{"id":"https://openalex.org/W3093096945","doi":"https://doi.org/10.1145/3422852.3423486","title":"Intra and Inter-modality Interactions for Audio-visual Event Detection","display_name":"Intra and Inter-modality Interactions for Audio-visual Event Detection","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3093096945","doi":"https://doi.org/10.1145/3422852.3423486","mag":"3093096945"},"language":"en","primary_location":{"id":"doi:10.1145/3422852.3423486","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3422852.3423486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Human-centric Multimedia Analysis","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/A5047970141","display_name":"Mathilde Brousmiche","orcid":"https://orcid.org/0000-0001-6044-1236"},"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":"Mathilde Brousmiche","raw_affiliation_strings":["University of Mons, Mons, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Mons, Mons, Belgium","institution_ids":["https://openalex.org/I130929987"]}]},{"author_position":"middle","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":"St\u00e9phane Dupont","raw_affiliation_strings":["University of Mons, Mons, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Mons, Mons, Belgium","institution_ids":["https://openalex.org/I130929987"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026531886","display_name":"Jean Rout","orcid":null},"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 Rout","raw_affiliation_strings":["University of Sherbrooke, Sherbrooke, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sherbrooke, Sherbrooke, Canada","institution_ids":["https://openalex.org/I135117807"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1643,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.34961556,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"5","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9973999857902527,"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":0.9939000010490417,"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":0.848074197769165},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7368274331092834},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7203481197357178},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.7066755294799805},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6350107192993164},{"id":"https://openalex.org/keywords/stimulus-modality","display_name":"Stimulus modality","score":0.4957042932510376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48155835270881653},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.46889036893844604},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42853349447250366},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.41256874799728394},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3772531747817993},{"id":"https://openalex.org/keywords/sensory-system","display_name":"Sensory system","score":0.3225443363189697},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.09005081653594971},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.08903706073760986}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.848074197769165},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7368274331092834},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7203481197357178},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7066755294799805},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6350107192993164},{"id":"https://openalex.org/C26486553","wikidata":"https://www.wikidata.org/wiki/Q371870","display_name":"Stimulus modality","level":3,"score":0.4957042932510376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48155835270881653},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.46889036893844604},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42853349447250366},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.41256874799728394},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3772531747817993},{"id":"https://openalex.org/C94487597","wikidata":"https://www.wikidata.org/wiki/Q11101","display_name":"Sensory system","level":2,"score":0.3225443363189697},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.09005081653594971},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.08903706073760986},{"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"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/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3422852.3423486","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3422852.3423486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st International Workshop on Human-centric Multimedia Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:orbi.umons.ac.be:20.500.12907/42336","is_oa":false,"landing_page_url":"https://orbi.umons.ac.be/handle/20.500.12907/42336","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM International Conference on Multimedia (2020-10-12); ACM International Conference on Multimedia, Seattle, United States - Washington [US-WA], 2020","raw_type":"http://purl.org/coar/resource_type/c_5794"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W142803501","https://openalex.org/W398859631","https://openalex.org/W1938425378","https://openalex.org/W2064675550","https://openalex.org/W2105582566","https://openalex.org/W2147704751","https://openalex.org/W2164899449","https://openalex.org/W2314395941","https://openalex.org/W2511428026","https://openalex.org/W2526050071","https://openalex.org/W2592463526","https://openalex.org/W2593116425","https://openalex.org/W2619697695","https://openalex.org/W2789221157","https://openalex.org/W2931433835","https://openalex.org/W2935690855","https://openalex.org/W2951527505","https://openalex.org/W2962899219","https://openalex.org/W2963246338","https://openalex.org/W2963446712","https://openalex.org/W2963524571","https://openalex.org/W2964109005","https://openalex.org/W2971680695","https://openalex.org/W2981372722","https://openalex.org/W2990113535","https://openalex.org/W2997909293","https://openalex.org/W3015925607","https://openalex.org/W3045969489","https://openalex.org/W3103807960"],"related_works":["https://openalex.org/W1540085252","https://openalex.org/W2006830765","https://openalex.org/W2593242293","https://openalex.org/W2051102306","https://openalex.org/W2006955852","https://openalex.org/W2155838649","https://openalex.org/W2063505906","https://openalex.org/W2127201435","https://openalex.org/W2153897251","https://openalex.org/W2143811757"],"abstract_inverted_index":{"The":[0,53],"presence":[1],"of":[2,16,33,49],"auditory":[3],"and":[4,21,39,63,75],"visual":[5,22],"sensory":[6],"streams":[7],"enables":[8],"human":[9],"beings":[10],"to":[11,26,56],"obtain":[12],"a":[13,17],"profound":[14],"understanding":[15],"scene.":[18],"While":[19],"audio":[20],"signals":[23],"are":[24,60],"able":[25],"provide":[27],"relevant":[28],"information":[29],"separately,":[30],"the":[31,47,83,87,91,103],"combination":[32],"both":[34,61],"modalities":[35,93],"offers":[36],"more":[37],"accurate":[38],"precise":[40],"information.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45,67],"address":[46],"problem":[48],"audio-visual":[50,70],"event":[51],"detection.":[52],"goal":[54],"is":[55],"identify":[57],"events":[58],"that":[59,72],"visible":[62],"audible.":[64],"For":[65],"this,":[66],"propose":[68],"an":[69],"network":[71],"models":[73],"intra":[74],"inter-modality":[76],"interactions":[77],"with":[78,94],"Multi-Head":[79],"Attention":[80],"layers.":[81],"Furthermore,":[82],"proposed":[84],"model":[85],"captures":[86],"temporal":[88],"correlation":[89],"between":[90],"two":[92],"multimodal":[95],"LSTMs.":[96],"Our":[97],"method":[98],"achieves":[99],"state-of-the-art":[100],"performance":[101],"on":[102],"AVE":[104],"dataset.":[105]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
