{"id":"https://openalex.org/W1998139235","doi":"https://doi.org/10.1145/2072298.2072059","title":"Audio-visual fusion using bayesian model combination for web video retrieval","display_name":"Audio-visual fusion using bayesian model combination for web video retrieval","publication_year":2011,"publication_date":"2011-11-28","ids":{"openalex":"https://openalex.org/W1998139235","doi":"https://doi.org/10.1145/2072298.2072059","mag":"1998139235"},"language":"en","primary_location":{"id":"doi:10.1145/2072298.2072059","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2072298.2072059","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":"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/A5109988007","display_name":"Vasant Manohar","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":"Vasant Manohar","raw_affiliation_strings":["Raytheon BBN Technologies, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Raytheon BBN Technologies, Cambridge, MA, USA","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":"Stavros Tsakalidis","raw_affiliation_strings":["Raytheon BBN Technologies, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Raytheon BBN Technologies, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102227196","display_name":"Pradeep Natarajan","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":"Pradeep Natarajan","raw_affiliation_strings":["Raytheon BBN Technologies, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Raytheon BBN Technologies, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107484450","display_name":"Rohit Prasad","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":"Rohit Prasad","raw_affiliation_strings":["Raytheon BBN Technologies, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Raytheon BBN Technologies, Cambridge, MA, USA","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":"Prem Natarajan","raw_affiliation_strings":["Raytheon BBN Technologies, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Raytheon BBN Technologies, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1306686416"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1537","last_page":"1540"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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":0.9988999962806702,"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":0.996999979019165,"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":0.9926000237464905,"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":0.8574031591415405},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7189205884933472},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6633917093276978},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5702731609344482},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5359939336776733},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5132160186767578},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4953211843967438},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4275680482387543},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.41108500957489014},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3598528206348419},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.15059301257133484},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.10293439030647278},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.07356268167495728}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8574031591415405},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7189205884933472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6633917093276978},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5702731609344482},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5359939336776733},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5132160186767578},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4953211843967438},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4275680482387543},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.41108500957489014},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3598528206348419},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.15059301257133484},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.10293439030647278},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.07356268167495728},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2072298.2072059","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2072298.2072059","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W308497914","https://openalex.org/W1625255723","https://openalex.org/W1989085630","https://openalex.org/W2002182716","https://openalex.org/W2006830243","https://openalex.org/W2025954386","https://openalex.org/W2036931824","https://openalex.org/W2090042335","https://openalex.org/W2099501835","https://openalex.org/W2103556603","https://openalex.org/W2107034620","https://openalex.org/W2110856735","https://openalex.org/W2113641473","https://openalex.org/W2119605622","https://openalex.org/W2136076704","https://openalex.org/W2151103935","https://openalex.org/W2165846633","https://openalex.org/W2543932557","https://openalex.org/W4232262564","https://openalex.org/W6636494156"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731","https://openalex.org/W2103924733"],"abstract_inverted_index":{"Combining":[0],"features":[1,90],"from":[2],"multiple,":[3,52],"heterogeneous,":[4],"audio":[5,24,68],"visual":[6,34,70],"sources":[7],"can":[8],"significantly":[9],"improve":[10],"retrieval":[11],"performance":[12],"in":[13,43],"consumer":[14],"domain":[15],"videos.":[16],"However,":[17],"such":[18],"videos":[19],"often":[20],"contain":[21],"unrelated":[22],"overlaid":[23],"content,":[25],"or":[26],"have":[27],"significant":[28],"camera":[29],"motion":[30],"to":[31],"reliably":[32],"extract":[33],"features.":[35],"We":[36,61],"present":[37],"an":[38],"approach,":[39],"which":[40],"overcomes":[41],"errors":[42],"individual":[44,89],"feature":[45,54],"streams":[46,55],"by":[47,65,91],"combining":[48,66],"classifiers":[49],"trained":[50],"on":[51],"heterogeneous":[53],"using":[56],"Bayesian":[57],"model":[58],"combination":[59],"(BAYCOM).":[60],"demonstrate":[62],"our":[63],"method,":[64],"low-level":[67],"and":[69,99],"features,":[71],"for":[72],"classification":[73],"of":[74,87],"a":[75],"large":[76],"200":[77],"hour":[78],"web":[79],"video":[80],"corpus.":[81],"The":[82],"combined":[83],"models":[84],"outperform":[85],"any":[86],"the":[88],"10%.":[92],"Further,":[93],"BAYCOM":[94],"consistently":[95],"outperforms":[96],"traditional":[97],"early":[98],"late":[100],"fusion":[101],"methods.":[102]},"counts_by_year":[{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
