{"id":"https://openalex.org/W2129304007","doi":"https://doi.org/10.1109/icassp.2003.1199139","title":"A fusion scheme of visual and auditory modalities for event detection in sports video","display_name":"A fusion scheme of visual and auditory modalities for event detection in sports video","publication_year":2003,"publication_date":"2003-12-22","ids":{"openalex":"https://openalex.org/W2129304007","doi":"https://doi.org/10.1109/icassp.2003.1199139","mag":"2129304007"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1199139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1199139","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"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":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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/A5100413849","display_name":"Min Xu","orcid":"https://orcid.org/0000-0001-9581-8849"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Min Xu","raw_affiliation_strings":["Institute for Infocomm Research, Singapore","Inst. For Infocomm Res., Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Inst. For Infocomm Res., Singapore, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024879728","display_name":"Ling\u2010Yu Duan","orcid":"https://orcid.org/0000-0002-4491-2023"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ling-Yu Duan","raw_affiliation_strings":["Institute for Infocomm Research, Singapore","Inst. For Infocomm Res., Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Inst. For Infocomm Res., Singapore, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022636178","display_name":"Changsheng Xu","orcid":"https://orcid.org/0000-0001-8343-9665"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chang-Sheng Xu","raw_affiliation_strings":["Institute for Infocomm Research, Singapore","Inst. For Infocomm Res., Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Inst. For Infocomm Res., Singapore, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091670458","display_name":"Qi Tian","orcid":"https://orcid.org/0000-0003-1892-364X"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qi Tian","raw_affiliation_strings":["Institute for Infocomm Research, Singapore","Inst. For Infocomm Res., Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Inst. For Infocomm Res., Singapore, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100413849"],"corresponding_institution_ids":["https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":7.2151,"has_fulltext":false,"cited_by_count":67,"citation_normalized_percentile":{"value":0.97903226,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"3","issue":null,"first_page":"III","last_page":"189"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":1.0,"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":1.0,"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":0.994700014591217,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9660999774932861,"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":0.7792053818702698},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5678731799125671},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5586865544319153},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5575594902038574},{"id":"https://openalex.org/keywords/basketball","display_name":"Basketball","score":0.5435007810592651},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5404755473136902},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4897949695587158},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4881749749183655},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4497048556804657},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.424384742975235},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.36940109729766846},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3503015637397766},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3271256685256958}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7792053818702698},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5678731799125671},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5586865544319153},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5575594902038574},{"id":"https://openalex.org/C103189561","wikidata":"https://www.wikidata.org/wiki/Q5372","display_name":"Basketball","level":2,"score":0.5435007810592651},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5404755473136902},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4897949695587158},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4881749749183655},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4497048556804657},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.424384742975235},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.36940109729766846},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3503015637397766},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3271256685256958},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2003.1199139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1199139","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"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":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1493926850","https://openalex.org/W1602298796","https://openalex.org/W1995501964","https://openalex.org/W2048390151","https://openalex.org/W2074310276","https://openalex.org/W2109029335","https://openalex.org/W2138043589","https://openalex.org/W2141110380","https://openalex.org/W2143800062","https://openalex.org/W2155134542","https://openalex.org/W2156572156","https://openalex.org/W6649032756"],"related_works":["https://openalex.org/W2369330680","https://openalex.org/W2387007275","https://openalex.org/W2389047293","https://openalex.org/W2348951541","https://openalex.org/W2363923555","https://openalex.org/W2379277877","https://openalex.org/W2359223739","https://openalex.org/W2377467184","https://openalex.org/W2375049945","https://openalex.org/W2356570223"],"abstract_inverted_index":{"We":[0,129],"propose":[1],"an":[2],"effective":[3],"fusion":[4,118,133],"scheme":[5,19,119,134],"of":[6,38,51,67,108,164],"visual":[7],"and":[8,89,105,143,155],"auditory":[9,54],"modalities":[10],"to":[11,124,135],"detect":[12],"events":[13,69,149],"in":[14,102],"sports":[15,103,127,139,147,160],"video.":[16],"The":[17],"proposed":[18,117],"is":[20],"built":[21],"upon":[22],"semantic":[23,42,72,99],"shot":[24,46,100],"classification,":[25],"where":[26],"we":[27,48,79,92],"classify":[28],"video":[29,148,161],"shots":[30],"into":[31],"several":[32],"major":[33,45],"or":[34],"interesting":[35,83],"classes,":[36],"each":[37],"which":[39],"has":[40],"clear":[41],"meanings.":[43],"Among":[44],"classes":[47],"perform":[49],"classification":[50,101],"the":[52,65,116],"different":[53],"signal":[55],"segments":[56],"(i.e.":[57],"silence,":[58],"hitting":[59],"ball,":[60],"applause,":[61],"commentator":[62],"speech)":[63],"with":[64,70,112],"goal":[66],"detecting":[68],"strong":[71],"meaning.":[73],"For":[74],"instance,":[75],"for":[76,98],"tennis":[77],"video,":[78],"have":[80,93],"identified":[81],"five":[82],"events:":[84],"serve,":[85],"reserve,":[86],"ace,":[87],"return,":[88],"score.":[90],"Since":[91],"developed":[94],"a":[95,106,125],"unified":[96],"framework":[97],"videos":[104],"set":[107],"audio":[109],"mid-level":[110],"representation":[111],"supervised":[113],"learning":[114],"methods,":[115],"can":[120],"be":[121],"easily":[122],"adapted":[123],"new":[126],"game.":[128],"are":[130],"extending":[131],"this":[132],"three":[136],"additional":[137],"typical":[138],"videos:":[140],"basketball,":[141],"volleyball":[142],"soccer.":[144],"Correctly":[145],"detected":[146],"will":[150],"greatly":[151],"facilitate":[152],"further":[153],"structural":[154],"temporal":[156],"analysis,":[157],"such":[158],"as":[159],"skimming,":[162],"table":[163],"content,":[165],"etc.":[166]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
