060"],"apc_list":null,"apc_paid":null,"fwci":0.436,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.60530451,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"9360","last_page":"9364"},"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":0.9997000098228455,"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":0.9997000098228455,"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":0.9972000122070312,"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":0.9955000281333923,"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":0.7138203978538513},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6487256288528442},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.5858498811721802},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5755130052566528},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5696427226066589},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5551975965499878},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5421399474143982},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4998490810394287},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.46055829524993896},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3347107172012329},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3024100065231323},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09752249717712402},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07955670356750488}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7138203978538513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6487256288528442},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.5858498811721802},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5755130052566528},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5696427226066589},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5551975965499878},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5421399474143982},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4998490810394287},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.46055829524993896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3347107172012329},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3024100065231323},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09752249717712402},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07955670356750488},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3613435","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3613435","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2064851185","https://openalex.org/W2081580037","https://openalex.org/W2128532956","https://openalex.org/W2157133710","https://openalex.org/W2171061940","https://openalex.org/W2289084343","https://openalex.org/W2507611421","https://openalex.org/W2724511873","https://openalex.org/W2801004733","https://openalex.org/W2904378456","https://openalex.org/W2955882737","https://openalex.org/W2963097937","https://openalex.org/W2963306805","https://openalex.org/W2963486920","https://openalex.org/W2963499153","https://openalex.org/W2963936013","https://openalex.org/W2997150218","https://openalex.org/W2997998901","https://openalex.org/W3010805239","https://openalex.org/W3034563158","https://openalex.org/W3049440217","https://openalex.org/W3092828241","https://openalex.org/W3101631402","https://openalex.org/W3119787359","https://openalex.org/W3143107425","https://openalex.org/W3195429019","https://openalex.org/W3197395033","https://openalex.org/W4200633401","https://openalex.org/W4214746887","https://openalex.org/W4312574495","https://openalex.org/W4312791158","https://openalex.org/W4378807209"],"related_works":["https://openalex.org/W2732813147","https://openalex.org/W2143460112","https://openalex.org/W2042906257","https://openalex.org/W2114275278","https://openalex.org/W4292830139","https://openalex.org/W4319309705","https://openalex.org/W1489511283","https://openalex.org/W4387272257","https://openalex.org/W2974914859","https://openalex.org/W2026565050"],"abstract_inverted_index":{"Human":[0],"beings":[1],"possess":[2],"the":[3,23,73,107],"remarkable":[4],"ability":[5],"to":[6,34,60,65,71,115],"recognize":[7,35],"unseen":[8,66],"concepts":[9,17,36],"by":[10],"integrating":[11],"their":[12,40],"visual":[13,42],"perception":[14],"of":[15,75],"known":[16],"with":[18],"some":[19,120],"high-level":[20],"descriptions.":[21],"However,":[22],"best-performing":[24],"deep":[25],"learning":[26,45],"frameworks":[27,112],"today":[28],"are":[29,102,113],"supervised":[30],"learners":[31],"that":[32,53],"struggle":[33],"without":[37],"training":[38],"on":[39],"labeled":[41],"samples.":[43],"Zero-shot":[44,111],"(ZSL)":[46],"has":[47],"recently":[48],"emerged":[49],"as":[50,124],"a":[51],"solution":[52],"mimics":[54],"humans":[55],"and":[56,95,104],"leverages":[57],"multimodal":[58],"information":[59],"transfer":[61],"knowledge":[62],"from":[63],"seen":[64],"concepts.":[67],"This":[68],"study":[69],"aims":[70],"emphasize":[72],"practicality":[74],"ZSL,":[76],"unlocking":[77],"its":[78],"potential":[79],"across":[80],"four":[81],"different":[82],"applications":[83],"in":[84,106],"computer":[85],"vision,":[86],"namely":[87],"--":[88],"object":[89,91],"recognition,":[90,94],"detection,":[92],"action":[93],"human-object":[96],"interaction":[97],"detection.":[98],"Several":[99],"task-specific":[100],"challenges":[101],"identified":[103],"addressed":[105],"presented":[108],"research":[109,122],"hypotheses.":[110],"proposed":[114],"attain":[116],"state-of-the-art":[117],"performance,":[118],"elucidating":[119],"future":[121],"directions":[123],"well.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
