{"id":"https://openalex.org/W2141939040","doi":"https://doi.org/10.1109/cvpr.2012.6247814","title":"Multimodal feature fusion for robust event detection in web videos","display_name":"Multimodal feature fusion for robust event detection in web videos","publication_year":2012,"publication_date":"2012-06-01","ids":{"openalex":"https://openalex.org/W2141939040","doi":"https://doi.org/10.1109/cvpr.2012.6247814","mag":"2141939040"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2012.6247814","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2012.6247814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Conference on Computer Vision and Pattern Recognition","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/A5066184920","display_name":"Prem Natarajan","orcid":"https://orcid.org/0000-0002-4386-6651"},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"P. Natarajan","raw_affiliation_strings":["Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA, USA","Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA 02138"],"affiliations":[{"raw_affiliation_string":"Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]},{"raw_affiliation_string":"Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA 02138","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102008932","display_name":"Shuang Wu","orcid":"https://orcid.org/0000-0001-9245-6037"},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuang Wu","raw_affiliation_strings":["Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA, USA","Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA 02138"],"affiliations":[{"raw_affiliation_string":"Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]},{"raw_affiliation_string":"Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA 02138","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069416097","display_name":"Shiv Vitaladevuni","orcid":"https://orcid.org/0000-0003-2709-5145"},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Vitaladevuni","raw_affiliation_strings":["Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA, USA","Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA 02138"],"affiliations":[{"raw_affiliation_string":"Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]},{"raw_affiliation_string":"Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA 02138","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110376025","display_name":"Xiaodan Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaodan Zhuang","raw_affiliation_strings":["Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA, USA","Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA 02138"],"affiliations":[{"raw_affiliation_string":"Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]},{"raw_affiliation_string":"Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA 02138","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073006801","display_name":"Stavros Tsakalidis","orcid":null},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Tsakalidis","raw_affiliation_strings":["Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA, USA","Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA 02138"],"affiliations":[{"raw_affiliation_string":"Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]},{"raw_affiliation_string":"Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA 02138","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046573028","display_name":"Unsang Park","orcid":"https://orcid.org/0000-0001-5539-9520"},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Unsang Park","raw_affiliation_strings":["Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA, USA","Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA 02138"],"affiliations":[{"raw_affiliation_string":"Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]},{"raw_affiliation_string":"Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA 02138","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071123729","display_name":"Ramendra Prasad","orcid":"https://orcid.org/0000-0003-3941-5839"},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R. Prasad","raw_affiliation_strings":["Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA, USA","Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA 02138"],"affiliations":[{"raw_affiliation_string":"Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]},{"raw_affiliation_string":"Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA 02138","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066184920","display_name":"Prem Natarajan","orcid":"https://orcid.org/0000-0002-4386-6651"},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Natarajan","raw_affiliation_strings":["Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA, USA","Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA 02138"],"affiliations":[{"raw_affiliation_string":"Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]},{"raw_affiliation_string":"Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA 02138","institution_ids":["https://openalex.org/I1306686416"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5066184920"],"corresponding_institution_ids":["https://openalex.org/I1306686416"],"apc_list":null,"apc_paid":null,"fwci":21.9388,"has_fulltext":false,"cited_by_count":181,"citation_normalized_percentile":{"value":0.99596734,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1298","last_page":"1305"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9976000189781189,"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":0.8553282022476196},{"id":"https://openalex.org/keywords/multiple-kernel-learning","display_name":"Multiple kernel