{"id":"https://openalex.org/W2118072670","doi":"https://doi.org/10.1109/mmsp.2004.1436583","title":"Hierarchical video clustering","display_name":"Hierarchical video clustering","publication_year":2005,"publication_date":"2005-06-07","ids":{"openalex":"https://openalex.org/W2118072670","doi":"https://doi.org/10.1109/mmsp.2004.1436583","mag":"2118072670"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp.2004.1436583","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2004.1436583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE 6th Workshop on Multimedia Signal Processing, 2004.","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/A5072859965","display_name":"Nemanja Petrovi\u0107","orcid":"https://orcid.org/0000-0003-4010-2311"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"N. Petrovic","raw_affiliation_strings":["Beckman Institute, University of Illinois, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beckman Institute, University of Illinois, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108373424","display_name":"Neboj\u0161a Joji\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"N. Jojic","raw_affiliation_strings":["Microsoft Research Limited, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Limited, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101457342","display_name":"Thomas S. Huang","orcid":"https://orcid.org/0000-0001-8474-5859"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"T.S. Huang","raw_affiliation_strings":["Beckman Institute, University of Illinois, Urbana-Champaign, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beckman Institute, University of Illinois, Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7694,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.71235626,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"423","last_page":"426"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9998000264167786,"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":0.9998000264167786,"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":0.994700014591217,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.989799976348877,"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/computer-science","display_name":"Computer science","score":0.8240156769752502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7040596008300781},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6354040503501892},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6109801530838013},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5795512199401855},{"id":"https://openalex.org/keywords/video-compression-picture-types","display_name":"Video compression picture types","score":0.5013914108276367},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.49121659994125366},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.44535520672798157},{"id":"https://openalex.org/keywords/video-post-processing","display_name":"Video post-processing","score":0.432623952627182},{"id":"https://openalex.org/keywords/block-matching-algorithm","display_name":"Block-matching algorithm","score":0.430078387260437},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40032070875167847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8240156769752502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7040596008300781},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6354040503501892},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6109801530838013},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5795512199401855},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.5013914108276367},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.49121659994125366},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.44535520672798157},{"id":"https://openalex.org/C117090137","wikidata":"https://www.wikidata.org/wiki/Q7927977","display_name":"Video post-processing","level":5,"score":0.432623952627182},{"id":"https://openalex.org/C167510206","wikidata":"https://www.wikidata.org/wiki/Q2835824","display_name":"Block-matching algorithm","level":4,"score":0.430078387260437},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40032070875167847},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp.2004.1436583","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2004.1436583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE 6th Workshop on Multimedia Signal Processing, 2004.","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":14,"referenced_works":["https://openalex.org/W1487800598","https://openalex.org/W1502713047","https://openalex.org/W1924584954","https://openalex.org/W2009941680","https://openalex.org/W2111384277","https://openalex.org/W2123073649","https://openalex.org/W2145748431","https://openalex.org/W2148603752","https://openalex.org/W2152239535","https://openalex.org/W2168272426","https://openalex.org/W2395537741","https://openalex.org/W4388323202","https://openalex.org/W6630225184","https://openalex.org/W6711931662"],"related_works":["https://openalex.org/W1574724839","https://openalex.org/W1623638113","https://openalex.org/W2032827369","https://openalex.org/W4221117092","https://openalex.org/W2213155192","https://openalex.org/W2187171999","https://openalex.org/W2140582509","https://openalex.org/W181787362","https://openalex.org/W2782365651","https://openalex.org/W3034776505"],"abstract_inverted_index":{"We":[0,58,92,111],"present":[1],"a":[2,35],"novel":[3],"generative":[4],"model":[5,61],"for":[6,46,89],"video":[7,10,15,22,25,65,75,82,95,109],"that":[8,94],"models":[9],"as":[11],"mixture":[12],"of":[13,54,98,121],"transformed":[14],"scenes.":[16],"The":[17,29],"learning":[18,30],"procedure":[19],"automatically":[20],"clusters":[21],"frames":[23,76],"into":[24,77],"scenes":[26],"and":[27,51,73,86,123],"objects.":[28],"algorithm":[31],"is":[32,44,101],"based":[33],"on":[34],"hierarchical,":[36],"on-line":[37],"EM":[38,56],"algorithm.":[39,57],"Fast":[40],"Fourier":[41],"transform":[42],"(FFT)":[43],"used":[45],"rapid":[47],"computations":[48],"in":[49,108,119],"E":[50],"M":[52],"step":[53],"the":[55,60,105],"use":[59],"to:":[62],"1.":[63],"perform":[64],"clustering":[66],"by":[67,83],"grouping":[68],"similar":[69],"(up":[70],"to":[71,103],"translation":[72,85],"scale)":[74],"clusters;":[78],"2.":[79],"robustly":[80],"stabilize":[81],"inferring":[84],"scale":[87],"intensity":[88],"each":[90],"frame.":[91],"believe":[93],"scene":[96],"modeling":[97],"this":[99,113],"kind":[100],"essential":[102],"bridge":[104],"\"semantic":[106],"gap\"":[107],"understanding.":[110],"illustrate":[112],"with":[114],"several":[115],"excellent":[116],"results,":[117],"both":[118],"terms":[120],"speed":[122],"accuracy.":[124]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}