{"id":"https://openalex.org/W3021321555","doi":"https://doi.org/10.1109/wacv45572.2020.9093616","title":"See the Sound, Hear the Pixels","display_name":"See the Sound, Hear the Pixels","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W3021321555","doi":"https://doi.org/10.1109/wacv45572.2020.9093616","mag":"3021321555"},"language":"en","primary_location":{"id":"doi:10.1109/wacv45572.2020.9093616","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv45572.2020.9093616","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","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":["Visualization and Perception Lab, IIT Madras, India"],"affiliations":[{"raw_affiliation_string":"Visualization and Perception Lab, IIT Madras, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000019969","display_name":"Sukhendu Das","orcid":"https://orcid.org/0000-0002-2823-9211"},"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":false,"raw_author_name":"Sukhendu Das","raw_affiliation_strings":["Visualization and Perception Lab, IIT Madras, India"],"affiliations":[{"raw_affiliation_string":"Visualization and Perception Lab, IIT Madras, India","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5014646768"],"corresponding_institution_ids":["https://openalex.org/I24676775"],"apc_list":null,"apc_paid":null,"fwci":7.9135,"has_fulltext":false,"cited_by_count":76,"citation_normalized_percentile":{"value":0.98382131,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2959","last_page":"2968"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8271288871765137},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6775439977645874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6189025640487671},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.612554132938385},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5668712854385376},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3911222517490387},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39080798625946045},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3597225546836853},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.08649769425392151}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8271288871765137},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6775439977645874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6189025640487671},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.612554132938385},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5668712854385376},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3911222517490387},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39080798625946045},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3597225546836853},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.08649769425392151},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv45572.2020.9093616","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv45572.2020.9093616","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":75,"referenced_works":["https://openalex.org/W335832833","https://openalex.org/W1575833922","https://openalex.org/W1686810756","https://openalex.org/W1938425378","https://openalex.org/W2015394094","https://openalex.org/W2065274193","https://openalex.org/W2095532467","https://openalex.org/W2105582566","https://openalex.org/W2106488367","https://openalex.org/W2106745099","https://openalex.org/W2117539524","https://openalex.org/W2142192571","https://openalex.org/W2151750630","https://openalex.org/W2164899449","https://openalex.org/W2170653751","https://openalex.org/W2171819471","https://openalex.org/W2396147015","https://openalex.org/W2511428026","https://openalex.org/W2526050071","https://openalex.org/W2556930864","https://openalex.org/W2593116425","https://openalex.org/W2604379605","https://openalex.org/W2619697695","https://openalex.org/W2751525844","https://openalex.org/W2810643877","https://openalex.org/W2884585870","https://openalex.org/W2890052321","https://openalex.org/W2905139236","https://openalex.org/W2931433835","https://openalex.org/W2949197413","https://openalex.org/W2962699416","https://openalex.org/W2962756039","https://openalex.org/W2962781483","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/W2963383024","https://openalex.org/W2963680395","https://openalex.org/W2963717374","https://openalex.org/W2964048159","https://openalex.org/W2964109005","https://openalex.org/W2964213933","https://openalex.org/W2964345931","https://openalex.org/W2980339970","https://openalex.org/W2981816492","https://openalex.org/W2981851635","https://openalex.org/W2982619606","https://openalex.org/W2988200020","https://openalex.org/W2989980422","https://openalex.org/W2990113535","https://openalex.org/W4293665662","https://openalex.org/W4294576248","https://openalex.org/W6634232107","https://openalex.org/W6637373629","https://openalex.org/W6682508104","https://openalex.org/W6684193366","https://openalex.org/W6711963698","https://openalex.org/W6725104640","https://openalex.org/W6728881024","https://openalex.org/W6729831399","https://openalex.org/W6729977899","https://openalex.org/W6735927292","https://openalex.org/W6738806211","https://openalex.org/W6747045456","https://openalex.org/W6749633790","https://openalex.org/W6749767719","https://openalex.org/W6750591037","https://openalex.org/W6750599028","https://openalex.org/W6752922659","https://openalex.org/W6753412334","https://openalex.org/W6754048563","https://openalex.org/W6757408916"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W4245955731","https://openalex.org/W2393726419","https://openalex.org/W2380912101","https://openalex.org/W1984634519","https://openalex.org/W2801048620"],"abstract_inverted_index":{"For":[0],"every":[1],"event":[2],"occurring":[3],"in":[4,77,97,182,193],"the":[5,15,27,41,74,91,138,146,180,196,205],"real":[6],"world,":[7],"most":[8],"often":[9],"a":[10,67,78,86,175,190,202],"sound":[11,75,95,149],"is":[12,134],"associated":[13],"with":[14,30,141],"corresponding":[16],"visual":[17,31,79],"scene.":[18],"Humans":[19],"possess":[20],"an":[21,35,46,183],"inherent":[22],"ability":[23],"to":[24,34,72,136,144,178,204],"automatically":[25],"map":[26],"audio":[28],"content":[29],"scenes":[32],"leading":[33],"effortless":[36],"and":[37,55,69,104,116,128,160],"enhanced":[38],"understanding":[39],"of":[40,93,148,155,207],"underlying":[42],"event.":[43],"This":[44],"triggers":[45],"interesting":[47],"question:":[48],"Can":[49],"this":[50,82,125],"natural":[51],"correspondence":[52],"between":[53],"video":[54],"audio,":[56],"which":[57,100],"has":[58,171],"been":[59,122,172],"diminutively":[60],"explored":[61],"so":[62],"far,":[63],"be":[64],"learned":[65],"by":[66],"machine":[68],"modeled":[70],"jointly":[71],"localize":[73],"source":[76,96],"scene?":[80],"In":[81],"paper,":[83],"we":[84],"propose":[85],"novel":[87,108,163],"algorithm":[88,140],"that":[89,132],"addresses":[90],"problem":[92],"localizing":[94],"unconstrained":[98],"videos,":[99],"uses":[101],"efficient":[102],"fusion":[103],"attention":[105],"mechanisms.":[106],"Two":[107],"blocks":[109],"namely,":[110],"Audio":[111,164],"Visual":[112,165],"Fusion":[113],"Block":[114,119],"(AVFB)":[115],"Segment-Wise":[117],"Attention":[118],"(SWAB)":[120],"have":[121],"developed":[123],"for":[124],"purpose.":[126],"Quantitative":[127],"qualitative":[129],"evaluations":[130,188],"show":[131],"it":[133],"feasible":[135],"use":[137],"same":[139],"minor":[142],"modifications":[143],"serve":[145],"purpose":[147],"localization":[150,181],"using":[151],"three":[152],"different":[153],"types":[154],"learning:":[156],"supervised,":[157],"weakly":[158],"supervised":[159],"unsupervised.":[161],"A":[162],"Triplet":[166],"Gram":[167],"Matrix":[168],"Loss":[169],"(AVTGML)":[170],"proposed":[173,209],"as":[174,201],"loss":[176],"function":[177],"learn":[179],"unsupervised":[184],"way.":[185],"Our":[186],"empirical":[187],"demonstrate":[189],"significant":[191],"increase":[192],"performance":[194],"over":[195],"existing":[197],"state-of-the-art":[198],"methods,":[199],"serving":[200],"testimony":[203],"superiority":[206],"our":[208],"approach.":[210]},"counts_by_year":[{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":3}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}