{"id":"https://openalex.org/W2100461058","doi":"https://doi.org/10.1109/icpr.2008.4760963","title":"Recovering audio-to-video synchronization by audiovisual correlation analysis","display_name":"Recovering audio-to-video synchronization by audiovisual correlation analysis","publication_year":2008,"publication_date":"2008-12-01","ids":{"openalex":"https://openalex.org/W2100461058","doi":"https://doi.org/10.1109/icpr.2008.4760963","mag":"2100461058"},"language":"en","primary_location":{"id":"doi:10.1109/icpr.2008.4760963","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2008.4760963","pdf_url":null,"source":{"id":"https://openalex.org/S4393916651","display_name":"Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition","issn_l":"1041-3278","issn":["1041-3278","1051-4651"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 19th International Conference on Pattern Recognition","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/A5101979563","display_name":"Yuyu Liu","orcid":"https://orcid.org/0000-0002-4814-8616"},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]},{"id":"https://openalex.org/I161296585","display_name":"Tokyo University of Science","ror":"https://ror.org/05sj3n476","country_code":"JP","type":"education","lineage":["https://openalex.org/I161296585"]},{"id":"https://openalex.org/I74640424","display_name":"Advanced Institute of Industrial Technology","ror":"https://ror.org/04f9apy08","country_code":"JP","type":"education","lineage":["https://openalex.org/I74640424"]},{"id":"https://openalex.org/I1304132090","display_name":"Sony (Taiwan)","ror":"https://ror.org/0214y7014","country_code":"TW","type":"company","lineage":["https://openalex.org/I1304132090","https://openalex.org/I4210143797"]}],"countries":["JP","TW","US"],"is_corresponding":true,"raw_author_name":"Yuyu Liu","raw_affiliation_strings":["Institute of Industrial Science, University of Tokyo","System Technologies Laboratories, Sony Corporation"],"affiliations":[{"raw_affiliation_string":"Institute of Industrial Science, University of Tokyo","institution_ids":["https://openalex.org/I74640424","https://openalex.org/I161296585"]},{"raw_affiliation_string":"System Technologies Laboratories, Sony Corporation","institution_ids":["https://openalex.org/I1304132090","https://openalex.org/I2800278093"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045996641","display_name":"Yoichi Sato","orcid":"https://orcid.org/0000-0003-0097-4537"},"institutions":[{"id":"https://openalex.org/I74640424","display_name":"Advanced Institute of Industrial Technology","ror":"https://ror.org/04f9apy08","country_code":"JP","type":"education","lineage":["https://openalex.org/I74640424"]},{"id":"https://openalex.org/I161296585","display_name":"Tokyo University of Science","ror":"https://ror.org/05sj3n476","country_code":"JP","type":"education","lineage":["https://openalex.org/I161296585"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoichi Sato","raw_affiliation_strings":["Institute of Industrial Science, University of Tokyo"],"affiliations":[{"raw_affiliation_string":"Institute of Industrial Science, University of Tokyo","institution_ids":["https://openalex.org/I74640424","https://openalex.org/I161296585"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101979563"],"corresponding_institution_ids":["https://openalex.org/I1304132090","https://openalex.org/I161296585","https://openalex.org/I2800278093","https://openalex.org/I74640424"],"apc_list":null,"apc_paid":null,"fwci":1.905,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.82487923,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2","issue":null,"first_page":"1","last_page":"4"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9966999888420105,"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/T11309","display_name":"Music and Audio Processing","score":0.9954000115394592,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/sync","display_name":"sync","score":0.8976758718490601},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.7842930555343628},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7510608434677124},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.5356521010398865},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5271524786949158},{"id":"https://openalex.org/keywords/kernel-density-estimation","display_name":"Kernel density estimation","score":0.41382017731666565},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4100944399833679},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.39075732231140137},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37400734424591064},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.16417238116264343},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12826597690582275},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10668894648551941},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.08372387290000916}],"concepts":[{"id":"https://openalex.org/C3913047","wikidata":"https://www.wikidata.org/wiki/Q1956265","display_name":"sync","level":3,"score":0.8976758718490601},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.7842930555343628},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7510608434677124},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5356521010398865},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5271524786949158},{"id":"https://openalex.org/C71134354","wikidata":"https://www.wikidata.org/wiki/Q458825","display_name":"Kernel density estimation","level":3,"score":0.41382017731666565},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4100944399833679},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.39075732231140137},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37400734424591064},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.16417238116264343},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12826597690582275},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10668894648551941},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.08372387290000916},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icpr.2008.4760963","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2008.4760963","pdf_url":null,"source":{"id":"https://openalex.org/S4393916651","display_name":"Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition","issn_l":"1041-3278","issn":["1041-3278","1051-4651"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 19th International Conference on Pattern Recognition","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.214.5599","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.214.5599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://figment.cse.usf.edu/~sfefilat/data/papers/MoAT4.4.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2105582566","https://openalex.org/W2118020555","https://openalex.org/W2118877769","https://openalex.org/W2147301311","https://openalex.org/W2148659689","https://openalex.org/W2158518995","https://openalex.org/W2164899449","https://openalex.org/W3097096317","https://openalex.org/W6677548441","https://openalex.org/W6683615932","https://openalex.org/W6684193366"],"related_works":["https://openalex.org/W2063547430","https://openalex.org/W2524993630","https://openalex.org/W2607244263","https://openalex.org/W2234430299","https://openalex.org/W1831690014","https://openalex.org/W1561022130","https://openalex.org/W1995263003","https://openalex.org/W2222580448","https://openalex.org/W4206700937","https://openalex.org/W1187005531"],"abstract_inverted_index":{"Audio-to-video":[0],"synchronization":[1],"(AV-sync)":[2],"may":[3],"drift":[4],"and":[5],"is":[6,46,82,93],"difficult":[7],"to":[8,22,64],"recover":[9,23],"without":[10],"dedicated":[11],"human":[12],"effort.":[13],"In":[14],"this":[15],"work,":[16],"we":[17],"develop":[18],"an":[19],"interactive":[20],"method":[21],"the":[24,66,72,77,97,104],"drifted":[25],"AV-sync":[26,92],"by":[27,96],"audiovisual":[28,74],"correlation":[29,75,81],"analysis.":[30],"Given":[31],"a":[32,35,38,44,52,61],"video":[33],"segment,":[34],"user":[36],"specifies":[37],"rough":[39],"time":[40],"span":[41],"during":[42],"which":[43],"person":[45],"speaking.":[47],"Our":[48],"system":[49],"first":[50],"detects":[51],"speaker":[53,78],"region":[54],"using":[55,84],"face":[56],"detection.":[57],"It":[58],"then":[59],"does":[60],"two-stage":[62],"search":[63],"find":[65],"optimum":[67,99],"AV-drift":[68],"that":[69],"can":[70],"maximize":[71],"average":[73],"inside":[76],"region.":[79],"The":[80],"evaluated":[83],"quadratic":[85],"mutual":[86],"information":[87],"with":[88],"kernel":[89],"density":[90],"estimation.":[91],"finally":[94],"recovered":[95],"detected":[98],"AV-drift.":[100],"Experimental":[101],"results":[102],"demonstrate":[103],"effectiveness":[105],"of":[106],"our":[107],"method.":[108]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
