{"id":"https://openalex.org/W2980492205","doi":"https://doi.org/10.1109/mlsp.2019.8918712","title":"Audio-Visual Fusion And Conditioning With Neural Networks For Event Recognition","display_name":"Audio-Visual Fusion And Conditioning With Neural Networks For Event Recognition","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2980492205","doi":"https://doi.org/10.1109/mlsp.2019.8918712","mag":"2980492205"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp.2019.8918712","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2019.8918712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 29th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://orbi.umons.ac.be/bitstream/20.500.12907/42259/1/Peer-reviewed-paper.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047970141","display_name":"Mathilde Brousmiche","orcid":"https://orcid.org/0000-0001-6044-1236"},"institutions":[{"id":"https://openalex.org/I135117807","display_name":"Universit\u00e9 de Sherbrooke","ror":"https://ror.org/00kybxq39","country_code":"CA","type":"education","lineage":["https://openalex.org/I135117807"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mathilde Brousmiche","raw_affiliation_strings":["Canada NECOTIS Lab, University of Sherbrooke"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Canada NECOTIS Lab, University of Sherbrooke","institution_ids":["https://openalex.org/I135117807"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026332327","display_name":"Jean Rouat","orcid":"https://orcid.org/0000-0002-9306-426X"},"institutions":[{"id":"https://openalex.org/I135117807","display_name":"Universit\u00e9 de Sherbrooke","ror":"https://ror.org/00kybxq39","country_code":"CA","type":"education","lineage":["https://openalex.org/I135117807"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jean Rouat","raw_affiliation_strings":["Canada NECOTIS Lab, University of Sherbrooke"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Canada NECOTIS Lab, University of Sherbrooke","institution_ids":["https://openalex.org/I135117807"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083563222","display_name":"St\u00e9phane Dupont","orcid":"https://orcid.org/0000-0003-3674-6747"},"institutions":[{"id":"https://openalex.org/I130929987","display_name":"University of Mons","ror":"https://ror.org/02qnnz951","country_code":"BE","type":"education","lineage":["https://openalex.org/I130929987"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Stephane Dupont","raw_affiliation_strings":["University of Mons, Belgium Numediart Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Mons, Belgium Numediart Institute","institution_ids":["https://openalex.org/I130929987"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1912,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.37673589,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9962000250816345,"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":0.7632120847702026},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6858606934547424},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6326224207878113},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.618195116519928},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.5494371056556702},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.537163496017456},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5277486443519592},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.46982240676879883},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4543130397796631},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.42364639043807983},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.41035333275794983},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3604382574558258},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.28284090757369995},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.17351698875427246},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.10403895378112793}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7632120847702026},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6858606934547424},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6326224207878113},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.618195116519928},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.5494371056556702},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.537163496017456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5277486443519592},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.46982240676879883},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4543130397796631},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.42364639043807983},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.41035333275794983},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3604382574558258},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.28284090757369995},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.17351698875427246},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.10403895378112793},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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":2,"locations":[{"id":"doi:10.1109/mlsp.2019.8918712","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2019.8918712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 