{"id":"https://openalex.org/W2099168818","doi":"https://doi.org/10.1145/1290128.1290138","title":"Local spatiotemporal descriptors for visual recognition of spoken phrases","display_name":"Local spatiotemporal descriptors for visual recognition of spoken phrases","publication_year":2007,"publication_date":"2007-09-28","ids":{"openalex":"https://openalex.org/W2099168818","doi":"https://doi.org/10.1145/1290128.1290138","mag":"2099168818"},"language":"en","primary_location":{"id":"doi:10.1145/1290128.1290138","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1290128.1290138","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the international workshop on Human-centered multimedia","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/A5082301986","display_name":"Guoying Zhao","orcid":"https://orcid.org/0000-0003-3694-206X"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Guoying Zhao","raw_affiliation_strings":["University of Oulu: Finland, Oulu, Finland"],"affiliations":[{"raw_affiliation_string":"University of Oulu: Finland, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014611768","display_name":"Matti Pietik\u00e4inen","orcid":"https://orcid.org/0000-0003-2263-6731"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Matti Pietik\u00e4inen","raw_affiliation_strings":["University of Oulu: Finland, Oulu, Finland"],"affiliations":[{"raw_affiliation_string":"University of Oulu: Finland, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013928164","display_name":"Abdenour Hadid","orcid":"https://orcid.org/0000-0001-9092-735X"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Abdenour Hadid","raw_affiliation_strings":["University of Oulu: Finland, Oulu, Finland"],"affiliations":[{"raw_affiliation_string":"University of Oulu: Finland, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5082301986"],"corresponding_institution_ids":["https://openalex.org/I98381234"],"apc_list":null,"apc_paid":null,"fwci":1.6212,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.83959548,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"57","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/T11448","display_name":"Face recognition and analysis","score":0.9944999814033508,"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/T10057","display_name":"Face and Expression Recognition","score":0.9919999837875366,"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":0.760930597782135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7001199126243591},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6960259079933167},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.6336029171943665},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6319887638092041},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6140093803405762},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5346319675445557},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4165201187133789},{"id":"https://openalex.org/keywords/local-binary-patterns","display_name":"Local binary patterns","score":0.4141320586204529},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15315371751785278},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.14600661396980286}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.760930597782135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7001199126243591},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6960259079933167},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6336029171943665},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6319887638092041},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6140093803405762},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5346319675445557},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4165201187133789},{"id":"https://openalex.org/C87335442","wikidata":"https://www.wikidata.org/wiki/Q2494345","display_name":"Local binary patterns","level":4,"score":0.4141320586204529},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15315371751785278},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.14600661396980286},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1290128.1290138","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1290128.1290138","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the international workshop on Human-centered multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.331.3198","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.331.3198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ee.oulu.fi/mvg/files/pdf/p57-zhao.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.714.1070","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.714.1070","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ee.oulu.fi/%7Egyzhao/Papers/2007/HCM.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W142803501","https://openalex.org/W142945732","https://openalex.org/W161516627","https://openalex.org/W636971608","https://openalex.org/W1498476715","https://openalex.org/W1527240141","https://openalex.org/W1664547674","https://openalex.org/W1978380426","https://openalex.org/W2015394094","https://openalex.org/W2039562357","https://openalex.org/W2064347532","https://openalex.org/W2068723942","https://openalex.org/W2071828724","https://openalex.org/W2096391593","https://openalex.org/W2097627987","https://openalex.org/W2106137268","https://openalex.org/W2106284211","https://openalex.org/W2113814270","https://openalex.org/W2139916508","https://openalex.org/W2141787596","https://openalex.org/W2142518644","https://openalex.org/W2157827878","https://openalex.org/W2160752178","https://openalex.org/W2160884118","https://openalex.org/W2163352848","https://openalex.org/W2163365749","https://openalex.org/W2163808566","https://openalex.org/W2163973301","https://openalex.org/W2164598857","https://openalex.org/W2168824259","https://openalex.org/W2169200946","https://openalex.org/W3099202502","https://openalex.org/W4285719527","https://openalex.org/W4301883704","https://openalex.org/W6605769872","https://openalex.org/W6631618440","https://openalex.org/W6785273600"],"related_works":["https://openalex.org/W2055219403","https://openalex.org/W2791313072","https://openalex.org/W3166997759","https://openalex.org/W2794489335","https://openalex.org/W2080437822","https://openalex.org/W2153027217","https://openalex.org/W2855870609","https://openalex.org/W1987527207","https://openalex.org/W3144203963","https://openalex.org/W2293488289"],"abstract_inverted_index":{"Visual":[0],"speech":[1,8],"information":[2],"plays":[3],"an":[4],"important":[5],"role":[6],"in":[7,58,95],"recognition":[9],"under":[10],"noisy":[11],"conditions":[12],"or":[13],"for":[14,53,71],"listeners":[15],"with":[16,78,103],"hearing":[17],"impairment.":[18],"In":[19,75,101],"this":[20],"paper,":[21],"we":[22],"propose":[23],"local":[24,62,127],"spatiotemporal":[25],"descriptors":[26],"to":[27,131],"represent":[28],"and":[29,48,84,91,97,129],"recognize":[30],"spoken":[31],"isolated":[32],"phrases":[33,83],"based":[34],"solely":[35],"on":[36,106],"visual":[37],"input.":[38],"Positions":[39],"of":[40,89,114,123,140],"the":[41,55,107,111,120],"eyes":[42],"determined":[43],"by":[44],"a":[45],"robust":[46],"face":[47,59],"eye":[49],"detector":[50],"are":[51,69],"used":[52,70],"localizing":[54],"mouth":[56],"regions":[57,68],"images.":[60],"Spatiotemporal":[61],"binary":[63],"patterns":[64],"extracted":[65],"from":[66,81],"these":[67],"describing":[72],"phrase":[73],"sequences.":[74],"our":[76,115,124],"experiments":[77],"817":[79],"sequences":[80],"ten":[82],"20":[85],"speakers,":[86],"promising":[87],"accuracies":[88],"62%":[90],"70%":[92],"were":[93],"obtained":[94],"speaker-independent":[96],"speaker-dependent":[98],"recognition,":[99],"respectively.":[100],"comparison":[102],"other":[104],"methods":[105],"Tulips1":[108],"audio-visual":[109],"database,":[110],"accuracy":[112],"92.7%":[113],"method":[116],"clearly":[117],"out":[118],"performs":[119],"others.":[121],"Advantages":[122],"approach":[125],"include":[126],"processing":[128],"robustness":[130],"monotonic":[132],"gray-scale":[133],"changes.":[134],"Moreover,":[135],"no":[136],"error":[137],"prone":[138],"segmentation":[139],"moving":[141],"lips":[142],"is":[143],"needed.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
