{"id":"https://openalex.org/W2083976588","doi":"https://doi.org/10.1109/mmsp.2010.5662015","title":"Unsupervised detection of multimodal clusters in edited recordings","display_name":"Unsupervised detection of multimodal clusters in edited recordings","publication_year":2010,"publication_date":"2010-10-01","ids":{"openalex":"https://openalex.org/W2083976588","doi":"https://doi.org/10.1109/mmsp.2010.5662015","mag":"2083976588"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp.2010.5662015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2010.5662015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Workshop on Multimedia Signal Processing","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/A5075750735","display_name":"Alfred Dielmann","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Alfred Dielmann","raw_affiliation_strings":["IDIAP Research Institute, Martigny, Switzerland","IDIAP Research Institute, Rue Marconi 19, PO BOX 592, CH-1920 Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"IDIAP Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Research Institute, Rue Marconi 19, PO BOX 592, CH-1920 Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5075750735"],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":1.33729833,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80794444,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"177","last_page":"182"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9980999827384949,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9894000291824341,"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/audio-visual","display_name":"Audio visual","score":0.796850323677063},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7267711162567139},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6650941371917725},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6426793336868286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5533195734024048},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5164792537689209},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4842943549156189},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44124504923820496},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.43464338779449463},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34211164712905884},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.13592815399169922}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.796850323677063},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7267711162567139},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6650941371917725},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6426793336868286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5533195734024048},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5164792537689209},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4842943549156189},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44124504923820496},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.43464338779449463},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34211164712905884},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.13592815399169922},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp.2010.5662015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2010.5662015","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Workshop on Multimedia Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W125260059","https://openalex.org/W1493517262","https://openalex.org/W1558086160","https://openalex.org/W1587845029","https://openalex.org/W1591300715","https://openalex.org/W1597863258","https://openalex.org/W1971791733","https://openalex.org/W2002256968","https://openalex.org/W2006407062","https://openalex.org/W2033431158","https://openalex.org/W2035602559","https://openalex.org/W2048793669","https://openalex.org/W2097128017","https://openalex.org/W2112039577","https://openalex.org/W2118407121","https://openalex.org/W2118847468","https://openalex.org/W2119288237","https://openalex.org/W2124319216","https://openalex.org/W2159591770","https://openalex.org/W2164899449","https://openalex.org/W2170271758","https://openalex.org/W2171757151","https://openalex.org/W2199495299","https://openalex.org/W4236385439","https://openalex.org/W6633534837","https://openalex.org/W6635141280","https://openalex.org/W6635532411","https://openalex.org/W6643432533","https://openalex.org/W6678139733","https://openalex.org/W6684193366"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W2361861616","https://openalex.org/W4214877189","https://openalex.org/W2263699433","https://openalex.org/W2773965352","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2381179799","https://openalex.org/W2980279061"],"abstract_inverted_index":{"Edited":[0],"video":[1],"recordings,":[2,141],"such":[3,75],"as":[4,76],"talk-shows":[5],"and":[6,18,88,98,115],"sitcoms,":[7],"often":[8],"include":[9],"Audio-Visual":[10,54,65,102],"clusters:":[11],"frequent":[12],"repetitions":[13],"of":[14,79,86,129,138],"closely":[15],"related":[16],"acoustic":[17],"visual":[19],"content.":[20],"For":[21],"example":[22],"during":[23],"a":[24,30,127],"political":[25,131],"debate,":[26],"every":[27],"time":[28],"that":[29,63,143],"given":[31],"participant":[32,81],"holds":[33],"the":[34,52,72,77,109,150],"conversational":[35],"floor,":[36],"her/his":[37,48],"voice":[38],"tends":[39],"to":[40,68],"co-occur":[41],"with":[42],"camera":[43],"views":[44],"(i.e.":[45],"shots)":[46],"showing":[47],"portrait.":[49],"Differently":[50],"from":[51],"previous":[53],"clustering":[55],"works,":[56],"this":[57],"paper":[58],"proposes":[59],"an":[60],"unsupervised":[61,95],"approach":[62],"detects":[64],"clusters,":[66],"avoiding":[67],"make":[69],"assumptions":[70],"on":[71,126],"recording":[73],"content,":[74],"presence":[78],"specific":[80],"voices":[82],"or":[83],"faces.":[84],"Sequences":[85],"audio":[87,96],"shot":[89,99],"clusters":[90,103,147],"are":[91,104],"automatically":[92,144],"identified":[93],"using":[94],"diarization":[97],"segmentation":[100],"techniques.":[101],"then":[105],"formed":[106],"by":[107],"ranking":[108],"co-occurrences":[110],"between":[111],"these":[112],"two":[113],"segmentations":[114],"selecting":[116],"those":[117],"which":[118],"significantly":[119],"go":[120],"beyond":[121],"chance.":[122],"Numerical":[123],"experiments":[124],"performed":[125],"collection":[128],"70":[130],"debates,":[132],"comprising":[133],"more":[134],"than":[135],"43":[136],"hours":[137],"live":[139],"edited":[140],"showed":[142],"extracted":[145],"AudioVisual":[146],"well":[148],"match":[149],"ground-truth":[151],"annotation,":[152],"achieving":[153],"high":[154],"purity":[155],"performances.":[156]},"counts_by_year":[{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