29th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:orbi.umons.ac.be:20.500.12907/42259","is_oa":true,"landing_page_url":"https://orbi.umons.ac.be/handle/20.500.12907/42259","pdf_url":"https://orbi.umons.ac.be/bitstream/20.500.12907/42259/1/Peer-reviewed-paper.pdf","source":{"id":"https://openalex.org/S7407055454","display_name":"ORBi UMONS","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Workshop on Machine Learning for Signal Processing (2019-10-13); International Workshop on Machine Learning for Signal Processing, Pittsburgh, United States [US], 2019","raw_type":"http://purl.org/coar/resource_type/c_5794"}],"best_oa_location":{"id":"pmh:oai:orbi.umons.ac.be:20.500.12907/42259","is_oa":true,"landing_page_url":"https://orbi.umons.ac.be/handle/20.500.12907/42259","pdf_url":"https://orbi.umons.ac.be/bitstream/20.500.12907/42259/1/Peer-reviewed-paper.pdf","source":{"id":"https://openalex.org/S7407055454","display_name":"ORBi UMONS","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Workshop on Machine Learning for Signal Processing (2019-10-13); International Workshop on Machine Learning for Signal Processing, Pittsburgh, United States [US], 2019","raw_type":"http://purl.org/coar/resource_type/c_5794"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2980492205.pdf"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1849277567","https://openalex.org/W1947481528","https://openalex.org/W1963753144","https://openalex.org/W1989085630","https://openalex.org/W2040510368","https://openalex.org/W2053101950","https://openalex.org/W2104657103","https://openalex.org/W2156303437","https://openalex.org/W2187089797","https://openalex.org/W2403757143","https://openalex.org/W2592463526","https://openalex.org/W2603777577","https://openalex.org/W2619947201","https://openalex.org/W2727849499","https://openalex.org/W2760103357","https://openalex.org/W2789221157","https://openalex.org/W2883430806","https://openalex.org/W2889624961","https://openalex.org/W2890952074","https://openalex.org/W2916297551","https://openalex.org/W2922915988","https://openalex.org/W2951138147","https://openalex.org/W2953092061","https://openalex.org/W2962910554","https://openalex.org/W2963066927","https://openalex.org/W2963446712","https://openalex.org/W2963596039","https://openalex.org/W2964109005","https://openalex.org/W2977965380","https://openalex.org/W3102469722","https://openalex.org/W3119339177","https://openalex.org/W6639204139","https://openalex.org/W6682864246","https://openalex.org/W6754392867","https://openalex.org/W6755865608","https://openalex.org/W6760334868","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W2373577936","https://openalex.org/W4221148444","https://openalex.org/W4387678054","https://openalex.org/W2953234277","https://openalex.org/W2389596151","https://openalex.org/W3095575180","https://openalex.org/W2626256601","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W4306784355"],"abstract_inverted_index":{"Video":[0],"event":[1,19,108],"recognition":[2,20,50],"based":[3,126],"on":[4,17,22,127],"audio":[5,38,79,94],"and":[6,26,78],"visual":[7,24,77,101],"modalities":[8],"is":[9,96,111],"an":[10],"open":[11],"research":[12],"problem.":[13],"The":[14],"mainstream":[15],"literature":[16],"video":[18,53],"focuses":[21],"the":[23,32,37,48,89,93,100,118,134,137],"modality":[25,95,129,139],"does":[27],"not":[28],"take":[29],"into":[30],"account":[31],"relevant":[33],"information":[34,90],"present":[35,91],"in":[36,92],"modality.":[39],"We":[40,55,104],"propose":[41,72],"to":[42,73,98],"study":[43],"several":[44],"fusion":[45,59,119],"architectures":[46,60],"for":[47],"audio-visual":[49],"task":[51],"of":[52,136],"events.":[54],"first":[56],"build":[57],"classical":[58],"using":[61],"concatenation,":[62],"addition":[63],"or":[64,120],"Multimodal":[65],"Compact":[66],"Bilinear":[67],"pooling":[68],"(MCB).":[69],"Then,":[70],"we":[71,132],"create":[74],"connections":[75],"between":[76],"processing":[80],"with":[81],"Feature-Wise":[82],"Linear":[83],"Modulation":[84],"(FiLM)":[85],"layers.":[86,142],"For":[87],"instance,":[88],"exploited":[97],"change":[99],"classification":[102,109],"behaviour.":[103],"found":[105],"that":[106],"multimodal":[107],"performance":[110],"always":[112],"better":[113],"than":[114],"unimodal":[115],"performance,":[116],"whatever":[117],"conditioning":[121],"method":[122],"used.":[123],"Classification":[124],"accuracy":[125],"one":[128],"improves":[130],"when":[131],"add":[133],"modulation":[135],"other":[138],"through":[140],"FiLM":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}