{"id":"https://openalex.org/W2164323948","doi":"https://doi.org/10.1109/icme.2004.1394468","title":"Detecting discussion scenes in instructional videos","display_name":"Detecting discussion scenes in instructional videos","publication_year":2005,"publication_date":"2005-03-21","ids":{"openalex":"https://openalex.org/W2164323948","doi":"https://doi.org/10.1109/icme.2004.1394468","mag":"2164323948"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2004.1394468","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2004.1394468","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Multimedia and Expo (ICME) (IEEE Cat. No.04TH8763)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5088449514","display_name":"Y. Li","orcid":"https://orcid.org/0009-0000-6426-6594"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Y. Li","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111478017","display_name":"C. Dorai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Dorai","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":1.0188,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77058672,"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":"1311","last_page":"1314"},"is_retracted":false,"is_paratext":false,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9984999895095825,"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":0.9955999851226807,"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":0.8387707471847534},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.7156262397766113},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6367879509925842},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.5473336577415466},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5463840961456299},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.5399946570396423},{"id":"https://openalex.org/keywords/transition","display_name":"Transition (genetics)","score":0.4110254645347595},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41055524349212646},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35070884227752686},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33558642864227295},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33477887511253357}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8387707471847534},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.7156262397766113},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6367879509925842},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.5473336577415466},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5463840961456299},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.5399946570396423},{"id":"https://openalex.org/C194232998","wikidata":"https://www.wikidata.org/wiki/Q1606712","display_name":"Transition (genetics)","level":3,"score":0.4110254645347595},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41055524349212646},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35070884227752686},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33558642864227295},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33477887511253357},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2004.1394468","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2004.1394468","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Multimedia and Expo (ICME) (IEEE Cat. No.04TH8763)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8700000047683716,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1482605500","https://openalex.org/W1893339448","https://openalex.org/W1924751832","https://openalex.org/W1943968395","https://openalex.org/W1996262499","https://openalex.org/W2124384059","https://openalex.org/W2131981197","https://openalex.org/W6628911050","https://openalex.org/W6639518841","https://openalex.org/W6640250534","https://openalex.org/W6640709233","https://openalex.org/W6678336504"],"related_works":["https://openalex.org/W3126131865","https://openalex.org/W2386430105","https://openalex.org/W2044344400","https://openalex.org/W4253186488","https://openalex.org/W1996938127","https://openalex.org/W2043380045","https://openalex.org/W2356521405","https://openalex.org/W4231814374","https://openalex.org/W2099557065","https://openalex.org/W2484410460"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,24,33,65,70,103],"problem":[4],"of":[5,19,27,108],"detecting":[6],"discussion":[7,50],"scenes":[8,51],"in":[9,52],"instructional":[10,109],"videos":[11],"using":[12,35],"statistical":[13],"approaches.":[14],"Specifically,":[15],"given":[16],"a":[17,36,42],"series":[18],"speech":[20],"segments":[21],"separated":[22],"from":[23],"audio":[25],"tracks":[26],"educational":[28,84],"videos,":[29,88],"we":[30,62],"first":[31],"model":[32,39,67],"instructor":[34],"Gaussian":[37],"mixture":[38],"(GMM),":[40],"then":[41],"four-state":[43],"transition":[44],"machine":[45],"is":[46],"designed":[47],"to":[48,68],"extract":[49],"real-time,":[53],"based":[54],"on":[55,82],"detected":[56],"instructor-student":[57],"speaker":[58],"change":[59],"points.":[60],"Meanwhile,":[61],"keep":[63],"updating":[64],"GMM":[66],"accommodate":[69],"instructor's":[71],"voice":[72],"variation":[73],"along":[74],"time.":[75],"Promising":[76],"experimental":[77],"results":[78],"have":[79,94],"been":[80,95],"achieved":[81],"five":[83],"(IBM":[85],"MicroMBA":[86],"program)":[87],"and":[89,106],"very":[90],"interesting":[91],"instruction/teaching":[92],"patterns":[93],"observed.":[96],"The":[97],"extracted":[98],"scene":[99],"information":[100],"would":[101],"facilitate":[102],"semantic":[104],"indexing":[105],"structuralization":[107],"video":[110],"content.":[111]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
