{"id":"https://openalex.org/W4388235350","doi":"https://doi.org/10.1145/3617695.3617728","title":"An Attention-based Audio-visual Fusion Method for Short Video Classification","display_name":"An Attention-based Audio-visual Fusion Method for Short Video Classification","publication_year":2023,"publication_date":"2023-08-11","ids":{"openalex":"https://openalex.org/W4388235350","doi":"https://doi.org/10.1145/3617695.3617728"},"language":"en","primary_location":{"id":"doi:10.1145/3617695.3617728","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3617695.3617728","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 7th International Conference on Big Data and Internet of Things","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/A5085760747","display_name":"Hong Liang Dai","orcid":"https://orcid.org/0009-0000-2131-9027"},"institutions":[{"id":"https://openalex.org/I78978612","display_name":"Yangzhou University","ror":"https://ror.org/03tqb8s11","country_code":"CN","type":"education","lineage":["https://openalex.org/I78978612"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hong Liang Dai","raw_affiliation_strings":["Yang Zhou University, China"],"affiliations":[{"raw_affiliation_string":"Yang Zhou University, China","institution_ids":["https://openalex.org/I78978612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108875164","display_name":"Xingfeng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I78978612","display_name":"Yangzhou University","ror":"https://ror.org/03tqb8s11","country_code":"CN","type":"education","lineage":["https://openalex.org/I78978612"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingfeng Zhang","raw_affiliation_strings":["Yang Zhou University, China"],"affiliations":[{"raw_affiliation_string":"Yang Zhou University, China","institution_ids":["https://openalex.org/I78978612"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103065636","display_name":"Haiyang Yu","orcid":"https://orcid.org/0009-0009-0962-2950"},"institutions":[{"id":"https://openalex.org/I78978612","display_name":"Yangzhou University","ror":"https://ror.org/03tqb8s11","country_code":"CN","type":"education","lineage":["https://openalex.org/I78978612"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiyang Yu","raw_affiliation_strings":["Yang Zhou University, China"],"affiliations":[{"raw_affiliation_string":"Yang Zhou University, China","institution_ids":["https://openalex.org/I78978612"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5085760747"],"corresponding_institution_ids":["https://openalex.org/I78978612"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13842894,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"28","last_page":"33"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9986000061035156,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9986000061035156,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9959999918937683,"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":0.9783999919891357,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8464657068252563},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6877137422561646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.620551347732544},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.5148953199386597},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.49811601638793945},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.46870157122612},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.46640506386756897},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4237367510795593},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.39008575677871704},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3866395056247711},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3836144804954529},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.2900383472442627},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.24499595165252686},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.16602420806884766},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.08813810348510742},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.06831058859825134}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8464657068252563},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6877137422561646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.620551347732544},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.5148953199386597},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.49811601638793945},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.46870157122612},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.46640506386756897},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4237367510795593},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.39008575677871704},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3866395056247711},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3836144804954529},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2900383472442627},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.24499595165252686},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.16602420806884766},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.08813810348510742},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.06831058859825134}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3617695.3617728","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1145/3617695.3617728","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 7th International Conference on Big Data and Internet of Things","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":17,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1537553349","https://openalex.org/W1965555842","https://openalex.org/W2347068106","https://openalex.org/W2531894595","https://openalex.org/W2780360157","https://openalex.org/W2789219568","https://openalex.org/W2892242667","https://openalex.org/W2903920459","https://openalex.org/W2962899219","https://openalex.org/W2962934715","https://openalex.org/W2963166524","https://openalex.org/W2963351448","https://openalex.org/W2963524571","https://openalex.org/W2982343573","https://openalex.org/W2990503944","https://openalex.org/W3015606043"],"related_works":["https://openalex.org/W3159882232","https://openalex.org/W1969715806","https://openalex.org/W4241650944","https://openalex.org/W2911173954","https://openalex.org/W2533629408","https://openalex.org/W2754746744","https://openalex.org/W27741130","https://openalex.org/W2064012922","https://openalex.org/W4292261062","https://openalex.org/W1579239598"],"abstract_inverted_index":{"The":[0,115],"short":[1,18,37,78,112,120,142],"multimedia":[2,121],"video":[3,38,79,113,122],"has":[4],"become":[5],"one":[6],"of":[7,90,93,141],"the":[8,13,33,43,52,84,88,91,99,103,111,126,138],"most":[9],"representative":[10],"products":[11],"in":[12],"new":[14],"media":[15],"era.":[16],"Because":[17],"videos":[19],"are":[20,40,108],"highly":[21],"time-sensitive,":[22],"it":[23],"is":[24,61,132],"essential":[25],"to":[26,41,50],"manage":[27],"and":[28,46,95,102,105,134],"classify":[29],"them":[30],"efficiently.":[31],"Currently,":[32],"primary":[34],"approaches":[35],"for":[36,58,77,110],"classification":[39,59,100,139],"extract":[42],"image":[44,94,104],"features":[45],"then":[47],"make":[48],"judgments":[49],"complete":[51],"classification.":[53,80,114],"However,":[54],"audio":[55,96,106],"information,":[56],"crucial":[57],"tasks,":[60],"often":[62],"discarded":[63],"or":[64],"used":[65],"separately.":[66],"To":[67],"this":[68,82],"end,":[69],"we":[70],"propose":[71],"an":[72],"attention-based":[73,128],"audio-visual":[74,129],"fusion":[75,130],"method":[76,131],"In":[81],"method,":[83],"attention":[85],"module":[86],"calculates":[87],"magnitude":[89],"influence":[92],"information":[97,107],"on":[98,118],"result,":[101],"fused":[109],"experimental":[116],"results":[117],"different":[119],"datasets":[123],"demonstrate":[124],"that":[125],"proposed":[127],"effective":[133],"can":[135],"significantly":[136],"improve":[137],"accuracy":[140],"videos.":[143]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}