{"id":"https://openalex.org/W3091482797","doi":"https://doi.org/10.1109/icra40945.2020.9197528","title":"AVOT: Audio-Visual Object Tracking of Multiple Objects for Robotics","display_name":"AVOT: Audio-Visual Object Tracking of Multiple Objects for Robotics","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W3091482797","doi":"https://doi.org/10.1109/icra40945.2020.9197528","mag":"3091482797"},"language":"en","primary_location":{"id":"doi:10.1109/icra40945.2020.9197528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","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/A5102778571","display_name":"Justin Wilson","orcid":"https://orcid.org/0000-0003-2768-3799"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin Wilson","raw_affiliation_strings":["Department of Computer Science, UNC Chapel Hill, Chapel Hill, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, UNC Chapel Hill, Chapel Hill, NC, USA","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102878981","display_name":"Ming C. Lin","orcid":"https://orcid.org/0000-0003-3736-6949"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming C. Lin","raw_affiliation_strings":["Department of Computer Science, UNC Chapel Hill, Chapel Hill, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, UNC Chapel Hill, Chapel Hill, NC, USA","institution_ids":["https://openalex.org/I114027177"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114027177"],"apc_list":null,"apc_paid":null,"fwci":0.7689,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.79955906,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10045","last_page":"10051"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9998999834060669,"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/T12597","display_name":"Fire Detection and Safety Systems","score":0.9778000116348267,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":0.9739000201225281,"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":0.8281751871109009},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7976309061050415},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7493903636932373},{"id":"https://openalex.org/keywords/bittorrent-tracker","display_name":"BitTorrent tracker","score":0.7319619655609131},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.6575399041175842},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5793420672416687},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5509136319160461},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.5370769500732422},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5033275485038757},{"id":"https://openalex.org/keywords/frame-rate","display_name":"Frame rate","score":0.4679279327392578},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4676615297794342},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4511137306690216},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4340449571609497},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.42007049918174744},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.18913742899894714},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08340677618980408}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8281751871109009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7976309061050415},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7493903636932373},{"id":"https://openalex.org/C57501372","wikidata":"https://www.wikidata.org/wiki/Q2021268","display_name":"BitTorrent tracker","level":3,"score":0.7319619655609131},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.6575399041175842},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5793420672416687},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5509136319160461},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.5370769500732422},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5033275485038757},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.4679279327392578},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4676615297794342},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4511137306690216},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4340449571609497},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.42007049918174744},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.18913742899894714},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08340677618980408},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra40945.2020.9197528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","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":101,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1483870316","https://openalex.org/W1522301498","https://openalex.org/W1677182931","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1964846093","https://openalex.org/W2037227137","https://openalex.org/W2079421984","https://openalex.org/W2117539524","https://openalex.org/W2126302311","https://openalex.org/W2144506857","https://openalex.org/W2149698446","https://openalex.org/W2150066425","https://openalex.org/W2154889144","https://openalex.org/W2158592639","https://openalex.org/W2158827467","https://openalex.org/W2160490642","https://openalex.org/W2163605009","https://openalex.org/W2170865122","https://openalex.org/W2184188583","https://openalex.org/W2186094539","https://openalex.org/W2194775991","https://openalex.org/W2214775225","https://openalex.org/W2291627510","https://openalex.org/W2470139095","https://openalex.org/W2470394683","https://openalex.org/W2558899534","https://openalex.org/W2593116425","https://openalex.org/W2604445072","https://openalex.org/W2608627404","https://openalex.org/W2612445135","https://openalex.org/W2613718673","https://openalex.org/W2619697695","https://openalex.org/W2641889749","https://openalex.org/W2751765471","https://openalex.org/W2780568882","https://openalex.org/W2797032258","https://openalex.org/W2799058067","https://openalex.org/W2886910176","https://openalex.org/W2889986507","https://openalex.org/W2890882065","https://openalex.org/W2895085622","https://openalex.org/W2901155229","https://openalex.org/W2901394229","https://openalex.org/W2901751978","https://openalex.org/W2905569329","https://openalex.org/W2913562503","https://openalex.org/W2918984654","https://openalex.org/W2924096267","https://openalex.org/W2942930375","https://openalex.org/W2949608135","https://openalex.org/W2952464165","https://openalex.org/W2953920664","https://openalex.org/W2962756039","https://openalex.org/W2962824803","https://openalex.org/W2962835968","https://openalex.org/W2963037989","https://openalex.org/W2963227409","https://openalex.org/W2963446712","https://openalex.org/W2963471260","https://openalex.org/W2963499285","https://openalex.org/W2963585656","https://openalex.org/W2964121744","https://openalex.org/W2964253307","https://openalex.org/W2964286567","https://openalex.org/W2990152177","https://openalex.org/W2991391304","https://openalex.org/W3106250896","https://openalex.org/W3123318516","https://openalex.org/W3210232381","https://openalex.org/W4288408844","https://openalex.org/W4293665662","https://openalex.org/W4297775537","https://openalex.org/W6620707391","https://openalex.org/W6628973269","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6639102338","https://openalex.org/W6678515836","https://openalex.org/W6684191040","https://openalex.org/W6686207219","https://openalex.org/W6687483927","https://openalex.org/W6696672603","https://openalex.org/W6703518758","https://openalex.org/W6720170144","https://openalex.org/W6725739302","https://openalex.org/W6729831399","https://openalex.org/W6730584787","https://openalex.org/W6737664043","https://openalex.org/W6740195615","https://openalex.org/W6743518424","https://openalex.org/W6747045456","https://openalex.org/W6750169759","https://openalex.org/W6754268173","https://openalex.org/W6756605188","https://openalex.org/W6756637626","https://openalex.org/W6761178061","https://openalex.org/W6761973954","https://openalex.org/W6785652829","https://openalex.org/W6803376173"],"related_works":["https://openalex.org/W4384788979","https://openalex.org/W2511178891","https://openalex.org/W2126676984","https://openalex.org/W2954509079","https://openalex.org/W178060743","https://openalex.org/W2909390414","https://openalex.org/W3104472694","https://openalex.org/W2141888607","https://openalex.org/W2753886513","https://openalex.org/W1765993298"],"abstract_inverted_index":{"Existing":[0,36],"state-of-the-art":[1],"object":[2,72,78,118,138,167,193],"tracking":[3,40,44,79,85,121,139],"can":[4,83],"run":[5],"into":[6],"challenges":[7],"when":[8,162],"objects":[9,28],"collide,":[10],"occlude,":[11],"or":[12,41],"come":[13],"close":[14],"to":[15,25,53,93,114,173],"one":[16],"another.":[17],"These":[18,47],"visually":[19,116],"based":[20,117,180],"trackers":[21,52],"may":[22,38,105],"also":[23],"fail":[24],"differentiate":[26],"between":[27,175],"with":[29,110],"the":[30,68,149],"same":[31],"appearance":[32],"but":[33],"different":[34],"materials.":[35],"methods":[37,179],"stop":[39],"incorrectly":[42],"start":[43],"another":[45],"object.":[46],"failures":[48],"are":[49],"uneasy":[50],"for":[51],"recover":[54],"from":[55,61,71,166],"since":[56],"they":[57],"often":[58],"use":[59,96],"results":[60],"previous":[62],"frames.":[63,101],"By":[64],"using":[65,148],"audio":[66,165,182],"of":[67],"impact":[69],"sounds":[70],"collisions,":[73],"rolling,":[74],"etc.,":[75],"our":[76],"audio-visual":[77,97,152],"(AVOT)":[80],"neural":[81,112],"network":[82,172],"reduce":[84],"error":[86],"and":[87,95,120,130,141,177,186],"drift.":[88],"We":[89,123],"train":[90],"AVOT":[91,156,176],"end":[92,94],"inputs":[98],"over":[99,132,188],"all":[100,189],"Our":[102,146],"audio-based":[103],"technique":[104],"be":[106],"used":[107],"in":[108,191],"conjunction":[109],"other":[111,178],"networks":[113],"augment":[115],"detection":[119],"methods.":[122],"evaluate":[124],"its":[125],"runtime":[126],"frames-per-second":[127],"(FPS)":[128],"performance":[129,135,187],"intersection":[131],"union":[133],"(IoU)":[134],"against":[136],"OpenCV":[137],"implementations":[140],"a":[142],"deep":[143,159],"learning":[144,160],"method.":[145],"experiments,":[147],"synthetic":[150],"Sound-20K":[151],"dataset,":[153],"demonstrate":[154],"that":[155],"outperforms":[157],"single-modality":[158],"methods,":[161],"there":[163],"is":[164],"collisions.":[168],"A":[169],"proposed":[170],"scheduler":[171],"switch":[174],"on":[181],"onset":[183],"maximizes":[184],"accuracy":[185],"frames":[190],"multimodal":[192],"tracking.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}