{"id":"https://openalex.org/W4408147875","doi":"https://doi.org/10.1080/01691864.2025.2469689","title":"DM <sup>2</sup> RM: dual-mode multimodal ranking for target objects and receptacles based on open-vocabulary instructions","display_name":"DM <sup>2</sup> RM: dual-mode multimodal ranking for target objects and receptacles based on open-vocabulary instructions","publication_year":2025,"publication_date":"2025-03-04","ids":{"openalex":"https://openalex.org/W4408147875","doi":"https://doi.org/10.1080/01691864.2025.2469689"},"language":"en","primary_location":{"id":"doi:10.1080/01691864.2025.2469689","is_oa":false,"landing_page_url":"https://doi.org/10.1080/01691864.2025.2469689","pdf_url":null,"source":{"id":"https://openalex.org/S192584203","display_name":"Advanced Robotics","issn_l":"0169-1864","issn":["0169-1864","1568-5535"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Robotics","raw_type":"journal-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/A5092489705","display_name":"Ryosuke Korekata","orcid":"https://orcid.org/0009-0008-0354-9070"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Ryosuke Korekata","raw_affiliation_strings":["Keio University"],"raw_orcid":"https://orcid.org/0009-0008-0354-9070","affiliations":[{"raw_affiliation_string":"Keio University","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023996791","display_name":"Kanta Kaneda","orcid":null},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kanta Kaneda","raw_affiliation_strings":["Keio University"],"raw_orcid":"https://orcid.org/0009-0001-3879-645X","affiliations":[{"raw_affiliation_string":"Keio University","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023168087","display_name":"Shunya Nagashima","orcid":"https://orcid.org/0009-0007-9741-7628"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shunya Nagashima","raw_affiliation_strings":["Keio University"],"raw_orcid":"https://orcid.org/0009-0007-9741-7628","affiliations":[{"raw_affiliation_string":"Keio University","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuto Imai","orcid":"https://orcid.org/0009-0005-4077-3627"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuto Imai","raw_affiliation_strings":["Keio University"],"raw_orcid":"https://orcid.org/0009-0005-4077-3627","affiliations":[{"raw_affiliation_string":"Keio University","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033744547","display_name":"Komei Sugiura","orcid":"https://orcid.org/0000-0002-0261-0510"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Komei Sugiura","raw_affiliation_strings":["Keio University"],"raw_orcid":"https://orcid.org/0000-0002-0261-0510","affiliations":[{"raw_affiliation_string":"Keio University","institution_ids":["https://openalex.org/I203951103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5092489705"],"corresponding_institution_ids":["https://openalex.org/I203951103"],"apc_list":null,"apc_paid":null,"fwci":0.7655,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.67461497,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"39","issue":"5","first_page":"243","last_page":"258"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9976000189781189,"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/T10028","display_name":"Topic Modeling","score":0.9937000274658203,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6202611327171326},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.5008032321929932},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.4959782063961029},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48581528663635254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4496847987174988},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4424353539943695},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3646671175956726},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3302368223667145},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.2393510937690735},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.132483571767807}],"concepts":[{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6202611327171326},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.5008032321929932},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.4959782063961029},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48581528663635254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4496847987174988},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4424353539943695},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3646671175956726},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3302368223667145},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2393510937690735},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.132483571767807},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/01691864.2025.2469689","is_oa":false,"landing_page_url":"https://doi.org/10.1080/01691864.2025.2469689","pdf_url":null,"source":{"id":"https://openalex.org/S192584203","display_name":"Advanced