{"id":"https://openalex.org/W2009616550","doi":"https://doi.org/10.1145/2072298.2072316","title":"Audio-visual grouplet","display_name":"Audio-visual grouplet","publication_year":2011,"publication_date":"2011-11-28","ids":{"openalex":"https://openalex.org/W2009616550","doi":"https://doi.org/10.1145/2072298.2072316","mag":"2009616550"},"language":"en","primary_location":{"id":"doi:10.1145/2072298.2072316","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2072298.2072316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Multimedia","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/A5101417077","display_name":"Wei Jiang","orcid":"https://orcid.org/0009-0007-4595-1060"},"institutions":[{"id":"https://openalex.org/I175669267","display_name":"Carestream (United States)","ror":"https://ror.org/048m16q57","country_code":"US","type":"company","lineage":["https://openalex.org/I175669267"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wei Jiang","raw_affiliation_strings":["Eastman Kodak Company, Rochester, NY, USA","Eastman Kodak Company, Rochester, NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Eastman Kodak Company, Rochester, NY, USA","institution_ids":["https://openalex.org/I175669267"]},{"raw_affiliation_string":"Eastman Kodak Company, Rochester, NY, USA#TAB#","institution_ids":["https://openalex.org/I175669267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051767562","display_name":"Alexander C. Loui","orcid":"https://orcid.org/0000-0002-7427-1503"},"institutions":[{"id":"https://openalex.org/I175669267","display_name":"Carestream (United States)","ror":"https://ror.org/048m16q57","country_code":"US","type":"company","lineage":["https://openalex.org/I175669267"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander C. Loui","raw_affiliation_strings":["Eastman Kodak Company, Rochester, NY, USA","Eastman Kodak Company, Rochester, NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Eastman Kodak Company, Rochester, NY, USA","institution_ids":["https://openalex.org/I175669267"]},{"raw_affiliation_string":"Eastman Kodak Company, Rochester, NY, USA#TAB#","institution_ids":["https://openalex.org/I175669267"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101417077"],"corresponding_institution_ids":["https://openalex.org/I175669267"],"apc_list":null,"apc_paid":null,"fwci":3.8636,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.94564874,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"123","last_page":"132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9975000023841858,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9937999844551086,"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/audio-visual","display_name":"Audio visual","score":0.7915593385696411},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7646385431289673},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6940197944641113},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6179675459861755},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5858288407325745},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.44439780712127686},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41337424516677856},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3831254839897156},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.14372137188911438}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7915593385696411},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7646385431289673},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6940197944641113},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6179675459861755},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5858288407325745},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.44439780712127686},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41337424516677856},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3831254839897156},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.14372137188911438},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2072298.2072316","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2072298.2072316","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1486994328","https://openalex.org/W1965555842","https://openalex.org/W1975723154","https://openalex.org/W1976727013","https://openalex.org/W1986482242","https://openalex.org/W1994424184","https://openalex.org/W1996514462","https://openalex.org/W2002044752","https://openalex.org/W2016067832","https://openalex.org/W2031489346","https://openalex.org/W2036718463","https://openalex.org/W2036931824","https://openalex.org/W2050964073","https://openalex.org/W2062903088","https://openalex.org/W2075727791","https://openalex.org/W2095787854","https://openalex.org/W2101567517","https://openalex.org/W2107466766","https://openalex.org/W2109124605","https://openalex.org/W2111918405","https://openalex.org/W2120945552","https://openalex.org/W2124195644","https://openalex.org/W2125587358","https://openalex.org/W2128017662","https://openalex.org/W2136076704","https://openalex.org/W2137981002","https://openalex.org/W2140647972","https://openalex.org/W2141364309","https://openalex.org/W2142194269","https://openalex.org/W2150040608","https://openalex.org/W2151103935","https://openalex.org/W2154151281","https://openalex.org/W2161763247","https://openalex.org/W2161969291","https://openalex.org/W2163292664","https://openalex.org/W2165874743","https://openalex.org/W2168793898","https://openalex.org/W2171819471","https://openalex.org/W2178225550","https://openalex.org/W2802922942","https://openalex.org/W4285719527","https://openalex.org/W6681876882","https://openalex.org/W6684458083","https://openalex.org/W6684578312"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2110523656","https://openalex.org/W1482209366","https://openalex.org/W2521627374","https://openalex.org/W2981954115"],"abstract_inverted_index":{"We":[0,152],"investigate":[1],"general":[2],"concept":[3,73],"classification":[4],"in":[5,50,106],"unconstrained":[6],"videos":[7],"by":[8,21,118],"joint":[9],"audio-visual":[10,26,56,67,84,122,145],"analysis.":[11],"A":[12],"novel":[13],"representation,":[14],"the":[15,23,60,77,83,125,158,167],"Audio-Visual":[16],"Grouplet":[17],"(AVG),":[18],"is":[19,30,86],"extracted":[20],"studying":[22],"statistical":[24],"temporal":[25,48,121],"interactions.":[27],"An":[28],"AVG":[29],"defined":[31],"as":[32,80],"a":[33],"set":[34],"of":[35,116,138,141],"audio":[36,96,108,132,135],"and":[37,109,112,134,173],"visual":[38,98,110,128,130],"codewords":[39],"that":[40,93,166],"are":[41],"grouped":[42],"together":[43],"according":[44],"to":[45,58],"their":[46],"strong":[47],"correlations":[49,123],"videos.":[51],"The":[52],"AVGs":[53,79,117,142],"carry":[54],"unique":[55],"cues":[57],"represent":[59],"video":[61],"content,":[62],"based":[63],"on":[64],"which":[65],"an":[66],"dictionary":[68,85],"can":[69,170],"be":[70],"constructed":[71],"for":[72,147],"classification.":[74],"By":[75],"using":[76],"entire":[78],"building":[81],"elements,":[82],"much":[87],"more":[88],"robust":[89],"than":[90],"traditional":[91],"vocabularies":[92],"use":[94],"discrete":[95],"or":[97],"codewords.":[99],"Specifically,":[100],"we":[101],"conduct":[102],"coarse-level":[103],"foreground/background":[104],"separation":[105],"both":[107],"channels,":[111],"discover":[113],"four":[114],"types":[115,140],"exploring":[119],"mixed-and-matched":[120],"among":[124],"following":[126],"factors:":[127],"foreground,":[129,133],"background,":[131],"background.":[136],"All":[137],"these":[139],"provide":[143],"discriminative":[144],"patterns":[146],"classifying":[148],"various":[149],"semantic":[150],"concepts.":[151],"extensively":[153],"evaluate":[154],"our":[155],"method":[156],"over":[157],"large-scale":[159],"Columbia":[160],"Consumer":[161],"Video":[162],"set.":[163],"Experiments":[164],"demonstrate":[165],"AVG-based":[168],"dictionaries":[169],"achieve":[171],"consistent":[172],"significant":[174],"performance":[175],"improvements":[176],"compared":[177],"with":[178],"other":[179],"state-of-the-art":[180],"approaches.":[181]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
