{"id":"https://openalex.org/W4367728104","doi":"https://doi.org/10.1109/lra.2023.3272518","title":"Learning Semantic-Agnostic and Spatial-Aware Representation for Generalizable Visual-Audio Navigation","display_name":"Learning Semantic-Agnostic and Spatial-Aware Representation for Generalizable Visual-Audio Navigation","publication_year":2023,"publication_date":"2023-05-02","ids":{"openalex":"https://openalex.org/W4367728104","doi":"https://doi.org/10.1109/lra.2023.3272518"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2023.3272518","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2023.3272518","pdf_url":"https://ieeexplore.ieee.org/ielx7/7083369/10102643/10114576.pdf","source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"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 Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/7083369/10102643/10114576.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063455114","display_name":"Hongcheng Wang","orcid":"https://orcid.org/0000-0002-8222-7529"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongcheng Wang","raw_affiliation_strings":["School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8222-7529","affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064198367","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0000-0002-7516-0784"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxuan Wang","raw_affiliation_strings":["Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, China","Center on Frontiers of Computing Studies, Institute for Artificial Intelligence, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Center on Frontiers of Computing Studies, Institute for Artificial Intelligence, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081893016","display_name":"Fangwei Zhong","orcid":"https://orcid.org/0000-0002-0428-4552"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangwei Zhong","raw_affiliation_strings":["National Key Laboratory of General Artificial Intelligence, School of Intelligence and Technology, BIGAI, Peking University,, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0428-4552","affiliations":[{"raw_affiliation_string":"National Key Laboratory of General Artificial Intelligence, School of Intelligence and Technology, BIGAI, Peking University,, Beijing, China","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102207921","display_name":"Mingdong Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingdong Wu","raw_affiliation_strings":["School of Computer Science, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100326970","display_name":"Jianwei Zhang","orcid":"https://orcid.org/0000-0002-7856-5760"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jianwei Zhang","raw_affiliation_strings":["TAMS, Department of Informatics, Universität Hamburg, Hamburg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-7856-5760","affiliations":[{"raw_affiliation_string":"TAMS, Department of Informatics, Universität Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100602395","display_name":"Yizhou Wang","orcid":"https://orcid.org/0000-0001-9888-6409"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhou Wang","raw_affiliation_strings":["Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, China","Center on Frontiers of Computing Studies, Institute for Artificial Intelligence, Peking University, Beijing, China","Nat'l Eng. Research Center of Visual Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9888-6409","affiliations":[{"raw_affiliation_string":"Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Center on Frontiers of Computing Studies, Institute for Artificial Intelligence, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Nat'l Eng. Research Center of Visual Technology, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100709867","display_name":"Hao Dong","orcid":"https://orcid.org/0000-0002-7984-9909"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Dong","raw_affiliation_strings":["School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7984-9909","affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3364,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.79370156,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"8","issue":"6","first_page":"3900","last_page":"3907"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9901000261306763,"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":0.8172255754470825},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6934638023376465},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6230852603912354},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5833539962768555},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5322859883308411},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5089082717895508},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4995872974395752},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.42226219177246094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8172255754470825},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6934638023376465},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6230852603912354},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5833539962768555},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5322859883308411},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5089082717895508},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4995872974395752},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.42226219177246094},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2023.3272518","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2023.3272518","pdf_url":"https://ieeexplore.ieee.org/ielx7/7083369/10102643/10114576.pdf","source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/lra.2023.3272518","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2023.3272518","pdf_url":"https://ieeexplore.ieee.org/ielx7/7083369/10102643/10114576.pdf","source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"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 