{"id":"https://openalex.org/W2724483756","doi":"https://doi.org/10.1109/siu.2017.7960723","title":"Multimodal video concept classification based on convolutional neural network and audio feature combination","display_name":"Multimodal video concept classification based on convolutional neural network and audio feature combination","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2724483756","doi":"https://doi.org/10.1109/siu.2017.7960723","mag":"2724483756"},"language":"en","primary_location":{"id":"doi:10.1109/siu.2017.7960723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/siu.2017.7960723","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 25th Signal Processing and Communications Applications Conference (SIU)","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/A5010753871","display_name":"Berkay Selbes","orcid":"https://orcid.org/0000-0002-6942-6160"},"institutions":[{"id":"https://openalex.org/I188740104","display_name":"Ba\u015fkent University","ror":"https://ror.org/02v9bqx10","country_code":"TR","type":"education","lineage":["https://openalex.org/I188740104"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Berkay Selbes","raw_affiliation_strings":["Bilgisayar M\u00fchendisli\u011fi, Ba\u015fkent \u00dcniversitesi, Ankara, T\u00fcrkiye"],"affiliations":[{"raw_affiliation_string":"Bilgisayar M\u00fchendisli\u011fi, Ba\u015fkent \u00dcniversitesi, Ankara, T\u00fcrkiye","institution_ids":["https://openalex.org/I188740104"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034079324","display_name":"Mustafa Sert","orcid":"https://orcid.org/0000-0002-7056-4245"},"institutions":[{"id":"https://openalex.org/I188740104","display_name":"Ba\u015fkent University","ror":"https://ror.org/02v9bqx10","country_code":"TR","type":"education","lineage":["https://openalex.org/I188740104"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Mustafa Sert","raw_affiliation_strings":["Bilgisayar M\u00fchendisli\u011fi, Ba\u015fkent \u00dcniversitesi, Ankara, T\u00fcrkiye"],"affiliations":[{"raw_affiliation_string":"Bilgisayar M\u00fchendisli\u011fi, Ba\u015fkent \u00dcniversitesi, Ankara, T\u00fcrkiye","institution_ids":["https://openalex.org/I188740104"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5010753871"],"corresponding_institution_ids":["https://openalex.org/I188740104"],"apc_list":null,"apc_paid":null,"fwci":0.1849,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.43614159,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"63","issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9990000128746033,"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":0.9973000288009644,"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":0.8308435678482056},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8308244347572327},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.692028284072876},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6544880867004395},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6235948801040649},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5710654854774475},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5668392181396484},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.5579102039337158},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5478047728538513},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5084154009819031},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4956115484237671},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4615016579627991},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.15597614645957947}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8308435678482056},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8308244347572327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.692028284072876},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6544880867004395},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6235948801040649},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5710654854774475},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5668392181396484},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.5579102039337158},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5478047728538513},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5084154009819031},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4956115484237671},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4615016579627991},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.15597614645957947},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/siu.2017.7960723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/siu.2017.7960723","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 25th Signal Processing and Communications Applications Conference (SIU)","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":14,"referenced_works":["https://openalex.org/W240069591","https://openalex.org/W1606296463","https://openalex.org/W2021167307","https://openalex.org/W2097117768","https://openalex.org/W2101234009","https://openalex.org/W2151103935","https://openalex.org/W2155893237","https://openalex.org/W2161969291","https://openalex.org/W2163605009","https://openalex.org/W2559423697","https://openalex.org/W2609599638","https://openalex.org/W4252911702","https://openalex.org/W6609060481","https://openalex.org/W6684191040"],"related_works":["https://openalex.org/W2888091758","https://openalex.org/W2134209752","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W2144773493","https://openalex.org/W1971646133","https://openalex.org/W2555630001"],"abstract_inverted_index":{"Video":[0],"concept":[1],"classification":[2,27,138],"is":[3],"a":[4,24],"very":[5],"important":[6],"task":[7],"for":[8,112],"several":[9],"applications":[10],"such":[11],"as":[12],"content":[13],"based":[14,29],"video":[15,26,62,109],"indexing":[16],"and":[17,48,57,65,87,115],"searching.":[18],"In":[19,37],"this":[20],"study,":[21],"we":[22,41],"propose":[23],"multi-modal":[25,116],"method":[28,105],"on":[30,106],"the":[31,38,55,61,71,84,100,107,127,132,137],"feature-level":[32],"fusion":[33,79],"of":[34,60,70,80,102,126],"audio-visual":[35],"signals.":[36],"proposed":[39,104],"method,":[40],"extract":[42],"Mel":[43],"Frequency":[44],"Cepstral":[45],"Coefficient":[46],"(MFCC)":[47],"convolutional":[49],"neural":[50],"network":[51],"(CNN)":[52],"features":[53,135],"from":[54],"audio":[56,128],"visual":[58],"parts":[59],"signal,":[63],"respectively":[64],"calculate":[66],"three":[67],"statistical":[68],"representations":[69],"MFCC":[72],"feature":[73,77],"vectors.":[74],"We":[75,98],"perform":[76],"level":[78],"both":[81,113],"modalities":[82],"using":[83,94],"concatenation":[85],"operator":[86],"train":[88],"Support":[89],"Vector":[90],"Machine":[91],"(SVM)":[92],"classifiers":[93],"these":[95],"multimodal":[96],"features.":[97],"evaluate":[99],"effectiveness":[101],"our":[103],"TRECVID":[108],"performance":[110],"dataset":[111],"single-":[114],"cases.":[117],"Our":[118],"results":[119],"show":[120],"that,":[121],"fusing":[122],"standard":[123],"deviation":[124],"representation":[125],"modality":[129],"along":[130],"with":[131],"GoogleNet":[133],"CNN":[134],"improves":[136],"accuracy.":[139]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}