{"id":"https://openalex.org/W3015925607","doi":"https://doi.org/10.1109/icassp40776.2020.9053895","title":"What Makes the Sound?: A Dual-Modality Interacting Network for Audio-Visual Event Localization","display_name":"What Makes the Sound?: A Dual-Modality Interacting Network for Audio-Visual Event Localization","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015925607","doi":"https://doi.org/10.1109/icassp40776.2020.9053895","mag":"3015925607"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053895","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053895","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5014646768","display_name":"Janani Ramaswamy","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Janani Ramaswamy","raw_affiliation_strings":["Dept. of Computer Science and Engineering, IIT Madras, Chennai, India"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Engineering, IIT Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5014646768"],"corresponding_institution_ids":["https://openalex.org/I24676775"],"apc_list":null,"apc_paid":null,"fwci":6.8482,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.97766424,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4372","last_page":"4376"},"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":0.998199999332428,"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":0.9955999851226807,"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":0.8065711259841919},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7763441801071167},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6965376138687134},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6783448457717896},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6008211970329285},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5299941897392273},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4857790768146515},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.44725117087364197},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.40508604049682617},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3766191005706787},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32754141092300415},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.14177384972572327},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.07979914546012878}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8065711259841919},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7763441801071167},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6965376138687134},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6783448457717896},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6008211970329285},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5299941897392273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4857790768146515},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.44725117087364197},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.40508604049682617},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3766191005706787},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32754141092300415},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.14177384972572327},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.07979914546012878},{"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/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053895","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053895","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1938425378","https://openalex.org/W2511428026","https://openalex.org/W2593116425","https://openalex.org/W2604379605","https://openalex.org/W2619697695","https://openalex.org/W2623327532","https://openalex.org/W2810643877","https://openalex.org/W2905139236","https://openalex.org/W2931433835","https://openalex.org/W2962756039","https://openalex.org/W2962865004","https://openalex.org/W2962898677","https://openalex.org/W2962960500","https://openalex.org/W2963115079","https://openalex.org/W2963150162","https://openalex.org/W2963218389","https://openalex.org/W2963680395","https://openalex.org/W2964109005","https://openalex.org/W2964213933","https://openalex.org/W2964345931","https://openalex.org/W2980339970","https://openalex.org/W4293665662","https://openalex.org/W4294576248","https://openalex.org/W6725104640","https://openalex.org/W6729831399","https://openalex.org/W6735927292","https://openalex.org/W6738806211","https://openalex.org/W6747045456","https://openalex.org/W6749633790","https://openalex.org/W6750591037","https://openalex.org/W6750599028","https://openalex.org/W6752922659","https://openalex.org/W6757408916"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"The":[0],"presence":[1,60],"of":[2,14,25,32,49,61,105,115,138],"auditory":[3],"and":[4,20,68,102],"visual":[5,21],"senses":[6],"enables":[7,90],"humans":[8],"to":[9,57],"obtain":[10],"a":[11,35,71,83],"profound":[12],"understanding":[13],"the":[15,30,39,47,54,59,100,106,113,120,136],"real-world":[16],"scenes.":[17],"While":[18],"audio":[19],"signals":[22],"are":[23],"capable":[24],"providing":[26],"scene":[27],"knowledge":[28],"individually,":[29],"combination":[31],"both":[33,66,125],"offers":[34],"better":[36],"insight":[37],"about":[38],"underlying":[40],"event.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45,81],"address":[46],"problem":[48],"audio-visual":[50],"event":[51,63],"localization":[52],"where":[53],"goal":[55],"is":[56,65],"identify":[58],"an":[62],"that":[64,89],"audible":[67],"visible":[69],"in":[70,124],"video,":[72],"using":[73],"fully":[74,126],"or":[75],"weakly":[76,130],"supervised":[77,131],"learning.":[78],"For":[79],"this,":[80],"propose":[82],"novel":[84],"Audio-Visual":[85],"Interacting":[86],"Network":[87],"(AVIN)":[88],"inter":[91],"as":[92,94,127,129],"well":[93,128],"intra":[95],"modality":[96],"interactions":[97],"by":[98],"exploiting":[99],"local":[101],"global":[103],"information":[104],"two":[107],"modalities.":[108],"Our":[109],"empirical":[110],"evaluations":[111],"confirm":[112],"superiority":[114],"our":[116,139],"proposed":[117],"model":[118],"over":[119],"existing":[121],"state-of-the-art":[122],"methods,":[123],"learning":[132],"tasks,":[133],"thus":[134],"asserting":[135],"efficacy":[137],"joint-modeling.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}