{"id":"https://openalex.org/W4385807432","doi":"https://doi.org/10.21437/interspeech.2023-668","title":"Visually grounded few-shot word acquisition with fewer shots","display_name":"Visually grounded few-shot word acquisition with fewer shots","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385807432","doi":"https://doi.org/10.21437/interspeech.2023-668"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-668","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5020033363","display_name":"Leanne Nortje","orcid":null},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":true,"raw_author_name":"Leanne Nortje","raw_affiliation_strings":["MediaLab, E&E Engineering, Stellenbosch University, South Africa"],"affiliations":[{"raw_affiliation_string":"MediaLab, E&E Engineering, Stellenbosch University, South Africa","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046382731","display_name":"Benjamin van Niekerk","orcid":"https://orcid.org/0000-0001-9207-6309"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Benjamin van Niekerk","raw_affiliation_strings":["MediaLab, E&E Engineering, Stellenbosch University, South Africa"],"affiliations":[{"raw_affiliation_string":"MediaLab, E&E Engineering, Stellenbosch University, South Africa","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040305929","display_name":"Herman Kamper","orcid":"https://orcid.org/0000-0003-2980-3475"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Herman Kamper","raw_affiliation_strings":["MediaLab, E&E Engineering, Stellenbosch University, South Africa"],"affiliations":[{"raw_affiliation_string":"MediaLab, E&E Engineering, Stellenbosch University, South Africa","institution_ids":["https://openalex.org/I26092322"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020033363"],"corresponding_institution_ids":["https://openalex.org/I26092322"],"apc_list":null,"apc_paid":null,"fwci":0.1235,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.40298784,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3412","last_page":"3416"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9987000226974487,"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":0.9983999729156494,"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/word","display_name":"Word (group theory)","score":0.8202000260353088},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7748871445655823},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.646510124206543},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6277921199798584},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6118898391723633},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5542751550674438},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5124393105506897},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4915786683559418},{"id":"https://openalex.org/keywords/ask-price","display_name":"Ask price","score":0.47345513105392456},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12223824858665466}],"concepts":[{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.8202000260353088},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7748871445655823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.646510124206543},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6277921199798584},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6118898391723633},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5542751550674438},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5124393105506897},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4915786683559418},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.47345513105392456},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12223824858665466},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-668","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320317153","display_name":"DeepMind","ror":"https://ror.org/00971b260"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W2010991551","https://openalex.org/W2013596317","https://openalex.org/W2074231493","https://openalex.org/W2091746061","https://openalex.org/W2108598243","https://openalex.org/W2132730112","https://openalex.org/W2194775991","https://openalex.org/W2408712009","https://openalex.org/W2415378728","https://openalex.org/W2556930864","https://openalex.org/W2618530766","https://openalex.org/W2747874407","https://openalex.org/W2796315435","https://openalex.org/W2802557066","https://openalex.org/W2889313720","https://openalex.org/W2963330681","https://openalex.org/W2963720603","https://openalex.org/W2964249784","https://openalex.org/W2995181338","https://openalex.org/W3049010983","https://openalex.org/W3157861865","https://openalex.org/W3198134274","https://openalex.org/W3198411039","https://openalex.org/W3198749384","https://openalex.org/W3209059054","https://openalex.org/W4234899042","https://openalex.org/W4297841895","https://openalex.org/W4306317873","https://openalex.org/W4319862278"],"related_works":["https://openalex.org/W2168627904","https://openalex.org/W2515552481","https://openalex.org/W1570348318","https://openalex.org/W2015444353","https://openalex.org/W3013494979","https://openalex.org/W156769215","https://openalex.org/W4308101915","https://openalex.org/W3194047734","https://openalex.org/W4252364083","https://openalex.org/W4210657415"],"abstract_inverted_index":{"We":[0],"propose":[1,66],"a":[2,17,22,28,59,108],"visually":[3],"grounded":[4],"speech":[5,103],"model":[6,34],"that":[7,69],"acquires":[8],"new":[9,93,117],"words":[10],"and":[11,27,104],"their":[12],"visual":[13],"depictions":[14],"from":[15,98],"just":[16],"few":[18],"wordimage":[19],"example":[20,89],"pairs.Given":[21],"set":[23],"of":[24,62,101],"test":[25],"images":[26],"spoken":[29],"query,":[30],"we":[31,106,119],"ask":[32],"the":[33,38,86],"which":[35],"image":[36],"depicts":[37],"query":[39],"word.Previous":[40],"work":[41,71],"has":[42],"simplified":[43],"this":[44,116],"problem":[45],"by":[46,57],"either":[47],"using":[48,58,85],"an":[49,67],"artificial":[50],"setting":[51],"with":[52,77,123],"digit":[53],"word-image":[54,74,88,95,114],"pairs":[55,75,90,97],"or":[56],"large":[60,99],"number":[61],"examples":[63],"per":[64],"class.We":[65],"approach":[68,83],"can":[70],"on":[72],"natural":[73],"but":[76],"less":[78],"examples,":[79],"i.e.":[80],"fewer":[81,124],"shots.Our":[82],"involves":[84],"given":[87],"to":[91,112],"mine":[92],"unsupervised":[94],"training":[96],"collections":[100],"unlabelled":[102],"images.Additionally,":[105],"use":[107],"word-to-image":[109],"attention":[110],"mechanism":[111],"determine":[113],"similarity.With":[115],"model,":[118],"achieve":[120],"better":[121],"performance":[122],"shots":[125],"than":[126],"any":[127],"existing":[128],"approach.":[129]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}