learning","score":0.6055291295051575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5987269878387451},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5833848714828491},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5749621391296387},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5100160837173462},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.48198384046554565},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.46393540501594543},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44995880126953125},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3699157238006592},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.33147701621055603},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3287280797958374},{"id":"https://openalex.org/keywords/kernel-method","display_name":"Kernel method","score":0.12684154510498047}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8553282022476196},{"id":"https://openalex.org/C2776879701","wikidata":"https://www.wikidata.org/wiki/Q25048660","display_name":"Multiple kernel learning","level":4,"score":0.6055291295051575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5987269878387451},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5833848714828491},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5749621391296387},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5100160837173462},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.48198384046554565},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.46393540501594543},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44995880126953125},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3699157238006592},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.33147701621055603},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3287280797958374},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.12684154510498047},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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":1,"locations":[{"id":"doi:10.1109/cvpr.2012.6247814","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2012.6247814","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306116","display_name":"U.S. Department of the Interior","ror":"https://ror.org/03v0pmy70"},{"id":"https://openalex.org/F4320333452","display_name":"Interior Business Center","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1512098439","https://openalex.org/W1625255723","https://openalex.org/W1677409904","https://openalex.org/W1970252168","https://openalex.org/W1993229407","https://openalex.org/W1994694952","https://openalex.org/W2020163092","https://openalex.org/W2035108077","https://openalex.org/W2036931824","https://openalex.org/W2038219201","https://openalex.org/W2061272711","https://openalex.org/W2090042335","https://openalex.org/W2098162425","https://openalex.org/W2100916003","https://openalex.org/W2105464873","https://openalex.org/W2106833577","https://openalex.org/W2110856735","https://openalex.org/W2112565353","https://openalex.org/W2113641473","https://openalex.org/W2119605622","https://openalex.org/W2120137102","https://openalex.org/W2123460005","https://openalex.org/W2128305246","https://openalex.org/W2142194269","https://openalex.org/W2148154194","https://openalex.org/W2150040608","https://openalex.org/W2150782236","https://openalex.org/W2151103935","https://openalex.org/W2155490028","https://openalex.org/W2160326621","https://openalex.org/W2162762921","https://openalex.org/W2162915993","https://openalex.org/W2168356304","https://openalex.org/W2169177311","https://openalex.org/W2917663306","https://openalex.org/W4243179967","https://openalex.org/W6636494156","https://openalex.org/W6675296101","https://openalex.org/W6678412313","https://openalex.org/W6679174546","https://openalex.org/W6680597956"],"related_works":["https://openalex.org/W2900715739","https://openalex.org/W2289496068","https://openalex.org/W2043864454","https://openalex.org/W2547116720","https://openalex.org/W2188831877","https://openalex.org/W2157356416","https://openalex.org/W3125885229","https://openalex.org/W1483460610","https://openalex.org/W2828181497","https://openalex.org/W4287635664"],"abstract_inverted_index":{"Combining":[0],"multiple":[1,122],"low-level":[2,57],"visual":[3,80],"features":[4,27,58,116],"is":[5],"a":[6,12,53,118,144],"proven":[7],"and":[8,36,51,65,87,99,108,126],"effective":[9],"strategy":[10,120],"for":[11,38,139],"range":[13],"of":[14,42,56,76,148],"computer":[15],"vision":[16],"tasks.":[17],"However,":[18],"limited":[19],"attention":[20],"has":[21],"been":[22],"paid":[23],"to":[24],"combining":[25],"such":[26,33],"with":[28],"information":[29,81,94],"from":[30,83],"other":[31],"modalities,":[32],"as":[34],"audio":[35,64],"videotext,":[37],"large":[39,54,145],"scale":[40],"analysis":[41],"web":[43],"videos.":[44,70],"In":[45],"our":[46,151],"work,":[47],"we":[48,91],"rigorously":[49],"analyze":[50],"combine":[52,113],"set":[55,147],"that":[59],"capture":[60],"appearance,":[61],"color,":[62],"motion,":[63],"audio-visual":[66],"co-occurrence":[67],"patterns":[68],"in":[69,143],"We":[71,112],"also":[72],"evaluate":[73],"the":[74,134,154,158],"utility":[75],"high-level":[77],"(i.e.,":[78],"semantic)":[79],"obtained":[82],"detecting":[84,140],"scene,":[85],"object,":[86],"action":[88],"concepts.":[89],"Further,":[90],"exploit":[92],"multimodal":[93],"by":[95],"analyzing":[96],"available":[97],"spoken":[98],"videotext":[100,109],"content":[101],"using":[102,117],"state-of-the-art":[103],"automatic":[104],"speech":[105],"recognition":[106,110],"(ASR)":[107],"systems.":[111],"these":[114],"diverse":[115],"two-step":[119],"employing":[121],"kernel":[123],"learning":[124],"(MKL)":[125],"late":[127],"score":[128],"level":[129],"fusion":[130],"methods.":[131],"Based":[132],"on":[133],"TRECVID":[135],"MED":[136],"2011":[137],"evaluations":[138],"10":[141],"events":[142],"benchmark":[146],"~45000":[149],"videos,":[150],"system":[152],"showed":[153],"best":[155],"performance":[156],"among":[157],"19":[159],"international":[160],"teams.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":19},{"year":2016,"cited_by_count":25},{"year":2015,"cited_by_count":25},{"year":2014,"cited_by_count":29},{"year":2013,"cited_by_count":24},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}