{"id":"https://openalex.org/W3093136537","doi":"https://doi.org/10.1145/3394171.3413568","title":"Generalized Zero-shot Learning with Multi-source Semantic Embeddings for Scene Recognition","display_name":"Generalized Zero-shot Learning with Multi-source Semantic Embeddings for Scene Recognition","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3093136537","doi":"https://doi.org/10.1145/3394171.3413568","mag":"3093136537"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413568","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th 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/A5055504013","display_name":"Xinhang Song","orcid":"https://orcid.org/0000-0002-0895-1076"},"institutions":[{"id":"https://openalex.org/I4210101410","display_name":"International Centre for Theoretical Physics Asia-Pacific","ror":"https://ror.org/01z2px678","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210101410","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinhang Song","raw_affiliation_strings":["ICT, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICT, Beijing, China","institution_ids":["https://openalex.org/I4210101410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101493128","display_name":"Haitao Zeng","orcid":"https://orcid.org/0000-0003-1538-461X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haitao Zeng","raw_affiliation_strings":["ICT, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICT, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017213372","display_name":"Sixian Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sixian Zhang","raw_affiliation_strings":["Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079201773","display_name":"Luis Herranz","orcid":"https://orcid.org/0000-0002-7022-3395"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I4387153096","display_name":"Computer Vision Center","ror":"https://ror.org/00s0nnj93","country_code":null,"type":"other","lineage":["https://openalex.org/I4387153040","https://openalex.org/I4387153096"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Luis Herranz","raw_affiliation_strings":["Computer Vision Center, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Vision Center, Barcelona, Spain","institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I4387153096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085719285","display_name":"Shuqiang Jiang","orcid":"https://orcid.org/0000-0002-1596-4326"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuqiang Jiang","raw_affiliation_strings":["ICT, China Academy of Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICT, China Academy of Science, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3976","last_page":"3985"},"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":0.9998999834060669,"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":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9932000041007996,"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":0.789258599281311},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7821077704429626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6984403133392334},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6503783464431763},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6340652704238892},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6136167049407959},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5488581657409668},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5321881771087646},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4935644865036011},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4680865406990051},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4497964382171631},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.4270744323730469},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3804754614830017},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35364943742752075},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32681944966316223}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.789258599281311},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7821077704429626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6984403133392334},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6503783464431763},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6340652704238892},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6136167049407959},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5488581657409668},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5321881771087646},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4935644865036011},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4680865406990051},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4497964382171631},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.4270744323730469},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3804754614830017},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35364943742752075},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32681944966316223},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3413568","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W93016980","https://openalex.org/W1524680991","https://openalex.org/W1542713999","https://openalex.org/W1677182931","https://openalex.org/W1905882502","https://openalex.org/W1924160326","https://openalex.org/W2032699694","https://openalex.org/W2033832873","https://openalex.org/W2099471712","https://openalex.org/W2110628941","https://openalex.org/W2117539524","https://openalex.org/W2128532956","https://openalex.org/W2134670479","https://openalex.org/W2171061940","https://openalex.org/W2277195237","https://openalex.org/W2289084343","https://openalex.org/W2400717490","https://openalex.org/W2552002300","https://openalex.org/W2552383788","https://openalex.org/W2601051138","https://openalex.org/W2602364336","https://openalex.org/W2732026016","https://openalex.org/W2780534582","https://openalex.org/W2799215068","https://openalex.org/W2899867883","https://openalex.org/W2924476266","https://openalex.org/W2950276680","https://openalex.org/W2950577311","https://openalex.org/W2962677366","https://openalex.org/W2962824231","https://openalex.org/W2962879692","https://openalex.org/W2963283377","https://openalex.org/W2963545832","https://openalex.org/W2963584589","https://openalex.org/W2963758027","https://openalex.org/W2963779825","https://openalex.org/W2963960318","https://openalex.org/W2970732459","https://openalex.org/W2979571231","https://openalex.org/W2981646256","https://openalex.org/W2982407353","https://openalex.org/W2986692991","https://openalex.org/W2998708909","https://openalex.org/W3010805239","https://openalex.org/W3017161914","https://openalex.org/W3104752576","https://openalex.org/W3105627154","https://openalex.org/W4240153047","https://openalex.org/W4297683907","https://openalex.org/W4301045096"],"related_works":["https://openalex.org/W4396941953","https://openalex.org/W2093104230","https://openalex.org/W2987280934","https://openalex.org/W4390874210","https://openalex.org/W4384918963","https://openalex.org/W4365211920","https://openalex.org/W2128027845","https://openalex.org/W3014948380","https://openalex.org/W4386184937","https://openalex.org/W4241564561"],"abstract_inverted_index":{"Recognizing":[0],"visual":[1,16,141,160],"categories":[2,48,77],"from":[3],"semantic":[4,41,122],"descriptions":[5,42,132,151],"is":[6,31],"a":[7,15,70,110,145,176,188],"promising":[8],"way":[9],"to":[10,46,99,158,174,181],"extend":[11],"the":[12,19,23,183,201,209,212],"capability":[13],"of":[14,76,121,211],"classifier":[17],"beyond":[18],"concepts":[20],"represented":[21],"in":[22,87],"training":[24],"data":[25],"(i.e.":[26,124],"seen":[27,47],"categories).":[28],"This":[29],"problem":[30],"addressed":[32],"by":[33],"(generalized)":[34],"zero-shot":[35,67,192],"learning":[36],"methods":[37],"(GZSL),":[38],"which":[39],"leverage":[40],"that":[43,133],"connect":[44],"them":[45],"(e.g.":[49],"label":[50],"embedding,":[51],"attributes).":[52],"Conventional":[53,92],"GZSL":[54,93],"are":[55,95,152,165],"designed":[56],"mostly":[57],"for":[58,191],"object":[59],"recognition.":[60],"In":[61,179],"this":[62],"paper":[63],"we":[64,108,143,186],"focus":[65],"on":[66,200],"scene":[68,136,193],"recognition,":[69],"more":[71],"challenging":[72],"setting":[73],"with":[74,114,171,195],"hundreds":[75],"where":[78,149],"their":[79],"differences":[80],"can":[81,134],"be":[82],"subtle":[83],"and":[84,128,154,168,204],"often":[85],"localized":[86],"certain":[88],"objects":[89],"or":[90],"regions.":[91],"representations":[94],"not":[96],"rich":[97],"enough":[98],"capture":[100],"these":[101,106],"local":[102,150],"discriminative":[103],"differences.":[104],"Addressing":[105],"limitations,":[107],"propose":[109,144],"feature":[111],"generation":[112],"framework":[113],"two":[115],"novel":[116],"components:":[117],"1)":[118],"multiple":[119],"sources":[120],"information":[123],"attributes,":[125],"word":[126],"embeddings":[127],"descriptions),":[129],"2)":[130],"region":[131],"enhance":[135],"discrimination.":[137],"To":[138],"generate":[139,159],"synthetic":[140],"features":[142,164,173],"two-step":[146],"generative":[147],"approach,":[148],"sampled":[153],"used":[155,169],"as":[156],"conditions":[157],"features.":[161],"The":[162],"generated":[163],"then":[166],"aggregated":[167],"together":[170],"real":[172],"train":[175],"joint":[177],"classifier.":[178],"order":[180],"evaluate":[182],"proposed":[184,202,213],"method,":[185],"introduce":[187],"new":[189],"dataset":[190,203,207],"recognition":[194],"multi-semantic":[196],"annotations.":[197],"Experimental":[198],"results":[199],"SUN":[205],"Attribute":[206],"illustrate":[208],"effectiveness":[210],"method.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}