{"id":"https://openalex.org/W1949924346","doi":"https://doi.org/10.1109/mfi.2015.7295798","title":"Multimodal object recognition from visual and audio sequences","display_name":"Multimodal object recognition from visual and audio sequences","publication_year":2015,"publication_date":"2015-09-01","ids":{"openalex":"https://openalex.org/W1949924346","doi":"https://doi.org/10.1109/mfi.2015.7295798","mag":"1949924346"},"language":"en","primary_location":{"id":"doi:10.1109/mfi.2015.7295798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mfi.2015.7295798","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)","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/A5103162780","display_name":"Weipeng He","orcid":"https://orcid.org/0000-0002-3874-3083"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Weipeng He","raw_affiliation_strings":["TAMS, University of Hamburg, Germany","TAMS, Department of Informatics, University of Hamburg, Vogt-K\u00f6lln-Str. 30, 22527 Germany"],"affiliations":[{"raw_affiliation_string":"TAMS, University of Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]},{"raw_affiliation_string":"TAMS, Department of Informatics, University of Hamburg, Vogt-K\u00f6lln-Str. 30, 22527 Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013710926","display_name":"Haojun Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Haojun Guan","raw_affiliation_strings":["TAMS, University of Hamburg, Germany","TAMS, Department of Informatics, University of Hamburg, Vogt-K\u00f6lln-Str. 30, 22527 Germany"],"affiliations":[{"raw_affiliation_string":"TAMS, University of Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]},{"raw_affiliation_string":"TAMS, Department of Informatics, University of Hamburg, Vogt-K\u00f6lln-Str. 30, 22527 Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100326970","display_name":"Jianwei Zhang","orcid":"https://orcid.org/0000-0002-7856-5760"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jianwei Zhang","raw_affiliation_strings":["TAMS, University of Hamburg, Germany","TAMS, Department of Informatics, University of Hamburg, Vogt-K\u00f6lln-Str. 30, 22527 Germany"],"affiliations":[{"raw_affiliation_string":"TAMS, University of Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]},{"raw_affiliation_string":"TAMS, Department of Informatics, University of Hamburg, Vogt-K\u00f6lln-Str. 30, 22527 Germany","institution_ids":["https://openalex.org/I159176309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103162780"],"corresponding_institution_ids":["https://openalex.org/I159176309"],"apc_list":null,"apc_paid":null,"fwci":0.5744,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.66021455,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"133","last_page":"138"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9821000099182129,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.7628703117370605},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.752076268196106},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.732551097869873},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6672126650810242},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5697427988052368},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.529975414276123},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5070829391479492},{"id":"https://openalex.org/keywords/conditional-independence","display_name":"Conditional independence","score":0.46818530559539795},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.45999017357826233},{"id":"https://openalex.org/keywords/joint-probability-distribution","display_name":"Joint probability distribution","score":0.4492255747318268},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.44774019718170166},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4471222162246704},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4335968494415283},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.43049943447113037},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15759626030921936},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09588748216629028}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7628703117370605},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.752076268196106},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.732551097869873},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6672126650810242},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5697427988052368},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.529975414276123},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5070829391479492},{"id":"https://openalex.org/C79772020","wikidata":"https://www.wikidata.org/wiki/Q5159264","display_name":"Conditional independence","level":2,"score":0.46818530559539795},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45999017357826233},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.4492255747318268},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.44774019718170166},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4471222162246704},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4335968494415283},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.43049943447113037},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15759626030921936},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09588748216629028},{"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/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mfi.2015.7295798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mfi.2015.7295798","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.75,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1560013842","https://openalex.org/W1625255723","https://openalex.org/W2053101950","https://openalex.org/W2070338807","https://openalex.org/W2111252376","https://openalex.org/W2113897020","https://openalex.org/W2116702966","https://openalex.org/W2125838338","https://openalex.org/W2135632505","https://openalex.org/W2151103935","https://openalex.org/W2163929346","https://openalex.org/W2168392347","https://openalex.org/W2171706135","https://openalex.org/W6636494156","https://openalex.org/W6684936967"],"related_works":["https://openalex.org/W2349769824","https://openalex.org/W2271369634","https://openalex.org/W2914532148","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W1995680679","https://openalex.org/W4306317269","https://openalex.org/W4291632780","https://openalex.org/W2964200874","https://openalex.org/W4244332233"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,72,101],"visual-audio":[4],"object":[5],"recognition":[6],"system":[7,13],"using":[8],"hidden":[9,51],"Markov":[10,52],"models.":[11,53],"The":[12,37,68,125],"uses":[14],"the":[15,25,29,34,44,47,61,80,94,113],"bag-of-words":[16],"model":[17],"with":[18,49,76],"scale":[19],"invariant":[20],"feature":[21,27,63],"transform":[22],"descriptors":[23],"as":[24,33,120,122],"visual":[26],"and":[28,65,90],"mel-frequency":[30],"cepstrum":[31],"coefficients":[32],"audio":[35],"feature.":[36],"classification":[38],"of":[39,46,103,115],"objects":[40,107],"is":[41],"based":[42,99],"on":[43,100],"computation":[45],"probabilities":[48],"learned":[50],"Two":[54],"different":[55,105],"fusion":[56,64,118,130],"methods":[57,119,131,138],"are":[58,108,139],"used":[59],"in":[60],"system:":[62],"decision":[66],"fusion.":[67],"former":[69],"method":[70,82],"learns":[71,83],"joint":[73],"probability":[74],"distribution":[75],"one":[77],"HMM,":[78],"while":[79,135],"latter":[81],"two":[84,117,137],"separate":[85],"distributions":[86],"for":[87],"each":[88],"modality":[89],"combines":[91],"them":[92],"under":[93],"conditional":[95],"independence":[96],"assumption.":[97],"Experiments":[98],"dataset":[102],"33":[104],"household":[106],"carried":[109],"out":[110],"to":[111],"evaluate":[112],"performance":[114],"these":[116,136],"well":[121],"unimodal":[123,133],"approaches.":[124],"result":[126],"shows":[127],"that":[128],"both":[129],"outperform":[132],"methods,":[134],"mostly":[140],"comparable.":[141]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}