{"id":"https://openalex.org/W3094402295","doi":"https://doi.org/10.1109/access.2021.3115082","title":"Object Permanence Through Audio-Visual Representations","display_name":"Object Permanence Through Audio-Visual Representations","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3094402295","doi":"https://doi.org/10.1109/access.2021.3115082","mag":"3094402295"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3115082","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3115082","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09547333.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09547333.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060098545","display_name":"Fanjun Bu","orcid":"https://orcid.org/0000-0002-9953-7347"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fanjun Bu","raw_affiliation_strings":["Department of Computer Science, Cornell University, Ithaca, NY 14850 USA. (e-mail: fb266@cornell.edu)","[Dept. of Comput. Sci., Cornell Univ., Ithaca, NY, USA]"],"raw_orcid":"https://orcid.org/0000-0002-9953-7347","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Cornell University, Ithaca, NY 14850 USA. (e-mail: fb266@cornell.edu)","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"[Dept. of Comput. Sci., Cornell Univ., Ithaca, NY, USA]","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017287995","display_name":"Chien\u2010Ming Huang","orcid":"https://orcid.org/0000-0002-6838-3701"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chien-Ming Huang","raw_affiliation_strings":["Department of Computer Science, Johns Hopkins University, Baltimore, MD 21218 USA","Dept. of Comput. Sci., Johns Hopkins Univ., Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-6838-3701","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Johns Hopkins University, Baltimore, MD 21218 USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Johns Hopkins Univ., Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.1389,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.40256393,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"9","issue":null,"first_page":"131574","last_page":"131582"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9786999821662903,"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/grasp","display_name":"GRASP","score":0.7517480254173279},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.751524806022644},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7195832133293152},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.699595034122467},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6772083044052124},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.66636723279953},{"id":"https://openalex.org/keywords/object-permanence","display_name":"Object permanence","score":0.6040126085281372},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.598136842250824},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.48880502581596375},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.45446979999542236},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4390130043029785},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3388368785381317},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07649621367454529}],"concepts":[{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.7517480254173279},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.751524806022644},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7195832133293152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.699595034122467},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6772083044052124},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.66636723279953},{"id":"https://openalex.org/C22304111","wikidata":"https://www.wikidata.org/wiki/Q1417978","display_name":"Object permanence","level":4,"score":0.6040126085281372},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.598136842250824},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.48880502581596375},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.45446979999542236},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4390130043029785},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3388368785381317},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07649621367454529},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"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/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C140441792","wikidata":"https://www.wikidata.org/wiki/Q2910672","display_name":"Cognitive development","level":3,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/access.2021.3115082","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3115082","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09547333.