{"id":"https://openalex.org/W2128594317","doi":"https://doi.org/10.1109/icip.2004.1421580","title":"Discovering meaningful multimedia patterns with audio-visual concepts and associated text","display_name":"Discovering meaningful multimedia patterns with audio-visual concepts and associated text","publication_year":2005,"publication_date":"2005-04-19","ids":{"openalex":"https://openalex.org/W2128594317","doi":"https://doi.org/10.1109/icip.2004.1421580","mag":"2128594317"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2004.1421580","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2004.1421580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 International Conference on Image Processing, 2004. ICIP '04.","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/A5049449495","display_name":"Lexing Xie","orcid":"https://orcid.org/0000-0001-8319-0118"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"L. Xie","raw_affiliation_strings":["Department of Electrical Engineering, Columbia University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064407363","display_name":"Leda Kennedy","orcid":"https://orcid.org/0000-0003-2976-9588"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"L. Kennedy","raw_affiliation_strings":["Department of Electrical Engineering, Columbia University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037340457","display_name":"Shih\u2010Fu Chang","orcid":"https://orcid.org/0000-0003-1444-1205"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S.-F. Chang","raw_affiliation_strings":["Department of Electrical Engineering, Columbia University, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097204452","display_name":"A. Divakarun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"A. Divakarun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058002649","display_name":"Hao Sun","orcid":"https://orcid.org/0000-0001-8094-1991"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H. Sun","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories, Inc., Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Inc., Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110978175","display_name":"C.-Y. Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C.-Y. Lin","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Hawthorne, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Hawthorne, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5049449495"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":4.8639,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.95610051,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"4","issue":null,"first_page":"2383","last_page":"2386"},"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":0.9988999962806702,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9879999756813049,"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":0.8391305804252625},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7356444597244263},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5666935443878174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5641632080078125},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5220277905464172},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.48191359639167786},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.45309996604919434},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4520159363746643},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.4486638307571411},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4413675367832184},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35656195878982544},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08327066898345947}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8391305804252625},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7356444597244263},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5666935443878174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5641632080078125},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5220277905464172},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.48191359639167786},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.45309996604919434},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4520159363746643},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.4486638307571411},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4413675367832184},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35656195878982544},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08327066898345947},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icip.2004.1421580","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2004.1421580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 International Conference on Image Processing, 2004. ICIP '04.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.72.6123","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.72.6123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ee.columbia.edu/~xlx/research/pub/icip04.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W91927884","https://openalex.org/W182831726","https://openalex.org/W1597739853","https://openalex.org/W1666447063","https://openalex.org/W1841959837","https://openalex.org/W2006969979","https://openalex.org/W2120805321","https://openalex.org/W6603774737","https://openalex.org/W6637249095","https://openalex.org/W6652311901"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2097963413","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W3145575561","https://openalex.org/W2995886640","https://openalex.org/W1591475660","https://openalex.org/W2001275470","https://openalex.org/W2164162849"],"abstract_inverted_index":{"The":[0,37,76],"work":[1],"presents":[2],"the":[3,9,54,56,60,63,70,74,117],"first":[4],"effort":[5],"to":[6,52,124],"automatically":[7],"annotate":[8],"semantic":[10,32],"meanings":[11,64],"of":[12,69,73,99],"temporal":[13,119],"video":[14,40,103],"patterns":[15,30,38,104],"obtained":[16,80,92],"through":[17,93],"unsupervised":[18],"discovery":[19],"processes.":[20],"This":[21],"problem":[22],"is":[23,79],"interesting":[24],"in":[25,39,67],"domains":[26],"where":[27],"neither":[28],"perceptual":[29],"nor":[31],"concepts":[33],"have":[34],"simple":[35],"structures.":[36],"are":[41,65,91,115],"modeled":[42],"with":[43,49,107],"hierarchical":[44],"hidden":[45],"Markov":[46],"models":[47],"(HHMM),":[48],"efficient":[50],"algorithms":[51],"learn":[53],"parameters,":[55],"model":[57,121],"complexity":[58],"and":[59,84,113],"relevant":[61],"features;":[62],"contained":[66],"words":[68],"speech":[71],"transcript":[72],"video.":[75],"pattern-word":[77],"association":[78],"via":[81],"cooccurrence":[82],"analysis":[83],"statistical":[85],"machine":[86],"translation":[87],"models.":[88],"Promising":[89],"results":[90],"extensive":[94],"experiments":[95],"on":[96],"20+":[97],"hours":[98],"TRECVID":[100],"news":[101],"videos:":[102],"that":[105],"associate":[106],"distinct":[108],"topics":[109],"such":[110],"as":[111],"el-nino":[112],"politics":[114],"identified;":[116],"HHMM":[118],"structure":[120],"compares":[122],"favorably":[123],"a":[125],"nontemporal":[126],"clustering":[127],"algorithm.":[128]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