Robotics and Automation Letters","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3598382722","display_name":null,"funder_award_id":"62136001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4612480795","display_name":null,"funder_award_id":"62006006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5379697419","display_name":null,"funder_award_id":"62061136001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4367728104.pdf","grobid_xml":"https://content.openalex.org/works/W4367728104.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W1714475535","https://openalex.org/W1797096580","https://openalex.org/W1973800293","https://openalex.org/W1974965325","https://openalex.org/W1980443700","https://openalex.org/W2042450346","https://openalex.org/W2050197540","https://openalex.org/W2052272730","https://openalex.org/W2058487874","https://openalex.org/W2071230191","https://openalex.org/W2085421181","https://openalex.org/W2087048062","https://openalex.org/W2139190150","https://openalex.org/W2169528473","https://openalex.org/W2551677029","https://openalex.org/W2736601468","https://openalex.org/W2884565639","https://openalex.org/W2949830259","https://openalex.org/W2962887844","https://openalex.org/W2963065757","https://openalex.org/W2964339842","https://openalex.org/W2981436548","https://openalex.org/W2981954954","https://openalex.org/W2982667879","https://openalex.org/W2987529085","https://openalex.org/W3044499041","https://openalex.org/W3089887959","https://openalex.org/W3108332675","https://openalex.org/W3176232375","https://openalex.org/W4225899838","https://openalex.org/W4233877385","https://openalex.org/W4288616852","https://openalex.org/W4312121730","https://openalex.org/W4312498304","https://openalex.org/W6639480849","https://openalex.org/W6729556111","https://openalex.org/W6734678876","https://openalex.org/W6741002519","https://openalex.org/W6747146101","https://openalex.org/W6753516098","https://openalex.org/W6760170756","https://openalex.org/W6764040762","https://openalex.org/W6770244962","https://openalex.org/W6780443396","https://openalex.org/W6784119104","https://openalex.org/W6790416196","https://openalex.org/W6797297730","https://openalex.org/W6804305004","https://openalex.org/W6810700606"],"related_works":["https://openalex.org/W2068608913","https://openalex.org/W3162204513","https://openalex.org/W3124914020","https://openalex.org/W2141033859","https://openalex.org/W2371138613","https://openalex.org/W2156434174","https://openalex.org/W2048963458","https://openalex.org/W2071701083","https://openalex.org/W3213722473","https://openalex.org/W2110944602"],"abstract_inverted_index":{"Visual-audio":[0],"navigation":[1],"(VAN)":[2],"is":[3],"attracting":[4],"more":[5,7],"and":[6,21,33,42,81,116,130,139,157],"attention":[8],"from":[9],"the":[10,36,46,100,108],"robotic":[11],"community":[12],"due":[13],"to":[14,35,57,77,123,152],"its":[15],"broad":[16],"applications,":[17],"e.g.,":[18],"household":[19],"robots":[20],"rescue":[22],"robots.":[23],"In":[24],"this":[25],"task,":[26],"an":[27],"embodied":[28],"agent":[29,109],"must":[30],"search":[31],"for":[32,84,94],"navigate":[34],"sound":[37,59,159],"source":[38],"with":[39,99,127,154],"egocentric":[40],"visual":[41,115],"audio":[43,117],"observations.":[44],"However,":[45],"existing":[47],"methods":[48],"are":[49],"limited":[50],"in":[51,64],"two":[52,69,91,105],"aspects:":[53],"1)":[54],"poor":[55],"generalization":[56,147],"unheard":[58,158],"categories;":[60],"2)":[61],"sample":[62],"inefficient":[63],"training.":[65],"Focusing":[66],"on":[67,125,134],"these":[68,104],"problems,":[70],"we":[71],"propose":[72],"a":[73,79,111],"brain-inspired":[74],"plug-and-play":[75],"method":[76,144],"learn":[78],"semantic-agnostic":[80],"spatial-aware":[82],"representation":[83,113],"generalizable":[85],"visual-audio":[86],"navigation.":[87],"We":[88],"meticulously":[89],"design":[90],"auxiliary":[92,106],"tasks":[93],"respectively":[95],"accelerating":[96],"learning":[97],"representations":[98],"above-desired":[101],"characteristics.":[102],"With":[103],"tasks,":[107],"learns":[110],"spatially-correlated":[112],"of":[114],"inputs":[118],"that":[119,142],"can":[120],"be":[121],"applied":[122],"work":[124],"environments":[126],"novel":[128],"sounds":[129],"maps.":[131],"Experiment":[132],"results":[133],"realistic":[135],"3D":[136],"scenes":[137,153],"(Replica":[138],"Matterport3D)":[140],"demonstrate":[141],"our":[143],"achieves":[145],"better":[146],"performance":[148],"when":[149],"zero-shot":[150],"transferred":[151],"unseen":[155],"maps":[156],"categories.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2023-05-04T00:00:00"}