{"id":"https://openalex.org/W2981985754","doi":"https://doi.org/10.1145/3343031.3351010","title":"Audiovisual Zooming","display_name":"Audiovisual Zooming","publication_year":2019,"publication_date":"2019-10-15","ids":{"openalex":"https://openalex.org/W2981985754","doi":"https://doi.org/10.1145/3343031.3351010","mag":"2981985754"},"language":"en","primary_location":{"id":"doi:10.1145/3343031.3351010","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3351010","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Multimedia","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/A5037296813","display_name":"Arun Asokan Nair","orcid":"https://orcid.org/0000-0002-6857-4313"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arun Asokan Nair","raw_affiliation_strings":["Snap Research, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Research, Baltimore, MD, USA","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073346635","display_name":"Austin Reiter","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Austin Reiter","raw_affiliation_strings":["Snap Research, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Research, New York, NY, USA","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101571936","display_name":"Changxi Zheng","orcid":"https://orcid.org/0000-0001-9228-1038"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changxi Zheng","raw_affiliation_strings":["Snap Research, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Research, New York, NY, USA","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051975921","display_name":"Shree K. Nayar","orcid":"https://orcid.org/0000-0002-6452-6998"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shree Nayar","raw_affiliation_strings":["Snap Research, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Snap Research, New York, NY, USA","institution_ids":["https://openalex.org/I4210142583"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210142583"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1107","last_page":"1118"},"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9965999722480774,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9965000152587891,"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/zoom","display_name":"Zoom","score":0.8017877340316772},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.789713978767395},{"id":"https://openalex.org/keywords/panning","display_name":"Panning (audio)","score":0.7818005084991455},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.6516737937927246},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5589004755020142},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5584942102432251},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5550047159194946},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4825403094291687},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.4750937223434448},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3997842073440552},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13042739033699036},{"id":"https://openalex.org/keywords/lens","display_name":"Lens (geology)","score":0.10137063264846802},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08497512340545654},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07738414406776428}],"concepts":[{"id":"https://openalex.org/C124913957","wikidata":"https://www.wikidata.org/wiki/Q1232548","display_name":"Zoom","level":3,"score":0.8017877340316772},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.789713978767395},{"id":"https://openalex.org/C108944566","wikidata":"https://www.wikidata.org/wiki/Q1524510","display_name":"Panning (audio)","level":4,"score":0.7818005084991455},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6516737937927246},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5589004755020142},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5584942102432251},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5550047159194946},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4825403094291687},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.4750937223434448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3997842073440552},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13042739033699036},{"id":"https://openalex.org/C15336307","wikidata":"https://www.wikidata.org/wiki/Q1766051","display_name":"Lens (geology)","level":2,"score":0.10137063264846802},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08497512340545654},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07738414406776428},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C78762247","wikidata":"https://www.wikidata.org/wiki/Q1273174","display_name":"Petroleum engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3343031.3351010","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3343031.3351010","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W164774473","https://openalex.org/W1500551892","https://openalex.org/W1503933356","https://openalex.org/W1515932869","https://openalex.org/W1536644969","https://openalex.org/W1552314771","https://openalex.org/W1574170747","https://openalex.org/W1622825395","https://openalex.org/W1967648217","https://openalex.org/W1971846076","https://openalex.org/W2005882741","https://openalex.org/W2066218102","https://openalex.org/W2067295501","https://openalex.org/W2099128937","https://openalex.org/W2101609516","https://openalex.org/W2127851351","https://openalex.org/W2135908157","https://openalex.org/W2158143227","https://openalex.org/W2167734090","https://openalex.org/W2568308529","https://openalex.org/W2735090526","https://openalex.org/W2800288142","https://openalex.org/W3122808968","https://openalex.org/W4210538530","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W1970823786","https://openalex.org/W2032030284","https://openalex.org/W2262768164","https://openalex.org/W2785782068","https://openalex.org/W4300189336","https://openalex.org/W1604934725","https://openalex.org/W2514326793","https://openalex.org/W2963576081","https://openalex.org/W2406240328","https://openalex.org/W2165915693"],"abstract_inverted_index":{"When":[0],"capturing":[1],"videos":[2],"on":[3,105,142,179],"a":[4,32,89,96,100,131,154,184,188],"mobile":[5,143,182,185],"platform,":[6],"often":[7],"the":[8,15,20,28,39,48,65,77,84,111,115,147],"target":[9],"of":[10,35,87,122,157,171],"interest":[11],"is":[12,42,52,73,81],"contaminated":[13,44],"by":[14,45],"surrounding":[16],"environment.":[17],"To":[18,145],"alleviate":[19],"visual":[21,56],"irrelevance,":[22],"camera":[23],"panning":[24],"and":[25,57,135,149,187],"zooming":[26,129,178],"provide":[27],"means":[29],"to":[30,75,92],"isolate":[31],"desired":[33],"field":[34],"view":[36],"(FOV).":[37],"However,":[38],"captured":[40],"audio":[41],"still":[43],"signals":[46],"outside":[47],"FOV.":[49],"This":[50],"effect":[51],"unnatural---for":[53],"human":[54],"perception,":[55],"auditory":[58,71,112],"cues":[59],"must":[60],"go":[61],"hand-in-hand.":[62],"We":[63,125],"present":[64],"concept":[66],"ofAudiovisual":[67],"Zooming,":[68],"whereby":[69],"an":[70,119,137],"FOV":[72,116],"formed":[74],"match":[76],"visual.":[78],"Our":[79],"framework":[80],"built":[82],"around":[83],"classic":[85],"idea":[86],"beamforming,":[88],"computational":[90],"approach":[91],"enhancing":[93],"sound":[94],"from":[95],"single":[97],"direction":[98],"using":[99],"microphone":[101,172],"array.":[102],"Yet,":[103],"beamforming":[104],"its":[106],"own":[107],"can":[108],"not":[109],"incorporate":[110],"FOV,":[113],"as":[114,130,161,163],"may":[117],"include":[118],"arbitrary":[120],"number":[121],"directional":[123],"sources.":[124],"formulate":[126],"our":[127,158],"audiovisual":[128,177],"generalized":[132],"eigenvalue":[133],"problem":[134],"propose":[136],"algorithm":[138],"for":[139,166,194],"efficient":[140],"computation":[141],"platforms.":[144],"inform":[146],"algorithmic":[148,159],"physical":[150],"implementation,":[151],"we":[152,175],"offer":[153],"theoretical":[155],"analysis":[156],"components":[160],"well":[162],"numerical":[164],"studies":[165],"understanding":[167],"various":[168],"design":[169],"choices":[170],"arrays.":[173],"Finally,":[174],"demonstrate":[176],"two":[180],"different":[181],"platforms:":[183],"smartphone":[186],"360$^\\circ":[189],"$":[190],"spherical":[191],"imaging":[192],"system":[193],"video":[195],"conference":[196],"settings.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
