{"id":"https://openalex.org/W4416429287","doi":"https://doi.org/10.1109/tnnls.2025.3619968","title":"Treasure Hunting: Embodied Contrastive Learning-Enhanced Coarse-to-Fine Object Seeking With Explorer and Discriminator Cooperation","display_name":"Treasure Hunting: Embodied Contrastive Learning-Enhanced Coarse-to-Fine Object Seeking With Explorer and Discriminator Cooperation","publication_year":2025,"publication_date":"2025-11-20","ids":{"openalex":"https://openalex.org/W4416429287","doi":"https://doi.org/10.1109/tnnls.2025.3619968","pmid":"https://pubmed.ncbi.nlm.nih.gov/41264429"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3619968","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3619968","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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":false,"raw_author_name":"Bolei Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-2784-011X","affiliations":[{"raw_affiliation_string":"School 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":["School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0006-2135-9532","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111359579","display_name":"Haonan Yang","orcid":"https://orcid.org/0009-0005-9644-0071"},"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":"Haonan Yang","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School 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":["School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-3393-8874","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038867899","display_name":"Rui Fan","orcid":"https://orcid.org/0000-0003-2593-6596"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Fan","raw_affiliation_strings":["College of Electronics and Information Engineering, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2593-6596","affiliations":[{"raw_affiliation_string":"College of Electronics and Information Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100438360","display_name":"Jianxin Wang","orcid":"https://orcid.org/0000-0003-1516-0480"},"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":["School of Computer Science and Engineering, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-1516-0480","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5147,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.6894154,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"37","issue":"3","first_page":"1092","last_page":"1106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.23019999265670776,"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":0.23019999265670776,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.17229999601840973,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.09080000221729279,"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/discriminator","display_name":"Discriminator","score":0.8378000259399414},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.690500020980835},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5770000219345093},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5241000056266785},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.43149998784065247},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.42649999260902405},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4189000129699707},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3926999866962433}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.8378000259399414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7069000005722046},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6992999911308289},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.690500020980835},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.588699996471405},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5770000219345093},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5241000056266785},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.43149998784065247},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.42649999260902405},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4189000129699707},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3926999866962433},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3772999942302704},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3677000105381012},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.33480000495910645},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2854999899864197},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2720000147819519},{"id":"https://openalex.org/C2779918689","wikidata":"https://www.wikidata.org/wiki/Q3771842","display_name":"Stimulus (psychology)","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.26159998774528503},{"id":"https://openalex.org/C104319648","wikidata":"https://www.wikidata.org/wiki/Q1412040","display_name":"Figure\u2013ground","level":3,"score":0.25780001282691956},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.2531000077724457}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2025.3619968","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3619968","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:41264429","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41264429","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1737521470","display_name":null,"funder_award_id":"62272489","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2651725945","display_name":null,"funder_award_id":"62350004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3480850936","display_name":null,"funder_award_id":"2021-17","funder_id":"https://openalex.org/F4320330206","funder_display_name":"Science