{"id":"https://openalex.org/W4388115457","doi":"https://doi.org/10.23919/eusipco58844.2023.10289723","title":"Automatic TV Genre Classification Based on Visually-Conditioned Deep Audio Features","display_name":"Automatic TV Genre Classification Based on Visually-Conditioned Deep Audio Features","publication_year":2023,"publication_date":"2023-09-04","ids":{"openalex":"https://openalex.org/W4388115457","doi":"https://doi.org/10.23919/eusipco58844.2023.10289723"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco58844.2023.10289723","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/eusipco58844.2023.10289723","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","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/A5000588289","display_name":"Alessandro Ilic Mezza","orcid":"https://orcid.org/0000-0002-9438-3190"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Ilic Mezza","raw_affiliation_strings":["Politecnico di Milano,Milan,Italy","Politecnico di Milano, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Milan,Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Paolo Sani","orcid":null},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Sani","raw_affiliation_strings":["Politecnico di Milano,Milan,Italy","Politecnico di Milano, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Milan,Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051897828","display_name":"Augusto Sarti","orcid":"https://orcid.org/0000-0002-5803-1702"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Augusto Sarti","raw_affiliation_strings":["Politecnico di Milano,Milan,Italy","Politecnico di Milano, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano,Milan,Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I93860229"],"apc_list":null,"apc_paid":null,"fwci":0.4833,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61269916,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"166","last_page":"170"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9965000152587891,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9814000129699707,"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":0.7401021122932434},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5393393635749817},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5027096271514893},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45409080386161804},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4153774678707123},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3519424796104431},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.23313656449317932},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.14040791988372803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7401021122932434},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5393393635749817},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5027096271514893},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45409080386161804},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4153774678707123},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3519424796104431},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.23313656449317932},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.14040791988372803}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/eusipco58844.2023.10289723","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/eusipco58844.2023.10289723","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:re.public.polimi.it:11311/1261010","is_oa":false,"landing_page_url":"https://hdl.handle.net/11311/1261010","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1597283066","https://openalex.org/W1989085630","https://openalex.org/W2016902084","https://openalex.org/W2032894676","https://openalex.org/W2051580196","https://openalex.org/W2077395415","https://openalex.org/W2145871814","https://openalex.org/W2258198666","https://openalex.org/W2274583232","https://openalex.org/W2288371874","https://openalex.org/W2330820318","https://openalex.org/W2593116425","https://openalex.org/W2619697695","https://openalex.org/W2939574508","https://openalex.org/W2944621473","https://openalex.org/W2955425717","https://openalex.org/W2963115079","https://openalex.org/W2963230557","https://openalex.org/W3094550259","https://openalex.org/W3105315310","https://openalex.org/W4248034423","https://openalex.org/W6694369573","https://openalex.org/W6762718338"],"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/W2393726419"],"abstract_inverted_index":{"Reliable":[0],"tools":[1],"for":[2,14,35],"automatic":[3],"genre":[4,60],"classification":[5],"(AGC)":[6],"are":[7,32],"highly":[8],"sought-after":[9],"by":[10],"the":[11,15,19,24,65,112,122],"television":[12],"industry":[13],"promise":[16],"of":[17,21,27,38,67,71,89],"saving":[18],"cost":[20],"manually":[22,86],"annotating":[23],"ever-growing":[25],"catalogs":[26],"media":[28],"content":[29],"providers.":[30],"Metadata":[31],"indeed":[33],"vital":[34],"a":[36,53,85,100],"variety":[37],"tasks,":[39],"including":[40],"data":[41],"analytics,":[42],"database":[43],"navigation,":[44],"and":[45,78,116],"recommender":[46],"systems.":[47],"In":[48],"recent":[49,132],"years,":[50],"however,":[51],"only":[52],"few":[54],"works":[55],"have":[56],"focused":[57],"on":[58,94,105,111,120],"TV":[59,91],"classification,":[61],"possibly":[62],"due":[63],"to":[64,127],"lack":[66],"publicly":[68],"available":[69],"datasets":[70],"broadcast":[72],"media.":[73],"To":[74],"bridge":[75],"this":[76],"gap":[77],"foster":[79],"future":[80],"research,":[81],"we":[82,98],"present":[83],"ITTV,":[84,121],"annotated":[87],"dataset":[88],"Italian":[90],"programs":[92],"gathered":[93],"YouTube.":[95],"From":[96],"this,":[97],"propose":[99],"novel":[101],"AGC":[102,134],"method":[103,124],"based":[104],"deep":[106],"audio":[107],"features":[108],"that":[109],"rely":[110],"well-established":[113],"\u201cLook,":[114],"Listen":[115],"Learn\u201d":[117],"paradigm.":[118],"Evaluated":[119],"proposed":[123],"is":[125],"shown":[126],"provide":[128],"state-of-the-art":[129],"results,":[130],"outperforming":[131],"audio-based":[133],"methods.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
