{"id":"https://openalex.org/W2107349681","doi":"https://doi.org/10.1145/1027527.1027587","title":"Analyzing discussion scene contents in instructional videos","display_name":"Analyzing discussion scene contents in instructional videos","publication_year":2004,"publication_date":"2004-10-10","ids":{"openalex":"https://openalex.org/W2107349681","doi":"https://doi.org/10.1145/1027527.1027587","mag":"2107349681"},"language":"en","primary_location":{"id":"doi:10.1145/1027527.1027587","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1027527.1027587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th annual ACM international conference on Multimedia","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/A5100785617","display_name":"Ying Li","orcid":"https://orcid.org/0000-0001-7370-1754"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying Li","raw_affiliation_strings":["IBM T.J. Watson Research Center, NY","[IBM T.J, Watson Research Center, NY]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, NY","institution_ids":[]},{"raw_affiliation_string":"[IBM T.J, Watson Research Center, NY]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112870855","display_name":"Chitra Dorai","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chitra Dorai","raw_affiliation_strings":["IBM T.J. Watson Research Center, NY","[IBM T.J, Watson Research Center, NY]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, NY","institution_ids":[]},{"raw_affiliation_string":"[IBM T.J, Watson Research Center, NY]","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":0.4756,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.56877294,"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":"264","last_page":"267"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":1.0,"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":1.0,"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/T12720","display_name":"Multimedia Communication and Technology","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9887999892234802,"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/cluster-analysis","display_name":"Cluster analysis","score":0.888738214969635},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8272875547409058},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.6774443984031677},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.5200755000114441},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45302504301071167},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.41568249464035034},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37515994906425476},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3633289337158203},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.1409696638584137}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.888738214969635},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8272875547409058},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.6774443984031677},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.5200755000114441},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45302504301071167},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.41568249464035034},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37515994906425476},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3633289337158203},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.1409696638584137},{"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/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1027527.1027587","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1027527.1027587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th annual ACM international conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:1398103","is_oa":false,"landing_page_url":"http://discovery.ucl.ac.uk/1398103/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"In: Schulzrinne, H and Dimitrova, N and Sasse, MA and Moon, SB and Lienhart, R, (eds.) (pp. pp. 264-267). ACM (2004)","raw_type":"Proceedings paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8799999952316284,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1482605500","https://openalex.org/W1484181928","https://openalex.org/W1971784203","https://openalex.org/W2122257751","https://openalex.org/W2124384059","https://openalex.org/W2164323948","https://openalex.org/W2319660501","https://openalex.org/W2402025388","https://openalex.org/W7065866364"],"related_works":["https://openalex.org/W3126131865","https://openalex.org/W4253186488","https://openalex.org/W2044344400","https://openalex.org/W1996938127","https://openalex.org/W2083611981","https://openalex.org/W2072507639","https://openalex.org/W4231814374","https://openalex.org/W2155964760","https://openalex.org/W2043380045","https://openalex.org/W2099557065"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"our":[3],"current":[4],"effort":[5],"on":[6,17,85,103],"analyzing":[7],"the":[8,62,66,104,110,113,118,129],"contents":[9],"of":[10,49,112,135],"discussion":[11,24,63,87,119],"scenes":[12,88],"in":[13,65],"instructional":[14,136],"videos":[15],"based":[16],"a":[18,23,36,74],"clustering":[19,38,106,115],"technique.":[20],"Specifically,":[21],"given":[22],"scene":[25,120],"pre-detected":[26],"from":[27,56,90,123],"an":[28,46],"education":[29],"or":[30,76],"training":[31],"video,":[32],"we":[33,59,96],"first":[34],"apply":[35],"mode-based":[37],"approach":[39],"to":[40],"group":[41],"all":[42],"speech":[43,55],"segments":[44],"into":[45,72],"optimal":[47],"number":[48],"clusters":[50],"where":[51],"each":[52],"cluster":[53],"contains":[54],"one":[57],"speaker;":[58],"then":[60],"analyze":[61],"patterns":[64],"scene,":[67],"and":[68,133],"subsequently":[69],"classify":[70],"it":[71],"either":[73],"2-speaker":[75],"multi-speaker":[77],"discussion.":[78],"Encouraging":[79],"classification":[80],"results":[81],"have":[82,97],"been":[83],"achieved":[84],"122":[86],"detected":[89],"five":[91],"IBM":[92],"MicroMBA":[93],"videos.":[94,137],"Moreover,":[95],"also":[98],"observed":[99],"fairly":[100],"good":[101],"performance":[102],"speaker":[105],"scheme,":[107],"which":[108],"demonstrates":[109],"superiority":[111],"proposed":[114],"approach.":[116],"Undoubtedly,":[117],"information":[121],"output":[122],"this":[124],"analysis":[125],"scheme":[126],"would":[127],"facilitate":[128],"content":[130],"browsing,":[131],"searching":[132],"understanding":[134]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}