and Technology Program of Hunan Province"},{"id":"https://openalex.org/G8324054742","display_name":null,"funder_award_id":"62332020","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"},{"id":"https://openalex.org/F4320330206","display_name":"Science and Technology Program of Hunan Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1901129140","https://openalex.org/W1999244633","https://openalex.org/W2000214310","https://openalex.org/W2079390801","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/W3034324855","https://openalex.org/W3034728521","https://openalex.org/W3037164854","https://openalex.org/W3091259027","https://openalex.org/W3095530566","https://openalex.org/W3109001458","https://openalex.org/W3134025030","https://openalex.org/W3159481202","https://openalex.org/W3165538103","https://openalex.org/W3173993018","https://openalex.org/W3194237121","https://openalex.org/W3201759799","https://openalex.org/W3206376852","https://openalex.org/W3207872317","https://openalex.org/W3210395242","https://openalex.org/W3214825189","https://openalex.org/W4214638047","https://openalex.org/W4214643368","https://openalex.org/W4221163448","https://openalex.org/W4226052928","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/W4382727195","https://openalex.org/W4383066272","https://openalex.org/W4386025780","https://openalex.org/W4386065508","https://openalex.org/W4386071526","https://openalex.org/W4386071636","https://openalex.org/W4386071706","https://openalex.org/W4386072289","https://openalex.org/W4386076477","https://openalex.org/W4386083032","https://openalex.org/W4386185486","https://openalex.org/W4387624022","https://openalex.org/W4387968661","https://openalex.org/W4388098937","https://openalex.org/W4389666115","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","https://openalex.org/W4402754246","https://openalex.org/W4408609834"],"related_works":[],"abstract_inverted_index":{"Object":[0],"navigation":[1],"(ObjcetNav),":[2],"which":[3,32,83,207],"enables":[4],"an":[5,12,69],"agent":[6],"to":[7,55,86,170,185,194,215],"seek":[8],"any":[9],"instance":[10,235],"of":[11,37,213],"object":[13,57,231],"category,":[14],"has":[15],"shown":[16],"great":[17],"advances.":[18],"However,":[19],"current":[20],"agents":[21,85],"are":[22,116],"built":[23],"upon":[24],"occlusion-prone":[25],"visual":[26,106,114,132,201],"observations":[27],"or":[28],"compressed":[29],"2-D":[30],"maps,":[31],"hinder":[33],"their":[34],"embodied":[35,70],"perception":[36],"3-D":[38,88,135],"scene":[39,89,188],"geometry.":[40],"Furthermore,":[41],"existing":[42],"methods":[43,246],"usually":[44],"decouple":[45],"ObjectNav":[46,151,241],"into":[47],"the":[48,130,145,162,166,173,178,186,196,210],"exploration":[49,182],"and":[50,59,79,91,155,180,203,234,251],"exploitation":[51],"subtasks,":[52],"easily":[53],"leading":[54],"ambiguous":[56],"localization":[58],"blind":[60],"exploration.":[61],"To":[62],"address":[63],"these":[64],"issues,":[65],"we":[66],"first":[67],"propose":[68],"contrastive":[71,140],"learning":[72,119],"(ECL)":[73],"method":[74,227],"with":[75,134,153],"geometric":[76,204],"consistency":[77],"(GC)":[78],"behavioral":[80],"awareness":[81],"(BA),":[82],"motivates":[84],"encode":[87],"layouts":[90],"semantic":[92,136],"cues":[93],"actively.":[94],"The":[95,124,190],"BA":[96],"is":[97,126,158,168,192],"modeled":[98,127],"by":[99,128,161],"predicting":[100],"navigational":[101],"actions":[102],"based":[103,143],"on":[104,144,230,247],"multiframe":[105],"images,":[107],"as":[108],"behaviors":[109],"causing":[110],"differences":[111],"between":[112],"adjacent":[113],"sensations":[115],"crucial":[117],"for":[118],"correlations":[120],"among":[121],"continuous":[122],"visions.":[123],"GC":[125],"aligning":[129],"behavior-aware":[131,200],"stimulus":[133],"shapes":[137],"through":[138],"unsupervised":[139],"learning.":[141],"Then,":[142],"above":[146],"ECL":[147,226],"pretraining,":[148],"a":[149,221],"coarse-to-fine":[150],"policy":[152],"explorer":[154,167],"discriminator":[156,191],"cooperation":[157],"proposed,":[159],"inspired":[160],"treasure-hunting":[163],"mindset.":[164],"Concretely,":[165],"designed":[169,193],"adaptively":[171],"switch":[172],"action":[174],"spaces,":[175],"thereby":[176],"switching":[177],"global":[179],"local":[181],"thoughts":[183],"according":[184],"accumulated":[187],"priors.":[189],"discriminate":[195],"target's":[197],"authenticity":[198],"using":[199],"features":[202],"invariance":[205],"priors,":[206],"permits":[208],"mimicking":[209],"human":[211],"behavior":[212],"\"approaching":[214],"confirm\"":[216],"when":[217],"distinguishing":[218],"objects":[219],"from":[220],"distance.":[222],"As":[223],"expected,":[224],"our":[225],"performs":[228],"well":[229],"detection":[232],"(ObjDet)":[233],"segmentation":[236],"(InstSeg)":[237],"tasks.":[238],"Our":[239],"ECL-enhanced":[240],"strategy":[242],"outperforms":[243],"state-of-the-art":[244],"(SOTA)":[245],"Matterport3D":[248],"(MP3D),":[249],"Gibson,":[250],"HM3D":[252],"datasets.":[253]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2025-11-20T00:00:00"}