{"id":"https://openalex.org/W2071925068","doi":"https://doi.org/10.1002/(sici)1098-1098(1998)9:5<320::aid-ima2>3.0.co;2-c","title":"Indexing audiovisual databases through joint audio and video processing","display_name":"Indexing audiovisual databases through joint audio and video processing","publication_year":1998,"publication_date":"1998-01-01","ids":{"openalex":"https://openalex.org/W2071925068","doi":"https://doi.org/10.1002/(sici)1098-1098(1998)9:5<320::aid-ima2>3.0.co;2-c","mag":"2071925068"},"language":"en","primary_location":{"id":"doi:10.1002/(sici)1098-1098(1998)9:5<320::aid-ima2>3.0.co;2-c","is_oa":false,"landing_page_url":"https://doi.org/10.1002/(sici)1098-1098(1998)9:5<320::aid-ima2>3.0.co;2-c","pdf_url":null,"source":{"id":"https://openalex.org/S15952048","display_name":"International Journal of Imaging Systems and Technology","issn_l":"0899-9457","issn":["0899-9457","1098-1098"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Imaging Systems and Technology","raw_type":"journal-article"},"type":"paratext","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/A5110139694","display_name":"Caterina Saraceno","orcid":null},"institutions":[{"id":"https://openalex.org/I79940851","display_name":"University of Brescia","ror":"https://ror.org/02q2d2610","country_code":"IT","type":"education","lineage":["https://openalex.org/I79940851"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Caterina Saraceno","raw_affiliation_strings":["Signals and Communications Laboratory, Department of Electronics for Automation, University of Brescia, Brescia I-25123, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signals and Communications Laboratory, Department of Electronics for Automation, University of Brescia, Brescia I-25123, Italy","institution_ids":["https://openalex.org/I79940851"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077643154","display_name":"Riccardo Leonardi","orcid":"https://orcid.org/0000-0003-0755-1924"},"institutions":[{"id":"https://openalex.org/I79940851","display_name":"University of Brescia","ror":"https://ror.org/02q2d2610","country_code":"IT","type":"education","lineage":["https://openalex.org/I79940851"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Riccardo Leonardi","raw_affiliation_strings":["Signals and Communications Laboratory, Department of Electronics for Automation, University of Brescia, Brescia I-25123, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signals and Communications Laboratory, Department of Electronics for Automation, University of Brescia, Brescia I-25123, Italy","institution_ids":["https://openalex.org/I79940851"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5077643154"],"corresponding_institution_ids":["https://openalex.org/I79940851"],"apc_list":{"value":3450,"currency":"USD","value_usd":3450},"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":"5","first_page":"320","last_page":"331"},"is_retracted":false,"is_paratext":true,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9959999918937683,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9958999752998352,"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":0.8554768562316895},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.668846845626831},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.5393246412277222},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4998972415924072},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4554117023944855},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43547502160072327},{"id":"https://openalex.org/keywords/semantic-analysis","display_name":"Semantic analysis (machine learning)","score":0.4223968982696533},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.40593069791793823},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3873363435268402},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3647300601005554},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3416612148284912},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3374730050563812},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.17430496215820312},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.14997166395187378},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.10586941242218018}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8554768562316895},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.668846845626831},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.5393246412277222},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4998972415924072},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4554117023944855},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43547502160072327},{"id":"https://openalex.org/C2777946921","wikidata":"https://www.wikidata.org/wiki/Q7449044","display_name":"Semantic analysis (machine learning)","level":2,"score":0.4223968982696533},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.40593069791793823},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3873363435268402},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3647300601005554},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3416612148284912},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3374730050563812},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.17430496215820312},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.14997166395187378},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.10586941242218018},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1002/(sici)1098-1098(1998)9:5<320::aid-ima2>3.0.co;2-c","is_oa":false,"landing_page_url":"https://doi.org/10.1002/(sici)1098-1098(1998)9:5<320::aid-ima2>3.0.co;2-c","pdf_url":null,"source":{"id":"https://openalex.org/S15952048","display_name":"International