{"id":"https://openalex.org/W4389666568","doi":"https://doi.org/10.1109/iros55552.2023.10342165","title":"Switching Head-Tail Funnel UNITER for Dual Referring Expression Comprehension with Fetch-and-Carry Tasks","display_name":"Switching Head-Tail Funnel UNITER for Dual Referring Expression Comprehension with Fetch-and-Carry Tasks","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389666568","doi":"https://doi.org/10.1109/iros55552.2023.10342165"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10342165","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/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,Yokohama,Kanagawa,Japan,223-8522"],"affiliations":[{"raw_affiliation_string":"Keio University,Yokohama,Kanagawa,Japan,223-8522","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030254193","display_name":"Motonari Kambara","orcid":"https://orcid.org/0000-0002-1991-9119"},"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":"Motonari Kambara","raw_affiliation_strings":["Keio University,Yokohama,Kanagawa,Japan,223-8522"],"affiliations":[{"raw_affiliation_string":"Keio University,Yokohama,Kanagawa,Japan,223-8522","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045226559","display_name":"Yu Yoshida","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":"Yu Yoshida","raw_affiliation_strings":["Keio University,Yokohama,Kanagawa,Japan,223-8522"],"affiliations":[{"raw_affiliation_string":"Keio University,Yokohama,Kanagawa,Japan,223-8522","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042770831","display_name":"Shintaro Ishikawa","orcid":"https://orcid.org/0000-0003-0810-3613"},"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":"Shintaro Ishikawa","raw_affiliation_strings":["Keio University,Yokohama,Kanagawa,Japan,223-8522"],"affiliations":[{"raw_affiliation_string":"Keio University,Yokohama,Kanagawa,Japan,223-8522","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063673622","display_name":"Yosuke Kawasaki","orcid":"https://orcid.org/0000-0002-3076-3258"},"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":"Yosuke Kawasaki","raw_affiliation_strings":["Keio University,Yokohama,Kanagawa,Japan,223-8522"],"affiliations":[{"raw_affiliation_string":"Keio University,Yokohama,Kanagawa,Japan,223-8522","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039641882","display_name":"Masaki Takahashi","orcid":"https://orcid.org/0000-0001-8138-041X"},"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":"Masaki Takahashi","raw_affiliation_strings":["Keio University,Yokohama,Kanagawa,Japan,223-8522"],"affiliations":[{"raw_affiliation_string":"Keio University,Yokohama,Kanagawa,Japan,223-8522","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,Yokohama,Kanagawa,Japan,223-8522"],"affiliations":[{"raw_affiliation_string":"Keio University,Yokohama,Kanagawa,Japan,223-8522","institution_ids":["https://openalex.org/I203951103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5092489705"],"corresponding_institution_ids":["https://openalex.org/I203951103"],"apc_list":null,"apc_paid":null,"fwci":1.7457,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.88005333,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3865","last_page":"3872"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9983999729156494,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9983999729156494,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9983000159263611,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9944999814033508,"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/dual","display_name":"Dual (grammatical number)","score":0.6090587377548218},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6006686091423035},{"id":"https://openalex.org/keywords/carry","display_name":"Carry (investment)","score":0.5960423946380615},{"id":"https://openalex.org/keywords/fetch","display_name":"Fetch","score":0.582472026348114},{"id":"https://openalex.org/keywords/funnel","display_name":"Funnel","score":0.4842240810394287},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.4797179102897644},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.4745562672615051},{"id":"https://openalex.org/keywords/environmental-science","display_name":"Environmental science","score":0.1440889835357666},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1381162703037262},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.11357718706130981},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10977014899253845},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09569358825683594},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.07986205816268921}],"concepts":[{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6090587377548218},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6006686091423035},{"id":"https://openalex.org/C2776299755","wikidata":"https://www.wikidata.org/wiki/Q432449","display_name":"Carry (investment)","level":2,"score":0.5960423946380615},{"id":"https://openalex.org/C131918245","wikidata":"https://www.wikidata.org/wiki/Q1409090","display_name":"Fetch","level":2,"score":0.582472026348114},{"id":"https://openalex.org/C17435862","wikidata":"https://www.wikidata.org/wiki/Q29957","display_name":"Funnel","level":2,"score":0.4842240810394287},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.4797179102897644},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4745562672615051},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.1440889835357666},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1381162703037262},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.11357718706130981},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10977014899253845},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09569358825683594},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.07986205816268921},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10342165","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2193945050","https://openalex.org/W2194775991","https://openalex.org/W2489434015","https://openalex.org/W2884565639","https://openalex.org/W2896457183","https://openalex.org/W2947311533","https://openalex.org/W2953626316","https://openalex.org/W2962716343","https://openalex.org/W2963800628","https://openalex.org/W2972544311","https://openalex.org/W2998552463","https://openalex.org/W3033188311","https://openalex.org/W3034758614","https://openalex.org/W3044312764","https://openalex.org/W3090449556","https://openalex.org/W3099587965","https://openalex.org/W3126809086","https://openalex.org/W3166396011","https://openalex.org/W3171125843","https://openalex.org/W3193171560","https://openalex.org/W3196798710","https://openalex.org/W3198196812","https://openalex.org/W3203511201","https://openalex.org/W3211462570","https://openalex.org/W3216551675","https://openalex.org/W4200631575","https://openalex.org/W4224912544","https://openalex.org/W4225832925","https://openalex.org/W4226052928","https://openalex.org/W4281633595","https://openalex.org/W4285069854","https://openalex.org/W4285102280","https://openalex.org/W4285306713","https://openalex.org/W4308614384","https://openalex.org/W4311248360","https://openalex.org/W4312351765","https://openalex.org/W4383108296","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6753516098","https://openalex.org/W6755207826","https://openalex.org/W6779089016","https://openalex.org/W6790124654","https://openalex.org/W6791353385","https://openalex.org/W6801810553","https://openalex.org/W6803666548","https://openalex.org/W6810640255","https://openalex.org/W6839015040","https://openalex.org/W6839459284","https://openalex.org/W6846853244","https://openalex.org/W6847670194"],"related_works":["https://openalex.org/W2073875810","https://openalex.org/W2356551568","https://openalex.org/W2081113335","https://openalex.org/W2358635018","https://openalex.org/W4242602405","https://openalex.org/W2364686644","https://openalex.org/W2889922688","https://openalex.org/W2368101485","https://openalex.org/W3201452447","https://openalex.org/W173332354"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,117,125,129,162,169],"domestic":[4,171],"service":[5],"robot":[6],"(DSR)":[7],"that":[8,142,184],"fetches":[9],"everyday":[10,166],"objects":[11,167],"and":[12,51,60,94,112,188],"carries":[13],"them":[14],"to":[15,19,39,47,65],"specified":[16],"destinations":[17],"according":[18],"free-form":[20],"natural":[21],"language":[22,73,152],"instructions.":[23],"Given":[24],"an":[25],"instruction":[26],"such":[27],"as":[28,173],"\u201cMove":[29],"the":[30,33,37,40,43,49,52,58,62,66,70,105,109,113,146,185],"bottle":[31,50],"on":[32,124,128],"left":[34],"side":[35],"of":[36,69,80,90,151,196],"plate":[38],"empty":[41],"chair,\u201d":[42],"DSR":[44,163],"is":[45,122],"expected":[46],"identify":[48],"chair":[53],"from":[54],"multiple":[55],"candidates":[56,93],"in":[57,78,149,160,168],"environment":[59,172],"carry":[61],"target":[63,91,110],"object":[64,92,111,136,186],"destination.":[67],"Most":[68],"existing":[71],"multimodal":[72],"understanding":[74],"methods":[75],"are":[76,191],"impractical":[77],"terms":[79,150],"computational":[81],"complexity":[82],"because":[83],"they":[84],"require":[85],"inferences":[86],"for":[87,132],"all":[88],"combinations":[89],"destination":[95,114],"candidates.":[96],"We":[97],"propose":[98],"Switching":[99],"Head-Tail":[100],"Funnel":[101],"UNITER,":[102],"which":[103,161],"solves":[104],"task":[106],"by":[107,175],"predicting":[108],"individually":[115],"using":[116],"single":[118],"model.":[119],"Our":[120],"method":[121,144,148],"validated":[123],"dataset":[126,131],"based":[127],"standard":[130],"Vision-and-Language":[133],"Navigation":[134],"with":[135,177,193],"manipulation":[137],"tasks.":[138],"The":[139,180],"results":[140,182],"show":[141,183],"our":[143],"outperforms":[145],"baseline":[147],"comprehension":[153],"accuracy.":[154],"Furthermore,":[155],"we":[156],"conduct":[157],"physical":[158],"experiments":[159],"delivers":[164],"standardized":[165,170],"requested":[174],"instructions":[176],"referring":[178],"expressions.":[179],"experimental":[181],"grasping":[187],"placing":[189],"actions":[190],"achieved":[192],"success":[194],"rates":[195],"more":[197],"than":[198],"90":[199],"%.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}