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2010.09948","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.09948","pdf_url":"https://arxiv.org/pdf/2010.09948","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3094402295","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2010.09948","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:doaj.org/article:45655f447e3d4e5c9f2947aed14d66f6","is_oa":true,"landing_page_url":"https://doaj.org/article/45655f447e3d4e5c9f2947aed14d66f6","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 9, Pp 131574-131582 (2021)","raw_type":"article"},{"id":"doi:10.48550/arxiv.2010.09948","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.09948","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3115082","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3115082","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09547333.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310145","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3094402295.pdf","grobid_xml":"https://content.openalex.org/works/W3094402295.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1996445118","https://openalex.org/W2033321361","https://openalex.org/W2041376653","https://openalex.org/W2055556996","https://openalex.org/W2064675550","https://openalex.org/W2099442061","https://openalex.org/W2102105423","https://openalex.org/W2112090547","https://openalex.org/W2127025755","https://openalex.org/W2157904933","https://openalex.org/W2163434194","https://openalex.org/W2168595862","https://openalex.org/W2182893224","https://openalex.org/W2424778531","https://openalex.org/W2479982633","https://openalex.org/W2511428026","https://openalex.org/W2586490229","https://openalex.org/W2619697695","https://openalex.org/W2918984654","https://openalex.org/W2941761746","https://openalex.org/W2959105467","https://openalex.org/W2962756039","https://openalex.org/W2963001155","https://openalex.org/W2963115079","https://openalex.org/W2963906196","https://openalex.org/W2964046428","https://openalex.org/W2964109005","https://openalex.org/W2964342924","https://openalex.org/W2982341288","https://openalex.org/W2989954484","https://openalex.org/W2999527441","https://openalex.org/W3009524608","https://openalex.org/W3033920763","https://openalex.org/W3091067209","https://openalex.org/W3091482797","https://openalex.org/W3106257603","https://openalex.org/W3106415892","https://openalex.org/W6729831399","https://openalex.org/W6758340793","https://openalex.org/W6783976316","https://openalex.org/W6786456065"],"related_works":["https://openalex.org/W2076593519","https://openalex.org/W3013031147","https://openalex.org/W2587217851","https://openalex.org/W3097958591","https://openalex.org/W3044214904","https://openalex.org/W3168857782","https://openalex.org/W3136875090","https://openalex.org/W2765852165","https://openalex.org/W3004396697","https://openalex.org/W2091862867","https://openalex.org/W169933034","https://openalex.org/W3093798208","https://openalex.org/W3099853888","https://openalex.org/W2085753829","https://openalex.org/W3099966603","https://openalex.org/W2887594886","https://openalex.org/W3174214845","https://openalex.org/W3212977909","https://openalex.org/W3001075632","https://openalex.org/W3002073295"],"abstract_inverted_index":{"As":[0],"robots":[1,37,167],"perform":[2],"manipulation":[3],"tasks":[4],"and":[5,78,93,129,168],"interact":[6],"with":[7],"objects,":[8],"it":[9],"is":[10],"probable":[11],"that":[12,17,148],"they":[13,56],"accidentally":[14],"drop":[15,83],"objects":[16,138],"subsequently":[18],"bounce":[19,76,91],"out":[20],"of":[21,31,48,97,120],"their":[22],"visual":[23,118],"fields":[24],"(e.g.,":[25,61],"due":[26],"to":[27,38,125,135,162],"an":[28,32],"inadequate":[29],"grasp":[30],"unfamiliar":[33],"object).":[34],"To":[35],"enable":[36],"recover":[39],"from":[40,82,171],"such":[41],"errors,":[42],"we":[43,66,146],"draw":[44],"upon":[45],"the":[46,79,89,94,117,121,126,131],"concept":[47],"object":[49,164,172],"permanence\u2014objects":[50],"remain":[51],"in":[52,113,155],"existence":[53],"even":[54],"when":[55],"are":[57],"not":[58],"being":[59],"sensed":[60],"seen)":[62],"directly.":[63],"In":[64],"particular,":[65],"developed":[67],"a":[68,73,98],"multimodal":[69,107],"neural":[70],"network":[71],"model\u2014using":[72],"partial,":[74],"observed":[75],"trajectory":[77,92],"audio":[80],"resulting":[81],"impact":[84],"as":[85],"its":[86],"inputs\u2014to":[87],"predict":[88],"full":[90],"end":[95,110],"location":[96],"dropped":[99,137,157],"object.":[100],"We":[101],"empirically":[102],"show":[103,147],"that:":[104],"(1)":[105],"our":[106,149],"method":[108,150],"predicted":[109],"locations":[111,128],"close":[112],"proximity":[114],"(i.e.,":[115],"within":[116],"field":[119],"robot\u2019s":[122],"wrist":[123],"camera)":[124],"actual":[127],"(2)":[130],"robot":[132],"was":[133],"able":[134],"retrieve":[136],"by":[139],"applying":[140],"minimal":[141],"vision-based":[142],"pick-up":[143],"adjustments.":[144],"Additionally,":[145],"outperformed":[151],"five":[152],"comparison":[153],"baselines":[154],"retrieving":[156],"objects.":[158],"Our":[159],"results":[160],"contribute":[161],"enabling":[163],"permanence":[165],"for":[166],"error":[169],"recovery":[170],"drops.":[173]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}