{"id":"https://openalex.org/W2137611207","doi":"https://doi.org/10.1109/icme.2001.1237704","title":"Duration dependent input output markov models for audio-visual event detection","display_name":"Duration dependent input output markov models for audio-visual event detection","publication_year":2001,"publication_date":"2001-01-01","ids":{"openalex":"https://openalex.org/W2137611207","doi":"https://doi.org/10.1109/icme.2001.1237704","mag":"2137611207"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2001.1237704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2001.1237704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Multimedia and Expo, 2001. ICME 2001.","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/A5039299246","display_name":"Milind Naphade","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M.R. Naphade","raw_affiliation_strings":["Department of Electrical and Computer Engineering Coordinated Science Laboratory and Beckman Institute for Advanced Science and Technology, University of Illinois, Urbana-Champaign, USA","#N#\u2004University of Illinois"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering Coordinated Science Laboratory and Beckman Institute for Advanced Science and Technology, University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"#N#\u2004University of Illinois","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002107058","display_name":"A. Garg","orcid":"https://orcid.org/0000-0001-9155-4794"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Garg","raw_affiliation_strings":["Department of Electrical and Computer Engineering Coordinated Science Laboratory and Beckman Institute for Advanced Science and Technology, University of Illinois, Urbana-Champaign, USA","University of Illinois at Urbana Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering Coordinated Science Laboratory and Beckman Institute for Advanced Science and Technology, University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101457342","display_name":"Thomas S. Huang","orcid":"https://orcid.org/0000-0001-8474-5859"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"T.S. Huang","raw_affiliation_strings":["Department of Electrical and Computer Engineering Coordinated Science Laboratory and Beckman Institute for Advanced Science and Technology, University of Illinois, Urbana-Champaign, USA","University of Illinois at Urbana Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering Coordinated Science Laboratory and Beckman Institute for Advanced Science and Technology, University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8802,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.85977115,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"253","last_page":"256"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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/T11309","display_name":"Music and Audio Processing","score":1.0,"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":0.9979000091552734,"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/T10860","display_name":"Speech and Audio Processing","score":0.9957000017166138,"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/duration","display_name":"Duration (music)","score":0.7786823511123657},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6875892281532288},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6071541905403137},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5436683297157288},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5043569803237915},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5043221712112427},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.4501131772994995},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.39241892099380493},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3357952833175659},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.17696213722229004},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1711530089378357},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11049970984458923},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.07277554273605347}],"concepts":[{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.7786823511123657},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6875892281532288},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6071541905403137},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5436683297157288},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5043569803237915},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5043221712112427},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4501131772994995},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.39241892099380493},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3357952833175659},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.17696213722229004},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1711530089378357},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11049970984458923},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.07277554273605347},{"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":1,"locations":[{"id":"doi:10.1109/icme.2001.1237704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2001.1237704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Multimedia and Expo, 2001. ICME 2001.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1528056001","https://openalex.org/W1943540054","https://openalex.org/W2002591263","https://openalex.org/W2003021679","https://openalex.org/W2069960468","https://openalex.org/W2114469907","https://openalex.org/W2125838338","https://openalex.org/W2131193678","https://openalex.org/W2152239535","https://openalex.org/W2154641643","https://openalex.org/W2165959773","https://openalex.org/W3181498640","https://openalex.org/W6798644212"],"related_works":["https://openalex.org/W1510894296","https://openalex.org/W2134386692","https://openalex.org/W2379651310","https://openalex.org/W2082284720","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2084326697","https://openalex.org/W2194396582","https://openalex.org/W2027903142","https://openalex.org/W2116722627"],"abstract_inverted_index":{"Detecting":[0],"semantic":[1,31],"events":[2,45],"from":[3],"audio-visual":[4,88],"data":[5],"with":[6,60,99],"Spatiotemporal":[7],"support":[8],"is":[9],"a":[10,35],"challenging":[11],"multimedia":[12],"Understanding":[13],"problem.":[14],"The":[15,50],"difficulty":[16],"lies":[17],"in":[18],"the":[19,53,61,73,83,87,93,97,100,105],"gap":[20],"that":[21,109],"exists":[22],"between":[23],"low":[24],"level":[25,30],"media":[26],"features":[27],"and":[28],"high":[29],"concept.":[32],"We":[33,81,91],"present":[34],"duration":[36,58,112],"dependent":[37],"input":[38,64],"output":[39,67],"Markov":[40],"model":[41,56,86],"(DDIOMM)":[42],"to":[43,55,66,85],"detect":[44],"based":[46],"on":[47],"multiple":[48],"modalities.":[49],"DDIOMM":[51,84,98],"combines":[52],"ability":[54],"nonexponential":[57],"densities":[59],"mapping":[62],"of":[63,96,111],"sequences":[65],"sequences.":[68],"In":[69],"spirit":[70],"it":[71],"resembles":[72],"IOHMMs":[74],"[1]":[75],"as":[76,78,102,104],"well":[77,103],"inhomogeneousHMMs":[79],"[2].":[80],"use":[82],"event":[89],"explosion.":[90],"compare":[92],"detection":[94,114],"performance":[95],"IOMM":[101],"HMM.":[106],"Experiments":[107],"reveal":[108],"modeling":[110],"improves":[113],"performance.":[115]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}