{"id":"https://openalex.org/W4401413869","doi":"https://doi.org/10.1109/icra57147.2024.10610980","title":"Aligning Knowledge Graph with Visual Perception for Object-goal Navigation","display_name":"Aligning Knowledge Graph with Visual Perception for Object-goal Navigation","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401413869","doi":"https://doi.org/10.1109/icra57147.2024.10610980"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610980","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610980","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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/A5101486827","display_name":"Nuo Xu","orcid":"https://orcid.org/0000-0003-2586-5804"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Nuo Xu","raw_affiliation_strings":["ZhejiangLab,Hangzhou,China,311100"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZhejiangLab,Hangzhou,China,311100","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396400","display_name":"Wen Wang","orcid":"https://orcid.org/0009-0009-1644-2341"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["ZhejiangLab,Hangzhou,China,311100"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZhejiangLab,Hangzhou,China,311100","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101761591","display_name":"Rong Yang","orcid":"https://orcid.org/0000-0001-5620-7615"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Yang","raw_affiliation_strings":["ZhejiangLab,Hangzhou,China,311100"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZhejiangLab,Hangzhou,China,311100","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039406326","display_name":"Mengjie Qin","orcid":"https://orcid.org/0000-0001-6350-2217"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengjie Qin","raw_affiliation_strings":["ZhejiangLab,Hangzhou,China,311100"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZhejiangLab,Hangzhou,China,311100","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028966460","display_name":"Zheyuan Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheyuan Lin","raw_affiliation_strings":["ZhejiangLab,Hangzhou,China,311100"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZhejiangLab,Hangzhou,China,311100","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101491069","display_name":"Wei Song","orcid":"https://orcid.org/0000-0003-0327-8385"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Song","raw_affiliation_strings":["ZhejiangLab,Hangzhou,China,311100"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZhejiangLab,Hangzhou,China,311100","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101539720","display_name":"Chunlong Zhang","orcid":"https://orcid.org/0000-0003-2291-1422"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunlong Zhang","raw_affiliation_strings":["ZhejiangLab,Hangzhou,China,311100"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZhejiangLab,Hangzhou,China,311100","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010340252","display_name":"Jason Gu","orcid":"https://orcid.org/0000-0002-7626-1077"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jason Gu","raw_affiliation_strings":["Dalhousie University,Department of Electrical and Computer Engineering,Halifax,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalhousie University,Department of Electrical and Computer Engineering,Halifax,Canada","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100323217","display_name":"Chao Li","orcid":"https://orcid.org/0000-0002-6304-8824"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Li","raw_affiliation_strings":["ZhejiangLab,Hangzhou,China,311100"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZhejiangLab,Hangzhou,China,311100","institution_ids":["https://openalex.org/I4210123185"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101486827"],"corresponding_institution_ids":["https://openalex.org/I4210123185"],"apc_list":null,"apc_paid":null,"fwci":3.1701,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.93003207,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5214","last_page":"5220"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987000226974487,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987000226974487,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9968000054359436,"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":0.7270257472991943},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.590888500213623},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5085417032241821},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48625004291534424},{"id":"https://openalex.org/keywords/goal-orientation","display_name":"Goal