Journal of Imaging Systems and Technology","issn_l":"0899-9457","issn":["0899-9457","1098-1098"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Imaging Systems and Technology","raw_type":"journal-article"},{"id":"pmh:oai:iris.unibs.it:11379/8146","is_oa":false,"landing_page_url":"http://hdl.handle.net/11379/8146","pdf_url":null,"source":{"id":"https://openalex.org/S4306400804","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Brescia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66752286","host_organization_name":"University of Milano-Bicocca","host_organization_lineage":["https://openalex.org/I66752286"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W1975359510","https://openalex.org/W2494533082","https://openalex.org/W4214771044","https://openalex.org/W4387698063","https://openalex.org/W4382560817","https://openalex.org/W3004352674","https://openalex.org/W3110605476","https://openalex.org/W3043119899","https://openalex.org/W1620668332"],"abstract_inverted_index":{"This":[0],"work":[1,94],"deals":[2],"with":[3],"the":[4,65,68,71,158,185,188,195,224,240,244,288,311],"representation":[5],"of":[6,32,61,67,144,147,187,198,210,223,269,290,301,313],"audiovisual":[7,43,225,275],"information,":[8],"to":[9,26,40,109,156,184,194,214,219,282],"organize":[10,41],"its":[11],"content":[12],"for":[13],"future":[14],"tasks":[15],"such":[16,84],"as":[17,85],"retrieval":[18],"and":[19,35,190,252,262,297],"information":[20,37],"browsing.":[21],"Some":[22],"indications":[23],"are":[24,173,212,258,279],"provided":[25],"demonstrate":[27],"that":[28,96,161,179,191,206],"a":[29,52,76,111,122,135,141,220,232,273,307,315,319],"cross-modal":[30,69],"analysis":[31],"simple":[33],"visual":[34],"audio":[36,97,137,148,171,199,211,241,284],"is":[38,55,99,130,139,154,177,182],"sufficient":[39],"an":[42],"sequence":[44],"into":[45,243],"semantically":[46],"meaningful":[47,155],"segments.":[48],"Each":[49],"segment":[50],"defines":[51],"scene":[53,72,167],"which":[54],"coherent":[56],"from":[57],"some":[58,324],"semantic":[59,151,186,221],"point":[60],"view.":[62],"Depending":[63,286],"on":[64,287],"sophistication":[66],"analysis,":[70],"may":[73],"represent":[74],"either":[75],"generic":[77,136,274],"story":[78],"unit":[79],"or":[80,87],"more":[81],"complex":[82],"situations":[83],"dialogues":[86],"actions.":[88],"The":[89,203,227,236,321],"results":[90],"shown":[91],"in":[92,101,231,310,318,327],"this":[93,283],"indicate":[95],"classification":[98],"key":[100],"establishing":[102],"relationships":[103],"among":[104,125],"consecutive":[105],"shots,":[106,127],"allowing":[107],"us":[108],"reach":[110],"scene-level":[112],"description.":[113],"A":[114],"higher":[115],"abstraction":[116],"level":[117],"can":[118,163,303],"be":[119,304],"reached":[120],"when":[121],"correlation":[123],"exists":[124],"nonconsecutive":[126],"defining":[128],"what":[129],"called":[131],"\u201cvideo":[132],"idioms.\u201d":[133],"Accordingly,":[134],"model":[138],"proposed:":[140],"linear":[142],"combination":[143],"four":[145,246],"classes":[146,159,205],"signals.":[149],"For":[150],"purposes,":[152],"it":[153,176,192],"select":[157],"so":[160],"they":[162],"serve":[164],"any":[165,216],"subsequent":[166],"characterization.":[168],"When":[169],"several":[170],"sources":[172],"combined":[174],"simultaneously,":[175],"assumed":[178],"only":[180],"one":[181],"linked":[183],"scene,":[189],"corresponds":[193],"dominant":[196],"class":[197],"(in":[200],"energy":[201],"terms).":[202],"different":[204,299,329],"identify":[207],"each":[208],"type":[209,289],"selected":[213],"facilitate":[215],"decision":[217],"related":[218],"characterization":[222],"information.":[226],"problem":[228],"therefore":[229],"lies":[230],"source":[233,270,291],"separation":[234],"task.":[235],"proposed":[237],"scheme":[238],"classifies":[239],"signal":[242],"following":[245],"component":[247],"types:":[248],"speech,":[249],"music,":[250],"silence,":[251],"miscellaneous":[253],"other":[254],"sounds.":[255],"Its":[256],"performance":[257],"quite":[259],"satisfactory":[260],"(\u223c90%)":[261],"were":[263],"tested":[264],"extensively":[265],"using":[266],"various":[267],"types":[268,300],"material.":[271],"Considering":[272],"sequence,":[276],"video":[277],"shots":[278],"merged":[280],"according":[281],"classification.":[285],"material":[292],"(broadcast":[293],"news,":[294],"commercials,":[295],"documentaries,":[296],"movies),":[298],"scenes":[302],"identified,":[305],"e.g.,":[306],"single":[308],"advertisement":[309],"case":[312],"commercials;":[314],"dialogue":[316],"situation":[317],"movie.":[320],"article":[322],"describes":[323],"experimental":[325],"simulations":[326],"these":[328],"fields.":[330],"\u00a9":[331],"1998":[332,345],"John":[333],"Wiley":[334],"&":[335],"Sons,":[336],"Inc.":[337],"Int":[338],"J":[339],"Imaging":[340],"Syst":[341],"Technol,":[342],"9,":[343],"320\u2013331,":[344]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2016-06-24T00:00:00"}
