{"id":"https://openalex.org/W2146035924","doi":"https://doi.org/10.1109/icpr.2008.4761474","title":"Audio-visual event classification via spatial-temporal-audio words","display_name":"Audio-visual event classification via spatial-temporal-audio words","publication_year":2008,"publication_date":"2008-12-01","ids":{"openalex":"https://openalex.org/W2146035924","doi":"https://doi.org/10.1109/icpr.2008.4761474","mag":"2146035924"},"language":"en","primary_location":{"id":"doi:10.1109/icpr.2008.4761474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2008.4761474","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/A5066499031","display_name":"Yu Cao","orcid":"https://orcid.org/0000-0002-3486-5518"},"institutions":[{"id":"https://openalex.org/I67328108","display_name":"California State University, Fresno","ror":"https://ror.org/03enmdz06","country_code":"US","type":"education","lineage":["https://openalex.org/I67328108"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Cao","raw_affiliation_strings":["Department of Computer Science, California State University, Fresno, CA, USA","Department of Computer Science, California State University, Fresno, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, California State University, Fresno, CA, USA","institution_ids":["https://openalex.org/I67328108"]},{"raw_affiliation_string":"Department of Computer Science, California State University, Fresno, CA#TAB#","institution_ids":["https://openalex.org/I67328108"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080594693","display_name":"Sung Baang","orcid":null},"institutions":[{"id":"https://openalex.org/I67328108","display_name":"California State University, Fresno","ror":"https://ror.org/03enmdz06","country_code":"US","type":"education","lineage":["https://openalex.org/I67328108"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sung Baang","raw_affiliation_strings":["Department of Computer Science, California State University, Fresno, CA, USA","Department of Computer Science, California State University, Fresno, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, California State University, Fresno, CA, USA","institution_ids":["https://openalex.org/I67328108"]},{"raw_affiliation_string":"Department of Computer Science, California State University, Fresno, CA#TAB#","institution_ids":["https://openalex.org/I67328108"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046784591","display_name":"Shih-Hsi Liu","orcid":"https://orcid.org/0000-0002-8172-6123"},"institutions":[{"id":"https://openalex.org/I67328108","display_name":"California State University, Fresno","ror":"https://ror.org/03enmdz06","country_code":"US","type":"education","lineage":["https://openalex.org/I67328108"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shih-Hsi Liu","raw_affiliation_strings":["Department of Computer Science, California State University, Fresno, CA, USA","Department of Computer Science, California State University, Fresno, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, California State University, Fresno, CA, USA","institution_ids":["https://openalex.org/I67328108"]},{"raw_affiliation_string":"Department of Computer Science, California State University, Fresno, CA#TAB#","institution_ids":["https://openalex.org/I67328108"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351449","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-6406-1983"},"institutions":[{"id":"https://openalex.org/I67328108","display_name":"California State University, Fresno","ror":"https://ror.org/03enmdz06","country_code":"US","type":"education","lineage":["https://openalex.org/I67328108"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["Department of Computer Science, California State University, Fresno, CA, USA","Department of Computer Science, California State University, Fresno, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, California State University, Fresno, CA, USA","institution_ids":["https://openalex.org/I67328108"]},{"raw_affiliation_string":"Department of Computer Science, California State University, Fresno, CA#TAB#","institution_ids":["https://openalex.org/I67328108"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107346944","display_name":"Sanqing Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125099","display_name":"Mayo Clinic in Arizona","ror":"https://ror.org/03jp40720","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1330342723","https://openalex.org/I4210125099"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanqing Hu","raw_affiliation_strings":["Department of Neurology, Mayo Clinic, Rochester, MN, USA","Department of Neurology, Mayo Clinic, Rochester, MN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Neurology, Mayo Clinic, Rochester, MN, USA","institution_ids":["https://openalex.org/I4210125099"]},{"raw_affiliation_string":"Department of Neurology, Mayo Clinic, Rochester, MN","institution_ids":["https://openalex.org/I4210125099"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4316,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53426124,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9990000128746033,"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":0.996999979019165,"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/probabilistic-latent-semantic-analysis","display_name":"Probabilistic latent semantic analysis","score":0.8640944957733154},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7647958993911743},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6567511558532715},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.616608738899231},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6125708818435669},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5601227283477783},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5099798440933228},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4594723582267761},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4389566481113434},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41847342252731323},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4145217537879944},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.364214688539505},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32427531480789185},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.13585257530212402},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.12132152915000916},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.09622937440872192}],"concepts":[{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.8640944957733154},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7647958993911743},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6567511558532715},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.616608738899231},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6125708818435669},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5601227283477783},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5099798440933228},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4594723582267761},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4389566481113434},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41847342252731323},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4145217537879944},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.364214688539505},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32427531480789185},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.13585257530212402},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.12132152915000916},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.09622937440872192},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icpr.2008.4761474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2008.4761474","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:10.1.1.214.5113","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.214.5113","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/TuAT8.7.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.485.4734","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.485.4734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://zimmer.csufresno.edu/~yucao/research/ICPR_08_Camera_Ready.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.550000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1880262756","https://openalex.org/W1967320926","https://openalex.org/W2013076218","https://openalex.org/W2068576236","https://openalex.org/W2096686458","https://openalex.org/W2097905551","https://openalex.org/W2103658758","https://openalex.org/W2113800095","https://openalex.org/W2113856781","https://openalex.org/W2119799051","https://openalex.org/W2134731454","https://openalex.org/W2140647972","https://openalex.org/W2143036568","https://openalex.org/W2158169396","https://openalex.org/W2171706135","https://openalex.org/W2533739470","https://openalex.org/W4237791300","https://openalex.org/W6674610679","https://openalex.org/W7053503548"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W2280377497","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W3174044702","https://openalex.org/W2967848559","https://openalex.org/W4283803360"],"abstract_inverted_index":{"In":[0],"this":[1,68],"paper,":[2],"we":[3],"propose":[4],"a":[5,18,38,84],"generative":[6],"model-based":[7],"approach":[8,14],"for":[9],"audio-visual":[10,58,93],"event":[11,59],"classification.":[12],"This":[13],"is":[15,61],"based":[16],"on":[17],"new":[19],"unsupervised":[20],"learning":[21],"method":[22],"using":[23,53],"an":[24],"extended":[25],"probabilistic":[26],"latent":[27,65],"semantic":[28],"analysis":[29],"(pLSA)":[30],"model.":[31,56,69],"We":[32],"represent":[33,89],"each":[34],"video":[35],"clip":[36],"as":[37,63],"collection":[39],"of":[40,73,86,92,100],"spatial-temporal-audio":[41,75],"words,":[42],"which":[43,82],"are":[44,77],"generated":[45],"by":[46],"fusing":[47],"the":[48,54,64,74,98,101],"visual":[49],"and":[50],"audio":[51],"features":[52],"pLSA":[55],"Each":[57],"class":[60],"treated":[62],"topic":[66],"in":[67],"The":[70],"probability":[71],"distributions":[72],"words":[76],"learnt":[78],"from":[79],"training":[80],"examples,":[81],"include":[83],"sequence":[85],"videos":[87],"that":[88],"different":[90],"types":[91],"events.":[94],"Experimental":[95],"results":[96],"show":[97],"effectiveness":[99],"proposed":[102],"approach.":[103]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}