{"id":"https://openalex.org/W4403791447","doi":"https://doi.org/10.1145/3664647.3681248","title":"Embodied Contrastive Learning with Geometric Consistency and Behavioral Awareness for Object Navigation","display_name":"Embodied Contrastive Learning with Geometric Consistency and Behavioral Awareness for Object Navigation","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791447","doi":"https://doi.org/10.1145/3664647.3681248"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681248","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5003059879","display_name":"Bolei Chen","orcid":"https://orcid.org/0000-0002-2784-011X"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bolei Chen","raw_affiliation_strings":["Shool of Computer Science and Engineering, Central South University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Shool of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102837695","display_name":"Jiaxu Kang","orcid":"https://orcid.org/0009-0006-2135-9532"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxu Kang","raw_affiliation_strings":["Shool of Computer Science and Engineering, Central South University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Shool of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002771011","display_name":"Ping Zhong","orcid":"https://orcid.org/0000-0003-3393-8874"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Zhong","raw_affiliation_strings":["Shool of Computer Science and Engineering, Central South University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Shool of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004436217","display_name":"Yixiong Liang","orcid":"https://orcid.org/0000-0003-0407-5838"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixiong Liang","raw_affiliation_strings":["Shool of Computer Science and Engineering, Central South University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Shool of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101706948","display_name":"Yu Sheng","orcid":"https://orcid.org/0000-0002-6347-0769"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Sheng","raw_affiliation_strings":["Shool of Computer Science and Engineering, Central South University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Shool of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100438360","display_name":"Jianxin Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianxin Wang","raw_affiliation_strings":["Shool of Computer Science and Engineering, Central South University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Shool of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5003059879"],"corresponding_institution_ids":["https://openalex.org/I139660479"],"apc_list":null,"apc_paid":null,"fwci":0.4986,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.66123587,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4776","last_page":"4785"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9986000061035156,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9984999895095825,"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/embodied-cognition","display_name":"Embodied cognition","score":0.8900068998336792},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6609182357788086},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6372325420379639},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5828423500061035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.542292594909668},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.49729397892951965},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.48321592807769775},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.355087548494339}],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.8900068998336792},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6609182357788086},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6372325420379639},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5828423500061035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.542292594909668},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.49729397892951965},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48321592807769775},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.355087548494339}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681248","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681248","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W2107667896","https://openalex.org/W2194775991","https://openalex.org/W2798483995","https://openalex.org/W2953127211","https://openalex.org/W2963150697","https://openalex.org/W2964339842","https://openalex.org/W3009928773","https://openalex.org/W3040041096","https://openalex.org/W3091259027","https://openalex.org/W3159481202","https://openalex.org/W3165538103","https://openalex.org/W3173993018","https://openalex.org/W3194237121","https://openalex.org/W3201759799","https://openalex.org/W3207872317","https://openalex.org/W3210395242","https://openalex.org/W3214825189","https://openalex.org/W4214638047","https://openalex.org/W4214643368","https://openalex.org/W4226052928","https://openalex.org/W4234552385","https://openalex.org/W4304092666","https://openalex.org/W4304097971","https://openalex.org/W4312295286","https://openalex.org/W4312707839","https://openalex.org/W4312729859","https://openalex.org/W4312834202","https://openalex.org/W4313180266","https://openalex.org/W4319990479","https://openalex.org/W4364353501","https://openalex.org/W4367680234","https://openalex.org/W4382362889","https://openalex.org/W4383066272","https://openalex.org/W4386025780","https://openalex.org/W4386065508","https://openalex.org/W4386071526","https://openalex.org/W4386072289","https://openalex.org/W4386076477","https://openalex.org/W4386083032","https://openalex.org/W4387968661","https://openalex.org/W4388098937","https://openalex.org/W4390871940","https://openalex.org/W4390872104","https://openalex.org/W4390872462","https://openalex.org/W4390872665","https://openalex.org/W4390872798","https://openalex.org/W4390873597","https://openalex.org/W4390874160","https://openalex.org/W4399618549"],"related_works":["https://openalex.org/W2380179524","https://openalex.org/W4283365723","https://openalex.org/W2963001125","https://openalex.org/W2091233881","https://openalex.org/W2352366064","https://openalex.org/W4250820896","https://openalex.org/W2124102101","https://openalex.org/W4250305970","https://openalex.org/W1484550171","https://openalex.org/W1570928019"],"abstract_inverted_index":{"Object":[0],"Navigation":[1],"(ObjcetNav),":[2],"which":[3,38,77],"enables":[4],"an":[5,12,63],"agent":[6],"to":[7,50,80,160],"seek":[8],"any":[9],"instance":[10,178],"of":[11,43,131,195],"object":[13,52,162,175],"category":[14],"specified":[15],"by":[16,90,98,139],"a":[17,156],"semantic":[18,36,87,137],"label,":[19],"has":[20],"shown":[21],"great":[22],"advances.":[23],"However,":[24],"current":[25],"agents":[26,79],"are":[27,116,153],"built":[28],"upon":[29],"occlusion-prone":[30],"visual":[31,105,114,133,147],"observations":[32],"or":[33],"compressed":[34],"2D":[35],"maps,":[37],"hinder":[39],"their":[40],"embodied":[41,92,199],"perception":[42],"3D":[44,83,136],"scene":[45,84],"geometry":[46],"and":[47,54,73,86,149,164,177,189],"easily":[48],"lead":[49],"ambiguous":[51],"localization":[53],"blind":[55],"exploration.":[56],"To":[57],"address":[58],"these":[59],"limitations,":[60],"we":[61],"present":[62],"Embodied":[64],"Contrastive":[65],"Learning":[66],"(ECL)":[67],"method":[68,171],"with":[69,135],"Geometric":[70],"Consistency":[71],"(GC)":[72],"Behavioral":[74],"Awareness":[75],"(BA),":[76],"motivates":[78],"actively":[81],"encode":[82],"layouts":[85],"cues.":[88],"Driven":[89],"our":[91,169,196],"exploration":[93,165],"strategy,":[94],"BA":[95],"is":[96,126],"modeled":[97,127],"predicting":[99],"navigational":[100],"actions":[101],"based":[102],"on":[103,174,187],"multi-frame":[104],"images,":[106],"as":[107,128],"behaviors":[108],"that":[109],"cause":[110],"differences":[111],"between":[112],"adjacent":[113],"sensations":[115],"crucial":[117],"for":[118],"learning":[119],"correlations":[120],"among":[121],"continuous":[122],"visions.":[123],"The":[124,144],"GC":[125],"the":[129,193],"alignment":[130],"behavior-aware":[132,146],"stimulus":[134],"shapes":[138],"employing":[140],"unsupervised":[141],"contrastive":[142],"learning.":[143],"aligned":[145],"features":[148],"geometric":[150],"invariance":[151],"priors":[152],"injected":[154],"into":[155],"modular":[157],"ObjectNav":[158,182],"framework":[159],"enhance":[161],"recognition":[163],"capabilities.":[166],"As":[167],"expected,":[168],"ECL":[170,197],"performs":[172],"well":[173],"detection":[176],"segmentation":[179],"tasks.":[180],"Our":[181],"strategy":[183],"outperforms":[184],"state-of-the-art":[185],"methods":[186],"MP3D":[188],"Gibson":[190],"datasets,":[191],"showing":[192],"potential":[194],"in":[198],"navigation.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}