{"id":"https://openalex.org/W1575493074","doi":"https://doi.org/10.1109/icip.2003.1246605","title":"Shot genre classification using compressed audio-visual features","display_name":"Shot genre classification using compressed audio-visual features","publication_year":2004,"publication_date":"2004-06-03","ids":{"openalex":"https://openalex.org/W1575493074","doi":"https://doi.org/10.1109/icip.2003.1246605","mag":"1575493074"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2003.1246605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2003.1246605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429)","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/A5087002063","display_name":"Masaru Sugano","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164495","display_name":"KDDI Research (Japan)","ror":"https://ror.org/05qsqt662","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210164495"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"M. Sugano","raw_affiliation_strings":["KDDI Research and Development Laboratories, Inc., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KDDI Research and Development Laboratories, Inc., Japan","institution_ids":["https://openalex.org/I4210164495"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033105601","display_name":"Roger Isaksson","orcid":null},"institutions":[{"id":"https://openalex.org/I190632392","display_name":"Lule\u00e5 University of Technology","ror":"https://ror.org/016st3p78","country_code":"SE","type":"education","lineage":["https://openalex.org/I190632392"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"R. Isaksson","raw_affiliation_strings":["Lule\u00e5 University of Technology, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lule\u00e5 University of Technology, Sweden","institution_ids":["https://openalex.org/I190632392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057276221","display_name":"Yasuyuki Nakajima","orcid":"https://orcid.org/0000-0002-4584-3621"},"institutions":[{"id":"https://openalex.org/I4210164495","display_name":"KDDI Research (Japan)","ror":"https://ror.org/05qsqt662","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210164495"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Y. Nakajima","raw_affiliation_strings":["KDDI Research and Development Laboratories, Inc., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KDDI Research and Development Laboratories, Inc., Japan","institution_ids":["https://openalex.org/I4210164495"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083165705","display_name":"Hiromasa Yanagihara","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164495","display_name":"KDDI Research (Japan)","ror":"https://ror.org/05qsqt662","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210164495"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"H. Yanagihara","raw_affiliation_strings":["KDDI Research and Development Laboratories, Inc., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KDDI Research and Development Laboratories, Inc., Japan","institution_ids":["https://openalex.org/I4210164495"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1891,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.75630712,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"3","issue":null,"first_page":"II","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9997000098228455,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9965000152587891,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.910099983215332,"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/automatic-summarization","display_name":"Automatic summarization","score":0.8764618635177612},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8417418003082275},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.7425369024276733},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6419376134872437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6377202272415161},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6290740966796875},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5721303820610046},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49820828437805176},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.47078388929367065},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4668707549571991},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42500805854797363},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4147488474845886},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3771725296974182},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3629215955734253},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3625485897064209},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3607008159160614},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2023102045059204}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8764618635177612},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8417418003082275},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.7425369024276733},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6419376134872437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6377202272415161},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6290740966796875},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5721303820610046},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49820828437805176},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.47078388929367065},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4668707549571991},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42500805854797363},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4147488474845886},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3771725296974182},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3629215955734253},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3625485897064209},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3607008159160614},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2023102045059204},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/icip.2003.1246605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2003.1246605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7400000095367432,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W57790744","https://openalex.org/W113000659","https://openalex.org/W1495867762","https://openalex.org/W1563750459","https://openalex.org/W2003889823","https://openalex.org/W2014143576","https://openalex.org/W2098573015","https://openalex.org/W2101251887","https://openalex.org/W2103076542","https://openalex.org/W2105740906","https://openalex.org/W2118724348","https://openalex.org/W2122594606","https://openalex.org/W2123629344","https://openalex.org/W2166248431","https://openalex.org/W2339586291","https://openalex.org/W3178658517","https://openalex.org/W6602360804","https://openalex.org/W6604529437","https://openalex.org/W6677584137","https://openalex.org/W6678407303","https://openalex.org/W6678438650","https://openalex.org/W6684426571","https://openalex.org/W6798670444"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W3148229873","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W2091301346","https://openalex.org/W1517524280","https://openalex.org/W4389760904","https://openalex.org/W4306886878","https://openalex.org/W4323520239"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"shot":[3,39,74,84,114],"genre":[4,46,75,115],"classification":[5,40],"from":[6],"MPEG":[7],"compressed":[8,30],"movies,":[9],"as":[10,58],"one":[11],"of":[12,23,97],"the":[13,32,42,77,98,101,112],"high-level":[14],"indexing":[15],"methods":[16],"for":[17,72],"audio-visual":[18,27],"contents.":[19],"Through":[20],"statistical":[21],"analysis":[22],"low-level":[24],"and":[25,63,110],"mid-level":[26],"features":[28],"on":[29],"domain,":[31],"proposed":[33],"method":[34],"can":[35,49,103,116],"achieve":[36],"subjectively":[37,68,107],"accurate":[38,108],"within":[41],"movies":[43,102],"into":[44,76,106],"predefined":[45],"set,":[47],"which":[48],"be":[50,104],"applied":[51],"to":[52],"various":[53],"content":[54],"handling":[55],"applications,":[56],"such":[57],"summarization,":[59],"navigation,":[60],"editing,":[61],"filtering,":[62],"so":[64],"on.":[65],"By":[66],"feeding":[67],"evaluated":[69],"feature":[70],"set":[71],"each":[73,83,119],"linear":[78],"machine":[79],"decision":[80],"tree":[81],"classifier,":[82],"is":[85],"classified":[86,105],"at":[87],"very":[88],"low":[89],"cost.":[90],"The":[91],"experimental":[92],"results":[93],"show":[94],"that":[95],"most":[96],"shots":[99],"in":[100],"genres,":[109],"also":[111],"dominant":[113],"correctly":[117],"resolve":[118],"movie":[120],"genre.":[121]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
