{"id":"https://openalex.org/W2981289613","doi":"https://doi.org/10.1145/3340555.3356101","title":"Spotting Visual Keywords from Temporal Sliding Windows","display_name":"Spotting Visual Keywords from Temporal Sliding Windows","publication_year":2019,"publication_date":"2019-10-14","ids":{"openalex":"https://openalex.org/W2981289613","doi":"https://doi.org/10.1145/3340555.3356101","mag":"2981289613"},"language":"en","primary_location":{"id":"doi:10.1145/3340555.3356101","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340555.3356101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Multimodal Interaction","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/A5101863447","display_name":"Yue Yao","orcid":"https://orcid.org/0000-0002-3673-3682"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Yue Yao","raw_affiliation_strings":["Australian National University, Australia"],"affiliations":[{"raw_affiliation_string":"Australian National University, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100417416","display_name":"Tianyu Wang","orcid":"https://orcid.org/0000-0001-9578-5039"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tianyu Wang","raw_affiliation_strings":["Australian National University, Australia"],"affiliations":[{"raw_affiliation_string":"Australian National University, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069395028","display_name":"Heming Du","orcid":"https://orcid.org/0000-0002-7391-0449"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Heming Du","raw_affiliation_strings":["Australian National University, Australia"],"affiliations":[{"raw_affiliation_string":"Australian National University, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100709340","display_name":"Liang Zheng","orcid":"https://orcid.org/0000-0002-1464-9500"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Liang Zheng","raw_affiliation_strings":["Australian National University, Australia"],"affiliations":[{"raw_affiliation_string":"Australian National University, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030379402","display_name":"Tom Gedeon","orcid":"https://orcid.org/0000-0001-8356-4909"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tom Gedeon","raw_affiliation_strings":["Australian National University, Australia"],"affiliations":[{"raw_affiliation_string":"Australian National University, Australia","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101863447"],"corresponding_institution_ids":["https://openalex.org/I118347636"],"apc_list":null,"apc_paid":null,"fwci":0.4976,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.64054253,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"536","last_page":"539"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9962000250816345,"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":0.8732092380523682},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.813954770565033},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.7500027418136597},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6418315172195435},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6337950229644775},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6329411268234253},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.5333449840545654},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5278686881065369},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5095975399017334},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4978306293487549},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4607814848423004},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4374735355377197},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.42281368374824524},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4136233329772949}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8732092380523682},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.813954770565033},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.7500027418136597},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6418315172195435},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6337950229644775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6329411268234253},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.5333449840545654},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5278686881065369},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5095975399017334},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4978306293487549},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4607814848423004},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4374735355377197},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.42281368374824524},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4136233329772949},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3340555.3356101","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340555.3356101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Multimodal Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2015143272","https://openalex.org/W2570575067","https://openalex.org/W2890952074","https://openalex.org/W2897492880","https://openalex.org/W2904419413","https://openalex.org/W2962876901","https://openalex.org/W2963247196","https://openalex.org/W2963524571","https://openalex.org/W2963528589"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W3119978414","https://openalex.org/W2170821097","https://openalex.org/W2516975559","https://openalex.org/W2388033618","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W1969408022"],"abstract_inverted_index":{"Visual":[0,24],"Keyword":[1,25],"Spotting":[2,26],"(KWS),":[3],"as":[4],"a":[5,49,60,100,119],"newly":[6],"proposed":[7,59],"task":[8],"deriving":[9],"from":[10],"visual":[11],"speech":[12],"recognition,":[13],"has":[14],"plenty":[15],"of":[16,45,51,54,84],"room":[17],"for":[18],"improvements.":[19],"This":[20],"paper":[21],"details":[22],"our":[23],"system":[27],"used":[28,108],"in":[29,109],"the":[30,40,43,52,55,82,91,95],"first":[31],"Mandarin":[32],"Audio-Visual":[33],"Speech":[34],"Recognition":[35],"Challenge":[36],"(MAVSR":[37],"2019).":[38],"With":[39],"assumption":[41],"that":[42,67,99],"vocabularies":[44],"target":[46],"dataset":[47,93],"are":[48],"subset":[50],"vocabulary":[53],"training":[56],"set,":[57],"we":[58],"simple":[61],"and":[62,94],"scalable":[63],"classification":[64],"based":[65,80],"strategy":[66],"achieves":[68],"19.0%":[69],"mean":[70],"average":[71],"precision":[72],"(mAP)":[73],"on":[74,81],"this":[75],"challenge.":[76],"Our":[77],"method":[78],"is":[79],"idea":[83],"using":[85],"sliding":[86],"windows":[87],"to":[88,117],"bridge":[89],"between":[90],"word-level":[92],"sentence-level":[96],"dataset,":[97],"showing":[98],"strong":[101],"word":[102],"level":[103],"classifier":[104],"can":[105],"be":[106],"directly":[107],"building":[110],"sentence":[111],"embedding,":[112],"thereby":[113],"making":[114],"it":[115],"possible":[116],"build":[118],"KWS":[120],"system.":[121]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}