{"id":"https://openalex.org/W3161610222","doi":"https://doi.org/10.1109/icassp39728.2021.9414924","title":"Detection of Audio-Video Synchronization Errors Via Event Detection","display_name":"Detection of Audio-Video Synchronization Errors Via Event Detection","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161610222","doi":"https://doi.org/10.1109/icassp39728.2021.9414924","mag":"3161610222"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5020690836","display_name":"Joshua P. Ebenezer","orcid":"https://orcid.org/0000-0003-4936-9784"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joshua P. Ebenezer","raw_affiliation_strings":["Amazon Prime Video,Seattle,WA","Amazon Prime Video, Seattle, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Prime Video,Seattle,WA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Prime Video, Seattle, WA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101488749","display_name":"Yongjun Wu","orcid":"https://orcid.org/0009-0009-6658-2027"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yongjun Wu","raw_affiliation_strings":["Amazon Prime Video,Seattle,WA","Amazon Prime Video, Seattle, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Prime Video,Seattle,WA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Prime Video, Seattle, WA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114194191","display_name":"Hai Wei","orcid":"https://orcid.org/0000-0002-9045-7113"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hai Wei","raw_affiliation_strings":["Amazon Prime Video,Seattle,WA","Amazon Prime Video, Seattle, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Prime Video,Seattle,WA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Prime Video, Seattle, WA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042275464","display_name":"Sriram Sethuraman","orcid":"https://orcid.org/0000-0002-2961-1599"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sriram Sethuraman","raw_affiliation_strings":["Amazon Prime Video,Seattle,WA","Amazon Prime Video, Seattle, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Prime Video,Seattle,WA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Prime Video, Seattle, WA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115590566","display_name":"Zongyi Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zongyi Liu","raw_affiliation_strings":["Amazon Prime Video,Seattle,WA","Amazon Prime Video, Seattle, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Prime Video,Seattle,WA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Prime Video, Seattle, WA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6792,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.70750472,"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":"4345","last_page":"4349"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9988999962806702,"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":0.9635000228881836,"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":0.8335555791854858},{"id":"https://openalex.org/keywords/sync","display_name":"sync","score":0.7735812664031982},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5821549296379089},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5049424767494202},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4992966651916504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49235713481903076},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4761350452899933},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4513125717639923},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4379331171512604},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4202554523944855},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.35889774560928345},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.23396539688110352},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.1617644727230072},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.14447754621505737}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8335555791854858},{"id":"https://openalex.org/C3913047","wikidata":"https://www.wikidata.org/wiki/Q1956265","display_name":"sync","level":3,"score":0.7735812664031982},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5821549296379089},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5049424767494202},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4992966651916504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49235713481903076},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4761350452899933},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4513125717639923},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4379331171512604},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4202554523944855},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.35889774560928345},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.23396539688110352},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.1617644727230072},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.14447754621505737},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":31,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1522734439","https://openalex.org/W1565247314","https://openalex.org/W2012296273","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2593610980","https://openalex.org/W2604379605","https://openalex.org/W2781330628","https://openalex.org/W2883595988","https://openalex.org/W2890052321","https://openalex.org/W2890952074","https://openalex.org/W2916798096","https://openalex.org/W2931364255","https://openalex.org/W2945919765","https://openalex.org/W2963155035","https://openalex.org/W2963854386","https://openalex.org/W2964048159","https://openalex.org/W2971680695","https://openalex.org/W2975680602","https://openalex.org/W2982325051","https://openalex.org/W3016659311","https://openalex.org/W3045062880","https://openalex.org/W3158553615","https://openalex.org/W6600983433","https://openalex.org/W6754048563","https://openalex.org/W6754392867","https://openalex.org/W6756871312","https://openalex.org/W6760224987","https://openalex.org/W6775888111","https://openalex.org/W6781150751"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W4315836293","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4243888788","https://openalex.org/W2157165686","https://openalex.org/W1975359510","https://openalex.org/W3004352674","https://openalex.org/W2088690926"],"abstract_inverted_index":{"We":[0,120],"present":[1],"a":[2,6,122],"new":[3],"method":[4,143],"and":[5,140],"large-scale":[7],"database":[8,124],"to":[9,23,46],"detect":[10,24,47],"audio-video":[11],"synchronization(A/V":[12],"sync)":[13],"errors":[14],"in":[15,37,55,84,89,104,111],"tennis":[16,30,134],"videos.":[17],"A":[18],"deep":[19,42],"network":[20,43,69],"is":[21,44,64,82,91,101,109,118],"trained":[22,45],"the":[25,29,35,38,48,52,56,61,67,71,75,80,86,94,99,105,112,148],"visual":[26,96],"signature":[27,50],"of":[28,51,74,125,131,133],"ball":[31,76],"being":[32,77],"hit":[33],"by":[34,66],"racquet":[36],"video":[39,90,106],"stream.":[40,58],"Another":[41],"auditory":[49],"same":[53],"event":[54,73,81,100],"audio":[57,62,68,72,113],"During":[59],"evaluation,":[60],"stream":[63,107],"searched":[65,92],"for":[70,93],"hit.":[78],"If":[79,98],"found":[83,103,110,141],"audio,":[85],"neighboring":[87],"interval":[88],"corresponding":[95],"signature.":[97],"not":[102],"but":[108],"stream,":[114],"A/V":[115,137],"sync":[116,138],"error":[117],"flagged.":[119],"developed":[121],"large-scaled":[123],"504,300":[126],"frames":[127],"from":[128],"6":[129],"hours":[130],"videos":[132],"events,":[135],"simulated":[136],"errors,":[139],"our":[142],"achieves":[144],"high":[145],"accuracy":[146],"on":[147],"task.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
