{"id":"https://openalex.org/W4416771689","doi":"https://doi.org/10.1109/sped67700.2025.11252119","title":"Improved visually prompted keyword localisation in real low-resource settings","display_name":"Improved visually prompted keyword localisation in real low-resource settings","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416771689","doi":"https://doi.org/10.1109/sped67700.2025.11252119"},"language":null,"primary_location":{"id":"doi:10.1109/sped67700.2025.11252119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped67700.2025.11252119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","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":["Stellenbosch University,Electrical and Electronic Engineering,Stellenbosch,South Africa"],"affiliations":[{"raw_affiliation_string":"Stellenbosch University,Electrical and Electronic Engineering,Stellenbosch,South Africa","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013389452","display_name":"Dan Onea\u0163\u0103","orcid":"https://orcid.org/0000-0003-4354-4393"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Dan Oneata","raw_affiliation_strings":["National University of Science and Technology POLITEHNICA Bucharest,Bucharest,Romania"],"affiliations":[{"raw_affiliation_string":"National University of Science and Technology POLITEHNICA Bucharest,Bucharest,Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092639624","display_name":"Gabriel P\u00eerlogeanu","orcid":null},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Gabriel P\u00eerlogeanu","raw_affiliation_strings":["National University of Science and Technology POLITEHNICA Bucharest,Bucharest,Romania"],"affiliations":[{"raw_affiliation_string":"National University of Science and Technology POLITEHNICA Bucharest,Bucharest,Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"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":["Stellenbosch University,Electrical and Electronic Engineering,Stellenbosch,South Africa"],"affiliations":[{"raw_affiliation_string":"Stellenbosch University,Electrical and Electronic Engineering,Stellenbosch,South Africa","institution_ids":["https://openalex.org/I26092322"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5020033363"],"corresponding_institution_ids":["https://openalex.org/I26092322"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40452311,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"46","last_page":"51"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5468999743461609,"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":0.5468999743461609,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.07779999822378159,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.06960000097751617,"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/ground-truth","display_name":"Ground truth","score":0.5163999795913696},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.47530001401901245},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4659000039100647},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.43160000443458557},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3111000061035156},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.28760001063346863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7009000182151794},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6014000177383423},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5486000180244446},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5163999795913696},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49950000643730164},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.47530001401901245},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4659000039100647},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43160000443458557},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3407999873161316},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2612000107765198}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sped67700.2025.11252119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped67700.2025.11252119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2074231493","https://openalex.org/W2108598243","https://openalex.org/W2586148577","https://openalex.org/W2618530766","https://openalex.org/W2962862718","https://openalex.org/W2963330681","https://openalex.org/W2963902314","https://openalex.org/W2964099072","https://openalex.org/W3005578234","https://openalex.org/W3095361818","https://openalex.org/W3157861865","https://openalex.org/W3159476814","https://openalex.org/W3198411039","https://openalex.org/W3200287550","https://openalex.org/W3209059054","https://openalex.org/W4285045129","https://openalex.org/W4287854499","https://openalex.org/W4296068421","https://openalex.org/W4319862234","https://openalex.org/W4319862278","https://openalex.org/W4395470973"],"related_works":[],"abstract_inverted_index":{"Given":[0],"an":[1],"image":[2],"query,":[3],"the":[4,17,81,112,143],"goal":[5],"in":[6,20,101,106,134,148],"visually":[7,52],"prompted":[8],"keyword":[9],"localisation":[10],"(VPKL)":[11],"is":[12,40,145],"to":[13,74,91,137],"find":[14],"occurrences":[15],"of":[16],"depicted":[18],"word":[19],"a":[21,34,51,87,103,119,131],"speech":[22,54],"collection.":[23],"This":[24,84],"can":[25,47],"be":[26,48],"useful":[27],"when":[28],"transcriptions":[29,71],"are":[30,126],"not":[31],"available":[32],"for":[33,80,111],"low-resource":[35,121],"language":[36],"(e.g.":[37],"if":[38],"it":[39],"unwritten).":[41],"Previous":[42],"work":[43],"showed":[44],"that":[45],"VPKL":[46,117],"performed":[49],"with":[50],"grounded":[53],"model":[55],"trained":[56],"on":[57,68,118],"paired":[58],"images":[59],"and":[60,77],"unlabelled":[61],"speech.":[62],"But":[63],"all":[64],"experiments":[65],"were":[66,72],"done":[67],"English.":[69],"Moreover,":[70],"used":[73],"get":[75],"positive":[76],"negative":[78],"pairs":[79,93,141],"contrastive":[82],"loss.":[83],"paper":[85],"introduces":[86],"few-shot":[88],"learning":[89],"scheme":[90],"mine":[92],"automatically":[94],"without":[95],"transcriptions.":[96],"On":[97],"English,":[98],"this":[99],"results":[100],"only":[102],"small":[104],"drop":[105,133],"performance.":[107],"We":[108],"also":[109],"\u2013":[110,115],"first":[113],"time":[114],"consider":[116],"real":[120],"language,":[122],"Yor\u00f9b\u00e1.":[123,149],"While":[124],"scores":[125],"reasonable,":[127],"here":[128],"we":[129],"see":[130],"bigger":[132],"performance":[135],"compared":[136],"using":[138],"ground":[139],"truth":[140],"because":[142],"mining":[144],"less":[146],"accurate":[147]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-27T00:00:00"}