orientation","score":0.47555917501449585},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.43808525800704956},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4198804795742035},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39154431223869324},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2025514543056488},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.10583701729774475},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.07939985394477844},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.05835992097854614}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7270257472991943},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.590888500213623},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5085417032241821},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48625004291534424},{"id":"https://openalex.org/C84653758","wikidata":"https://www.wikidata.org/wiki/Q5575175","display_name":"Goal orientation","level":2,"score":0.47555917501449585},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.43808525800704956},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4198804795742035},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39154431223869324},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2025514543056488},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.10583701729774475},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.07939985394477844},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.05835992097854614}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610980","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610980","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2907492528","https://openalex.org/W2962732398","https://openalex.org/W2962887844","https://openalex.org/W2967853831","https://openalex.org/W2983335573","https://openalex.org/W2986357018","https://openalex.org/W3003265726","https://openalex.org/W3036497058","https://openalex.org/W3040041096","https://openalex.org/W3101465773","https://openalex.org/W3109001458","https://openalex.org/W3129238537","https://openalex.org/W3173993018","https://openalex.org/W3201759799","https://openalex.org/W3206376852","https://openalex.org/W3210395242","https://openalex.org/W3211462570","https://openalex.org/W4214643368","https://openalex.org/W4285787895","https://openalex.org/W4293566037","https://openalex.org/W4313180266","https://openalex.org/W4362564480","https://openalex.org/W4386076477","https://openalex.org/W4386083015","https://openalex.org/W6620707391","https://openalex.org/W6692846177","https://openalex.org/W6747106673","https://openalex.org/W6754725917","https://openalex.org/W6780167394","https://openalex.org/W6780443396","https://openalex.org/W6785121346","https://openalex.org/W6790124654","https://openalex.org/W6791353385"],"related_works":["https://openalex.org/W2569624374","https://openalex.org/W2965298293","https://openalex.org/W1607180678","https://openalex.org/W2081877814","https://openalex.org/W1905708401","https://openalex.org/W2745134424","https://openalex.org/W2628861693","https://openalex.org/W2901222770","https://openalex.org/W2240585660","https://openalex.org/W1164829494"],"abstract_inverted_index":{"Object-goal":[0],"navigation":[1,134],"is":[2],"a":[3,28,118,131,147],"challenging":[4],"task":[5],"that":[6],"requires":[7],"guiding":[8],"an":[9],"agent":[10,22],"to":[11,23,51,107,151],"specific":[12],"objects":[13],"based":[14],"on":[15,42],"first-person":[16],"visual":[17,63,113],"observations.":[18],"The":[19,115],"ability":[20],"of":[21,55,98,117,149,157],"comprehend":[24],"its":[25],"surroundings":[26],"plays":[27],"crucial":[29],"role":[30],"in":[31,60],"achieving":[32],"successful":[33],"object":[34],"finding.":[35],"However,":[36],"existing":[37],"knowledge-graph-based":[38],"navigators":[39],"often":[40],"rely":[41],"discrete":[43],"categorical":[44],"one-hot":[45],"vectors":[46],"and":[47,69,73,103,123,145,155],"vote":[48],"counting":[49],"strategy":[50],"construct":[52],"graph":[53,121],"representation":[54],"the":[56,80,99,128,142,153],"scenes,":[57],"which":[58],"results":[59],"misalignment":[61,76],"with":[62,84,112,130],"images.":[64],"To":[65],"provide":[66],"more":[67],"accurate":[68],"coherent":[70],"scene":[71,101],"descriptions":[72],"address":[74],"this":[75],"issue,":[77],"we":[78],"propose":[79],"Aligning":[81],"Knowledge":[82],"Graph":[83],"Visual":[85],"Perception":[86],"(AKGVP)":[87],"method":[88,140],"for":[89],"object-goal":[90],"navigation.":[91],"Technically,":[92],"our":[93,139,158],"approach":[94],"introduces":[95],"continuous":[96,119],"modeling":[97],"hierarchical":[100],"architecture":[102,122],"leverages":[104],"visual-language":[105],"pre-training":[106],"align":[108],"natural":[109],"language":[110],"description":[111],"perception.":[114],"integration":[116],"knowledge":[120],"multimodal":[124],"feature":[125],"alignment":[126],"empowers":[127],"navigator":[129],"remarkable":[132],"zero-shot":[133],"capability.":[135],"We":[136],"extensively":[137],"evaluate":[138],"using":[141],"AI2-THOR":[143],"simulator":[144],"conduct":[146],"series":[148],"experiments":[150],"demonstrate":[152],"effectiveness":[154],"efficiency":[156],"navigator.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-19T08:33:51.333923","created_date":"2025-10-10T00:00:00"}