{"id":"https://openalex.org/W2157485273","doi":"https://doi.org/10.1109/icdcsw.2004.1284019","title":"Video scene determination using audiovisual data analysis","display_name":"Video scene determination using audiovisual data analysis","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2157485273","doi":"https://doi.org/10.1109/icdcsw.2004.1284019","mag":"2157485273"},"language":"en","primary_location":{"id":"doi:10.1109/icdcsw.2004.1284019","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdcsw.2004.1284019","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"24th International Conference on Distributed Computing Systems Workshops, 2004. Proceedings.","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/A5073263477","display_name":"Seungmin Rho","orcid":"https://orcid.org/0000-0003-1936-6785"},"institutions":[{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Seungmin Rho","raw_affiliation_strings":["Graduate School of Information and Communication, Ajou University, Suwon, South Korea"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information and Communication, Ajou University, Suwon, South Korea","institution_ids":["https://openalex.org/I57664883"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071337745","display_name":"Eenjun Hwang","orcid":"https://orcid.org/0000-0002-0418-4092"},"institutions":[{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Eenjun Hwang","raw_affiliation_strings":["Graduate School of Information and Communication, Ajou University, Suwon, South Korea"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information and Communication, Ajou University, Suwon, South Korea","institution_ids":["https://openalex.org/I57664883"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5073263477"],"corresponding_institution_ids":["https://openalex.org/I57664883"],"apc_list":null,"apc_paid":null,"fwci":0.5609,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.68946176,"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":"124","last_page":"129"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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":0.989799976348877,"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":0.8625612258911133},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.8019014000892639},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6825336217880249},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6812475323677063},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6473139524459839},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5839044451713562},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.5096437931060791},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.42894038558006287},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.4253756105899811},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4030683636665344},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33913862705230713},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.32935214042663574},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.2241707146167755},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.18467602133750916},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.17865127325057983}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8625612258911133},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.8019014000892639},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6825336217880249},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6812475323677063},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6473139524459839},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5839044451713562},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.5096437931060791},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.42894038558006287},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.4253756105899811},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4030683636665344},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33913862705230713},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.32935214042663574},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2241707146167755},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.18467602133750916},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.17865127325057983},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdcsw.2004.1284019","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdcsw.2004.1284019","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"24th International Conference on Distributed Computing Systems Workshops, 2004. Proceedings.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W137585820","https://openalex.org/W1568422127","https://openalex.org/W1970704574","https://openalex.org/W2027518030","https://openalex.org/W2032360374","https://openalex.org/W2044222806","https://openalex.org/W2057613716","https://openalex.org/W2106055371","https://openalex.org/W2109553605","https://openalex.org/W2111331420","https://openalex.org/W2124660252","https://openalex.org/W2124988752","https://openalex.org/W2128838222","https://openalex.org/W2130234690","https://openalex.org/W2137542411","https://openalex.org/W2144679084","https://openalex.org/W2150207155","https://openalex.org/W2158513576","https://openalex.org/W6664934753","https://openalex.org/W6678725532"],"related_works":["https://openalex.org/W2159474661","https://openalex.org/W2750276072","https://openalex.org/W2507139944","https://openalex.org/W1873761914","https://openalex.org/W2499429124","https://openalex.org/W1498836399","https://openalex.org/W2098934641","https://openalex.org/W2008725429","https://openalex.org/W2050333689","https://openalex.org/W1479881079"],"abstract_inverted_index":{"While":[0],"current":[1],"approaches":[2],"for":[3,27,35,71,84,92,97],"segmenting":[4],"or":[5],"classifying":[6],"audiovisual":[7,69],"data":[8,70],"are":[9,80],"mostly":[10],"focused":[11],"on":[12],"visual":[13],"information,":[14,89],"audio":[15,42],"information":[16],"may":[17],"also":[18,47,91],"play":[19],"an":[20],"important":[21],"role":[22],"in":[23,62],"the":[24,60,63],"content":[25],"parsing":[26],"many":[28],"applications.":[29],"We":[30,46],"propose":[31],"a":[32,94],"novel":[33],"scheme":[34],"determining":[36],"video":[37,44,72,87],"scenes":[38],"by":[39],"analyzing":[40],"both":[41],"and":[43,56,66,74,78],"data.":[45],"describe":[48],"some":[49,58],"preliminary":[50],"experiments":[51],"that":[52],"we":[53],"have":[54],"performed":[55],"report":[57],"of":[59,68],"results":[61],"automatic":[64],"segmentation":[65,77],"classification":[67,79],"indexing":[73,88],"retrieval.":[75],"Audio":[76],"used":[81],"not":[82],"only":[83],"extracting":[85],"useful":[86],"but":[90],"performing":[93],"preprocessing":[95],"step":[96],"other":[98],"analysis":[99],"modules.":[100]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}