{"id":"https://openalex.org/W2114447562","doi":"https://doi.org/10.1109/icarcv.2004.1469078","title":"Efficient identification of speakers in news video based on shot segmentation","display_name":"Efficient identification of speakers in news video based on shot segmentation","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2114447562","doi":"https://doi.org/10.1109/icarcv.2004.1469078","mag":"2114447562"},"language":"en","primary_location":{"id":"doi:10.1109/icarcv.2004.1469078","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarcv.2004.1469078","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICARCV 2004 8th Control, Automation, Robotics and Vision Conference, 2004.","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/A5047781677","display_name":"Qing Chang","orcid":"https://orcid.org/0000-0002-1320-6046"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qing Chang","raw_affiliation_strings":["Dept. of Comput. Sci. & Eng., Fudan Univ., Shanghai, China","[Dept. of Comput. Sci. & Eng., Fudan Univ., Shanghai, China]"],"affiliations":[{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Fudan Univ., Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"[Dept. of Comput. Sci. & Eng., Fudan Univ., Shanghai, China]","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003418019","display_name":"Xiangyang Xue","orcid":"https://orcid.org/0000-0002-4897-9209"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang-yang Xue","raw_affiliation_strings":["Dept. of Comput. Sci. & Eng., Fudan Univ., Shanghai, China","[Dept. of Comput. Sci. & Eng., Fudan Univ., Shanghai, China]"],"affiliations":[{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Fudan Univ., Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"[Dept. of Comput. Sci. & Eng., Fudan Univ., Shanghai, China]","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070355771","display_name":"Hong Lu","orcid":"https://orcid.org/0000-0002-4572-2854"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Lu","raw_affiliation_strings":["Dept. of Comput. Sci. & Eng., Fudan Univ., Shanghai, China","[Dept. of Comput. Sci. & Eng., Fudan Univ., Shanghai, China]"],"affiliations":[{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Fudan Univ., Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"[Dept. of Comput. Sci. & Eng., Fudan Univ., Shanghai, China]","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102147471","display_name":"You-san Nie","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"You-san Nie","raw_affiliation_strings":["Dept. of Comput. Sci. & Eng., Fudan Univ., Shanghai, China","[Dept. of Comput. Sci. & Eng., Fudan Univ., Shanghai, China]"],"affiliations":[{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Fudan Univ., Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"[Dept. of Comput. Sci. & Eng., Fudan Univ., Shanghai, China]","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5047781677"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.186985,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1533","last_page":"1537 Vol. 2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9994999766349792,"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":0.9994000196456909,"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/shot","display_name":"Shot (pellet)","score":0.8628933429718018},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8036065697669983},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7298980355262756},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6306169629096985},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.622397243976593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5486885905265808},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5099114179611206},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4841059446334839},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.45060279965400696},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.39606112241744995},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3902747631072998},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.18100503087043762}],"concepts":[{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.8628933429718018},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8036065697669983},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7298980355262756},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6306169629096985},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.622397243976593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5486885905265808},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5099114179611206},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4841059446334839},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.45060279965400696},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.39606112241744995},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3902747631072998},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.18100503087043762},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icarcv.2004.1469078","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarcv.2004.1469078","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICARCV 2004 8th Control, Automation, Robotics and Vision Conference, 2004.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1835965142","https://openalex.org/W1993518282","https://openalex.org/W2008957275","https://openalex.org/W2075662881","https://openalex.org/W2098498971","https://openalex.org/W2128838222","https://openalex.org/W2131981197","https://openalex.org/W2153823022","https://openalex.org/W2165880886","https://openalex.org/W4248215879","https://openalex.org/W6638699884","https://openalex.org/W6674697456","https://openalex.org/W6682407652"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1521049138"],"abstract_inverted_index":{"An":[0],"effective":[1],"method":[2],"for":[3],"speaker":[4,43,63],"identification":[5,64],"in":[6,11,44,50,85,93],"news":[7,48],"video":[8,49],"is":[9,15,29,40,56,65],"presented":[10],"this":[12],"paper,":[13],"which":[14],"based":[16,34],"on":[17,35,58,70],"shot":[18,32,46],"segmentation":[19,33],"and":[20,24],"exploits":[21],"both":[22],"audio":[23,28,68],"visual":[25],"cues.":[26],"Firstly,":[27],"segmented":[30],"by":[31],"the":[36,71],"observation":[37],"that":[38,78],"there":[39],"only":[41],"one":[42],"a":[45],"of":[47],"most":[51],"cases.":[52],"Furthermore,":[53],"speech/non-speech":[54],"discrimination":[55],"implemented":[57],"each":[59],"shot.":[60],"Finally,":[61],"text-independent":[62],"proposed":[66],"using":[67],"features":[69],"discriminated":[72],"speech":[73],"shots.":[74],"Experimental":[75],"results":[76],"show":[77],"our":[79],"algorithm":[80],"can":[81,90],"obtain":[82],"satisfactory":[83],"performance":[84],"identifying":[86],"speakers,":[87],"so":[88],"it":[89],"be":[91],"used":[92],"real":[94],"application.":[95]},"counts_by_year":[],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}