{"id":"https://openalex.org/W4401991032","doi":"https://doi.org/10.1109/icmew63481.2024.10645389","title":"Enhancing Visual Wake Word Spotting with Pretrained Model and Feature Balance Scaling","display_name":"Enhancing Visual Wake Word Spotting with Pretrained Model and Feature Balance Scaling","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4401991032","doi":"https://doi.org/10.1109/icmew63481.2024.10645389"},"language":"en","primary_location":{"id":"doi:10.1109/icmew63481.2024.10645389","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icmew63481.2024.10645389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","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/A5062890586","display_name":"Xuandong Huang","orcid":"https://orcid.org/0000-0001-6629-5129"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xuandong Huang","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China,Hefei,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077046519","display_name":"Shangfei Wang","orcid":"https://orcid.org/0000-0003-1164-9895"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shangfei Wang","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China,Hefei,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062247066","display_name":"Jinghao Yan","orcid":"https://orcid.org/0009-0008-6845-9201"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinghao Yan","raw_affiliation_strings":["Tencent Inc.,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tencent Inc.,Beijing,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012291253","display_name":"Kai Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Tang","raw_affiliation_strings":["Tencent Inc.,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tencent Inc.,Beijing,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101623000","display_name":"Pengfei Hu","orcid":"https://orcid.org/0009-0005-3345-605X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"H. Pengfei","raw_affiliation_strings":["Tencent Inc.,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tencent Inc.,Beijing,China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5062890586"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13660596,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"abs/1809.00496","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9797000288963318,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9797000288963318,"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/T12720","display_name":"Multimedia Communication and Technology","score":0.9653000235557556,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9164000153541565,"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/spotting","display_name":"Spotting","score":0.903628945350647},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7232455015182495},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6308907866477966},{"id":"https://openalex.org/keywords/balance","display_name":"Balance (ability)","score":0.5311043858528137},{"id":"https://openalex.org/keywords/wake","display_name":"Wake","score":0.5298713445663452},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5111334919929504},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5006487369537354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49279382824897766},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46672454476356506},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.43812140822410583},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3921208679676056},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09017971158027649},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07953104376792908},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06140577793121338},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.05616256594657898}],"concepts":[{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.903628945350647},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7232455015182495},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6308907866477966},{"id":"https://openalex.org/C168031717","wikidata":"https://www.wikidata.org/wiki/Q1530280","display_name":"Balance (ability)","level":2,"score":0.5311043858528137},{"id":"https://openalex.org/C48939323","wikidata":"https://www.wikidata.org/wiki/Q294879","display_name":"Wake","level":2,"score":0.5298713445663452},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5111334919929504},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5006487369537354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49279382824897766},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46672454476356506},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.43812140822410583},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3921208679676056},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09017971158027649},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07953104376792908},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06140577793121338},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.05616256594657898},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmew63481.2024.10645389","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icmew63481.2024.10645389","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8472469554","display_name":null,"funder_award_id":"92048203","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1553469512","https://openalex.org/W1999121090","https://openalex.org/W2122797512","https://openalex.org/W2594690981","https://openalex.org/W2897492880","https://openalex.org/W2943235166","https://openalex.org/W2973226577","https://openalex.org/W3016011581","https://openalex.org/W3162293946","https://openalex.org/W4224933780","https://openalex.org/W4224940398","https://openalex.org/W4226046733","https://openalex.org/W4288391450","https://openalex.org/W4297841644","https://openalex.org/W4375869136","https://openalex.org/W4386075947","https://openalex.org/W4392910573","https://openalex.org/W6714171909","https://openalex.org/W6752581720","https://openalex.org/W6754420807","https://openalex.org/W6761937618","https://openalex.org/W6796538260","https://openalex.org/W6810168380","https://openalex.org/W6850372469"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W3119978414","https://openalex.org/W4286904253","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2117995638"],"abstract_inverted_index":{"Wake":[0],"word":[1,25,56,67,127],"spotting":[2,26,68],"mainly":[3],"focus":[4,90],"on":[5,91],"audio":[6],"modality":[7,14],"or":[8],"audio-visual":[9],"multimodal":[10],"exploration.":[11],"The":[12],"visual":[13,23,54,65,73],"delivers":[15],"stable":[16],"outcomes":[17],"under":[18],"poor":[19],"acoustic":[20],"conditions,":[21],"making":[22],"wake":[24,55,66,126],"an":[27,61],"emerging":[28],"and":[29,41,48,63,95,113,135,167,181],"challenging":[30],"task.":[31],"However,":[32],"challenges":[33],"such":[34],"as":[35],"overfitting":[36],"due":[37],"to":[38,79,89,125,140],"subject":[39],"dependence":[40],"performance":[42],"decrease":[43],"from":[44],"imbalances":[45],"between":[46],"positive":[47,112],"negative":[49,114],"samples":[50,115],"still":[51],"exist":[52],"in":[53,150,175],"spotting.":[57],"This":[58,118],"paper":[59],"introduces":[60],"efficient":[62],"robust":[64],"system.":[69],"Notably,":[70],"a":[71,161,168,176],"pretrained":[72],"lipreading":[74],"sequence":[75],"encoder":[76],"is":[77],"employed":[78],"extract":[80],"more":[81],"effective":[82],"lip":[83,92],"movement":[84,93],"features,":[85],"allowing":[86],"the":[87,106,130,137,151,155],"model":[88],"patterns":[94],"prevent":[96],"overfitting.":[97],"Additionally,":[98],"we":[99],"propose":[100],"feature":[101,107],"balance":[102],"scaling,":[103],"which":[104],"adjusts":[105],"value":[108],"ranges":[109],"of":[110,132,154,165,172,179],"both":[111],"during":[116],"training.":[117],"scaling":[119],"method":[120],"can":[121],"be":[122],"easily":[123],"applied":[124],"spotting,":[128],"mitigating":[129],"impact":[131],"data":[133],"imbalance":[134],"enhancing":[136],"classifier's":[138],"ability":[139],"handle":[141],"out-of-bound":[142],"samples.":[143],"Finally,":[144],"our":[145],"system":[146],"achieved":[147],"notable":[148],"results":[149],"final":[152,177],"evaluation":[153],"ChatCLR":[156],"challenge's":[157],"1st":[158],"task,":[159],"attaining":[160],"false":[162,169],"alarm":[163],"rate":[164,171],"0.110":[166],"reject":[170],"0.070,":[173],"culminating":[174],"score":[178],"0.180":[180],"securing":[182],"third":[183],"place.":[184]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}