{"id":"https://openalex.org/W4372259966","doi":"https://doi.org/10.1109/icassp49357.2023.10095502","title":"Hierarchical Transformer for Multi-Label Trailer Genre Classification","display_name":"Hierarchical Transformer for Multi-Label Trailer Genre Classification","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372259966","doi":"https://doi.org/10.1109/icassp49357.2023.10095502"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095502","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095502","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5077576132","display_name":"Zi-Hui Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihui Cai","raw_affiliation_strings":["Wuhan University,Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering","Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080389312","display_name":"Hongwei Ding","orcid":"https://orcid.org/0000-0002-0851-1994"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongwei Ding","raw_affiliation_strings":["Wuhan University,Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering","Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038344032","display_name":"Xuemeng Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuemeng Wu","raw_affiliation_strings":["Wuhan University,Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering","Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102757264","display_name":"Mohan Xu","orcid":"https://orcid.org/0000-0001-5173-2269"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mohan Xu","raw_affiliation_strings":["Wuhan University,Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering","Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041280931","display_name":"Xiaohui Cui","orcid":"https://orcid.org/0000-0001-6079-009X"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohui Cui","raw_affiliation_strings":["Wuhan University,Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering","Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03683298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9979000091552734,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9851999878883362,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7661210894584656},{"id":"https://openalex.org/keywords/trailer","display_name":"Trailer","score":0.7371019721031189},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7208482623100281},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5703673362731934},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.520929753780365},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4717978835105896},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4478040933609009},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4228646457195282},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3541252613067627},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.15702447295188904},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1423906683921814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7661210894584656},{"id":"https://openalex.org/C2779101595","wikidata":"https://www.wikidata.org/wiki/Q7832787","display_name":"Trailer","level":2,"score":0.7371019721031189},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7208482623100281},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5703673362731934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.520929753780365},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4717978835105896},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4478040933609009},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4228646457195282},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3541252613067627},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.15702447295188904},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1423906683921814},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095502","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095502","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324116","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W55768394","https://openalex.org/W2032879722","https://openalex.org/W2076771430","https://openalex.org/W2095705004","https://openalex.org/W2107462874","https://openalex.org/W2194775991","https://openalex.org/W2212050411","https://openalex.org/W2549104515","https://openalex.org/W2583824863","https://openalex.org/W2593116425","https://openalex.org/W2618530766","https://openalex.org/W2620683660","https://openalex.org/W2750406316","https://openalex.org/W2767290858","https://openalex.org/W2899663614","https://openalex.org/W2917266953","https://openalex.org/W2963524571","https://openalex.org/W2963542740","https://openalex.org/W3081277999","https://openalex.org/W3094502228","https://openalex.org/W3138516171","https://openalex.org/W3159393962","https://openalex.org/W3196974791","https://openalex.org/W4214612132","https://openalex.org/W4240980853","https://openalex.org/W4312560592","https://openalex.org/W4312777209","https://openalex.org/W4385245566","https://openalex.org/W6674330103","https://openalex.org/W6739901393","https://openalex.org/W6755977528","https://openalex.org/W6780226713","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2897924318","https://openalex.org/W2138997758"],"abstract_inverted_index":{"Determining":[0],"the":[1,52,85,89,96,101,105,119,124],"genres":[2],"of":[3,59,115],"a":[4,7,44,62,79],"trailer":[5],"is":[6,66,74],"challenging":[8],"multi-label":[9],"classification":[10],"task.":[11],"Previous":[12],"studies":[13],"tend":[14],"to":[15,94,122],"classify":[16],"by":[17,40,76,88],"CNN":[18,36],"or":[19],"RNN.":[20,38],"Recently,":[21],"Transformer":[22,46],"based":[23],"on":[24,136],"attention":[25],"mechanism":[26],"has":[27],"achieved":[28],"better":[29],"results":[30],"in":[31],"many":[32],"research":[33],"fields":[34,111],"than":[35],"and":[37,56,70,99,117],"Inspired":[39],"these,":[41],"we":[42,103],"propose":[43],"Hierarchical":[45],"(HT).":[47],"HT":[48],"can":[49,82],"process":[50],"both":[51],"frame":[53],"sequence":[54],"(HT-F)":[55],"audio":[57,71],"(HT-A)":[58],"trailers.":[60],"Besides,":[61],"feature":[63],"compression":[64],"module":[65],"inserted":[67],"into":[68,112],"HT-F,":[69],"spectrogram":[72],"segment":[73],"processed":[75,87],"HT-A":[77],"as":[78],"whole,":[80],"which":[81],"effectively":[83],"reduce":[84,95],"data":[86],"second":[90],"Transformer.":[91],"In":[92],"order":[93],"training":[97],"cost":[98],"improve":[100],"performance,":[102],"load":[104],"pre-trained":[106],"weights":[107],"from":[108],"other":[109],"related":[110],"some":[113],"parameters":[114],"HT,":[116],"utilize":[118],"limited":[120],"resources":[121],"train":[123],"remaining":[125],"parameters.":[126],"Experiments":[127],"show":[128],"that":[129],"our":[130],"best":[131],"model":[132],"outperforms":[133],"state-of-the-art":[134],"methods":[135],"several":[137],"comprehensive":[138],"metrics.":[139]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}