{"id":"https://openalex.org/W2130234690","doi":"https://doi.org/10.1109/icme.2001.1237652","title":"Scene detection by audio-visual features","display_name":"Scene detection by audio-visual features","publication_year":2001,"publication_date":"2001-01-01","ids":{"openalex":"https://openalex.org/W2130234690","doi":"https://doi.org/10.1109/icme.2001.1237652","mag":"2130234690"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2001.1237652","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2001.1237652","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/A5103343725","display_name":"A. Yoshitaka","orcid":null},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"A. Yoshitaka","raw_affiliation_strings":["Faculty of Engineering, Hiroshima University, Higashihiroshima, Hiroshima, Japan"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Hiroshima University, Higashihiroshima, Hiroshima, Japan","institution_ids":["https://openalex.org/I113306721"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085907353","display_name":"M. Miyake","orcid":"https://orcid.org/0000-0003-4417-9762"},"institutions":[{"id":"https://openalex.org/I113306721","display_name":"Hiroshima University","ror":"https://ror.org/03t78wx29","country_code":"JP","type":"education","lineage":["https://openalex.org/I113306721"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"M. Miyake","raw_affiliation_strings":["Faculty of Engineering, Hiroshima University, Higashihiroshima, Hiroshima, Japan"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Hiroshima University, Higashihiroshima, Hiroshima, Japan","institution_ids":["https://openalex.org/I113306721"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103343725"],"corresponding_institution_ids":["https://openalex.org/I113306721"],"apc_list":null,"apc_paid":null,"fwci":1.4441,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.85667334,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"48","last_page":"51"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9998999834060669,"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":0.9998999834060669,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.996399998664856,"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":0.9955999851226807,"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/computer-science","display_name":"Computer science","score":0.7847501039505005},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7272382974624634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7164182066917419},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6190818548202515},{"id":"https://openalex.org/keywords/scene-statistics","display_name":"Scene statistics","score":0.5937723517417908},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.5372030735015869},{"id":"https://openalex.org/keywords/change-detection","display_name":"Change detection","score":0.5149462819099426},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.49257737398147583},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4664537310600281},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4584931433200836},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.4417901337146759},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3577198088169098},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.27371692657470703},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.2734502851963043},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.11054584383964539},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.0993853211402893},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06926706433296204},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.06791883707046509}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7847501039505005},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7272382974624634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7164182066917419},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6190818548202515},{"id":"https://openalex.org/C197654239","wikidata":"https://www.wikidata.org/wiki/Q7430757","display_name":"Scene statistics","level":3,"score":0.5937723517417908},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.5372030735015869},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.5149462819099426},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.49257737398147583},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4664537310600281},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4584931433200836},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.4417901337146759},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3577198088169098},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27371692657470703},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2734502851963043},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.11054584383964539},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0993853211402893},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06926706433296204},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.06791883707046509},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2001.1237652","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2001.1237652","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":[{"display_name":"Sustainable cities and communities","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1597863258","https://openalex.org/W2114762973","https://openalex.org/W2114851223","https://openalex.org/W2119261219","https://openalex.org/W2160376883"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2568858292","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W2148858788"],"abstract_inverted_index":{"Compared":[0],"with":[1,41,78],"cut":[2],"detection":[3,9,28,52,115],"of":[4,16,49,62,88,107,112],"video":[5,30,56],"data,":[6],"scene":[7,50,108,113],"boundary":[8,27,51,114],"is":[10,75],"more":[11],"complicated":[12],"since":[13],"the":[14,46,86,100,105,110],"transition":[15,106],"an":[17],"atmosphere":[18],"and/or":[19],"visual":[20,79],"scenery":[21],"need":[22],"to":[23,84,103],"be":[24],"recognized.":[25],"Scene":[26],"by":[29,53],"processing":[31],"may":[32],"contain":[33],"ambiguity":[34],"because":[35],"scenes":[36],"are":[37],"not":[38],"always":[39],"classified":[40],"clear":[42],"distinction.":[43],"We":[44],"propose":[45],"noble":[47],"way":[48],"audio":[54,65,101],"and":[55,64,72],"features,":[57],"which":[58],"takes":[59],"editing":[60],"pattern":[61],"movies":[63],"features":[66],"into":[67],"account.":[68],"Back-ground":[69],"noise":[70],"extraction":[71,81],"its":[73],"classification":[74],"cooperatively":[76],"evaluated":[77],"feature":[80],"in":[82],"order":[83],"detect":[85,104],"sequence":[87],"shots":[89],"as":[90,116],"a":[91],"single":[92],"scene.":[93],"In":[94],"this":[95],"paper,":[96],"we":[97],"show":[98],"that":[99],"analysis":[102],"improves":[109],"accuracy":[111],"well.":[117]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}