{"id":"https://openalex.org/W4417054634","doi":"https://doi.org/10.1109/iccv51701.2025.00523","title":"COSMO: Combination of Selective Memorization for Low-Cost Vision-and-Language Navigation","display_name":"COSMO: Combination of Selective Memorization for Low-Cost Vision-and-Language Navigation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417054634","doi":"https://doi.org/10.1109/iccv51701.2025.00523"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00523","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.24065","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103005601","display_name":"Siqi Zhang","orcid":"https://orcid.org/0009-0001-3999-6111"},"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":true,"raw_author_name":"Siqi Zhang","raw_affiliation_strings":["Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049868894","display_name":"Yanyuan Qiao","orcid":"https://orcid.org/0000-0002-5606-0702"},"institutions":[{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yanyuan Qiao","raw_affiliation_strings":["Ecole polytechnique f&#x00E9;d&#x00E9;rale de Lausanne"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ecole polytechnique f&#x00E9;d&#x00E9;rale de Lausanne","institution_ids":["https://openalex.org/I142476485"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043193778","display_name":"Qunbo Wang","orcid":"https://orcid.org/0000-0002-5607-7854"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qunbo Wang","raw_affiliation_strings":["Institute of Automation,Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation,Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770893","display_name":"Zike Yan","orcid":"https://orcid.org/0000-0002-9865-2060"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zike Yan","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100731727","display_name":"Qi Wu","orcid":"https://orcid.org/0000-0003-4454-6665"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qi Wu","raw_affiliation_strings":["The University of Adelaide"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Adelaide","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004301353","display_name":"Zhihua Wei","orcid":"https://orcid.org/0000-0002-5937-3907"},"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":"Zhihua Wei","raw_affiliation_strings":["Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100725601","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0002-8839-0087"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Liu","raw_affiliation_strings":["Institute of Automation,Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation,Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5103005601"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36771461,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5511","last_page":"5522"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9803000092506409,"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":0.9803000092506409,"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/T12031","display_name":"Speech and dialogue systems","score":0.002899999963119626,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.002099999925121665,"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/memorization","display_name":"Memorization","score":0.6288999915122986},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5981000065803528},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5918999910354614},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.37380000948905945},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.3398999869823456},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.33480000495910645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.635699987411499},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.6288999915122986},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5981000065803528},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5918999910354614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5134999752044678},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.37380000948905945},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28200000524520874},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.27320000529289246},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00523","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.24065","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.24065","pdf_url":"https://arxiv.org/pdf/2503.24065","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"doi:10.48550/arxiv.2503.24065","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.24065","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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.24065","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.24065","pdf_url":"https://arxiv.org/pdf/2503.24065","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4465382280","display_name":null,"funder_award_id":"62376199,62206170,6243000159,62102416","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-and-Language":[0],"Navigation":[1],"(VLN)":[2],"tasks":[3],"have":[4,30],"gained":[5],"prominence":[6],"within":[7,118],"artificial":[8],"intelligence":[9],"research":[10],"due":[11],"to":[12,43,53,63],"their":[13],"potential":[14],"application":[15],"in":[16,169],"fields":[17],"like":[18],"home":[19],"assistants.":[20],"Many":[21],"contemporary":[22],"VLN":[23,148],"approaches,":[24],"while":[25,48,122],"based":[26],"on":[27,145],"transformer":[28,90],"architectures,":[29],"increasingly":[31],"incorporated":[32],"additional":[33],"components":[34],"such":[35],"as":[36],"external":[37],"knowledge":[38],"bases":[39],"or":[40],"map":[41],"information":[42],"enhance":[44],"performance.":[45],"These":[46],"additions,":[47],"boosting":[49],"performance,":[50],"also":[51,164],"lead":[52],"larger":[54],"models":[55],"and":[56,68,89,92,105,152],"increased":[57],"computational":[58,70,170],"costs.":[59,171],"In":[60],"this":[61],"paper,":[62],"achieve":[64],"both":[65],"high":[66],"performance":[67,159],"low":[69],"costs,":[71],"we":[72],"propose":[73],"a":[74,119,133,166],"novel":[75],"architecture":[76],"with":[77],"the":[78,100,106,123,127,138],"COmbination":[79],"of":[80,140,160],"Selective":[81,102,108],"MemOrization":[82],"(COSMO).":[83],"Specifically,":[84],"COSMO":[85],"integrates":[86],"state-space":[87],"modules":[88],"modules,":[91],"incorporates":[93],"two":[94],"VLN-customized":[95],"selective":[96,128],"state":[97,129],"space":[98,130],"modules:":[99],"Round":[101],"Scan":[103],"(RSS)":[104],"Cross-modal":[107],"State":[109],"Space":[110],"Module":[111],"(CS3).":[112],"RSS":[113],"facilitates":[114],"comprehensive":[115],"inter-modal":[116],"interactions":[117],"single":[120],"scan,":[121],"CS3":[124],"module":[125,131],"adapts":[126],"into":[132],"dual-stream":[134],"architecture,":[135],"thereby":[136],"enhancing":[137],"acquisition":[139],"cross-modal":[141],"interactions.":[142],"Experimental":[143],"validations":[144],"three":[146],"mainstream":[147],"benchmarks,":[149],"REVERIE,":[150],"R2R,":[151],"R2R-CE,":[153],"not":[154],"only":[155],"demonstrate":[156],"competitive":[157],"navigation":[158],"our":[161],"model":[162],"but":[163],"show":[165],"significant":[167],"reduction":[168]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}