Robotics","issn_l":"0169-1864","issn":["0169-1864","1568-5535"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Robotics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5299999713897705,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G167863043","display_name":"\u5b9f\u4e16\u754c\u3092\u691c\u7d22\u53ef\u80fd\u3068\u3059\u308b\u30af\u30ed\u30b9\u30e2\u30fc\u30c0\u30eb\u8a00\u8a9e\u51e6\u7406\u57fa\u76e4\u306e\u69cb\u7bc9","funder_award_id":"23K28168","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4354532953","display_name":null,"funder_award_id":"23H03478","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320321034","display_name":"New Energy and Industrial Technology Development Organization","ror":"https://ror.org/0055k7a87"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1825604117","https://openalex.org/W2149427297","https://openalex.org/W2185175083","https://openalex.org/W2187089797","https://openalex.org/W2193945050","https://openalex.org/W2489434015","https://openalex.org/W2905544595","https://openalex.org/W2947311533","https://openalex.org/W2962716343","https://openalex.org/W2963800628","https://openalex.org/W2963922343","https://openalex.org/W2964211610","https://openalex.org/W2964339842","https://openalex.org/W2972544311","https://openalex.org/W3009928773","https://openalex.org/W3034578524","https://openalex.org/W3037369911","https://openalex.org/W3090449556","https://openalex.org/W3099587965","https://openalex.org/W3172514680","https://openalex.org/W3192009892","https://openalex.org/W3193171560","https://openalex.org/W3203247393","https://openalex.org/W4207072548","https://openalex.org/W4210665528","https://openalex.org/W4312424618","https://openalex.org/W4366851068","https://openalex.org/W4383097638","https://openalex.org/W4383108457","https://openalex.org/W4383108895","https://openalex.org/W4385245566","https://openalex.org/W4386075729","https://openalex.org/W4386076142","https://openalex.org/W4388720459","https://openalex.org/W4389666568","https://openalex.org/W4389666751","https://openalex.org/W4389667373","https://openalex.org/W4390691239","https://openalex.org/W4390874280","https://openalex.org/W4390874575","https://openalex.org/W4393160744","https://openalex.org/W4402890475","https://openalex.org/W4403448419","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2188500270","https://openalex.org/W2303858293","https://openalex.org/W2349784553","https://openalex.org/W3022596247","https://openalex.org/W2915512527","https://openalex.org/W51364034","https://openalex.org/W2601444686","https://openalex.org/W4307058054","https://openalex.org/W4292238148","https://openalex.org/W2793336762"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3,116,157],"aim":[4],"to":[5,21,72,102],"develop":[6],"a":[7,76,86,91,98,118,165,176],"domestic":[8],"service":[9],"robot":[10],"(DSR)":[11],"that,":[12],"guided":[13],"by":[14],"open-vocabulary":[15,35],"instructions,":[16],"can":[17],"carry":[18],"everyday":[19],"objects":[20,50,69],"the":[22,38,48,52,56,67,104,109,114,141,159,162,183],"specified":[23],"pieces":[24],"of":[25,65,127,149,161,180],"furniture.":[26],"Few":[27],"existing":[28],"methods":[29],"handle":[30],"mobile":[31],"manipulation":[32],"tasks":[33],"with":[34,133],"instructions":[36,132],"in":[37,147,152],"image":[39,153],"retrieval":[40,154],"setting,":[41],"and":[42,51,70,94,130,190],"most":[43],"do":[44],"not":[45],"identify":[46],"both":[47,66],"target":[49,68],"receptacles.":[53],"We":[54,84],"propose":[55],"Dual-Mode":[57],"Multimodal":[58],"Ranking":[59],"model":[60,78,101],"(DM2RM),":[61],"which":[62],"enables":[63],"images":[64,123],"receptacles":[71],"be":[73],"retrieved":[74],"using":[75],"single":[77],"based":[79,107],"on":[80,108,164],"multimodal":[81],"foundation":[82],"models.":[83],"introduce":[85],"switching":[87],"mechanism":[88],"that":[89,140],"leverages":[90],"mode":[92],"token":[93],"phrase":[95],"identification":[96],"via":[97],"large":[99],"language":[100],"switch":[103],"embedding":[105],"space":[106],"prediction":[110],"target.":[111],"To":[112],"evaluate":[113],"DM2RM,":[115],"construct":[117],"novel":[119],"dataset":[120],"including":[121,170],"real-world":[122,167],"collected":[124],"from":[125],"hundreds":[126],"building-scale":[128],"environments":[129],"crowd-sourced":[131],"referring":[134],"expressions.":[135],"The":[136],"evaluation":[137],"results":[138],"show":[139],"proposed":[142],"DM2RM":[143,163],"outperforms":[144],"previous":[145],"approaches":[146],"terms":[148],"standard":[150],"metrics":[151],"settings.":[155],"Furthermore,":[156],"demonstrate":[158],"application":[160],"standardized":[166],"DSR":[168],"platform":[169],"fetch-and-carry":[171],"actions,":[172],"where":[173],"it":[174],"achieves":[175],"task":[177],"success":[178],"rate":[179],"82%":[181],"despite":[182],"zero-shot":[184],"transfer":[185],"setting.":[186],"Demonstration":[187],"videos,":[188],"code,":[189],"more":[191],"materials":[192],"are":[193],"available":[194],"at":[195],"https://kkrr10.github.io/dm2rm/.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-14T06:11:07.267592","created_date":"2025-10-10T00:00:00"}