{"id":"https://openalex.org/W4383109113","doi":"https://doi.org/10.1109/icra48891.2023.10160748","title":"Embodied Referring Expression for Manipulation Question Answering in Interactive Environment","display_name":"Embodied Referring Expression for Manipulation Question Answering in Interactive Environment","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383109113","doi":"https://doi.org/10.1109/icra48891.2023.10160748"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160748","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160748","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","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/A5014093222","display_name":"Qie Sima","orcid":null},"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":true,"raw_author_name":"Qie Sima","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,Beijing,China","Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008661936","display_name":"Sinan Tan","orcid":"https://orcid.org/0000-0003-2035-2479"},"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":"Sinan Tan","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,Beijing,China","Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041101317","display_name":"Huaping Liu","orcid":"https://orcid.org/0000-0002-4042-6044"},"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":"Huaping Liu","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,Beijing,China","Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055546056","display_name":"Fuchun Sun","orcid":"https://orcid.org/0000-0003-3546-6305"},"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":"Fuchun Sun","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology,Beijing,China","Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100572937","display_name":"Weifeng Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096886","display_name":"Siemens (China)","ror":null,"country_code":"CN","type":null,"lineage":["https://openalex.org/I4210096886"]},{"id":"https://openalex.org/I51629411","display_name":"Siemens (China)","ror":"https://ror.org/00v6g9845","country_code":"CN","type":"company","lineage":["https://openalex.org/I1325886976","https://openalex.org/I51629411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weifeng Xu","raw_affiliation_strings":["Siemens Ltd.,China","Siemens Ltd., China"],"affiliations":[{"raw_affiliation_string":"Siemens Ltd.,China","institution_ids":["https://openalex.org/I4210096886"]},{"raw_affiliation_string":"Siemens Ltd., China","institution_ids":["https://openalex.org/I51629411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074369080","display_name":"Ling Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096886","display_name":"Siemens (China)","ror":null,"country_code":"CN","type":null,"lineage":["https://openalex.org/I4210096886"]},{"id":"https://openalex.org/I51629411","display_name":"Siemens (China)","ror":"https://ror.org/00v6g9845","country_code":"CN","type":"company","lineage":["https://openalex.org/I1325886976","https://openalex.org/I51629411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ling Fu","raw_affiliation_strings":["Siemens Ltd.,China","Siemens Ltd., China"],"affiliations":[{"raw_affiliation_string":"Siemens Ltd.,China","institution_ids":["https://openalex.org/I4210096886"]},{"raw_affiliation_string":"Siemens Ltd., China","institution_ids":["https://openalex.org/I51629411"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5014093222"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.471,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.63864164,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7635","last_page":"7641"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9990000128746033,"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":0.966890811920166},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8200557827949524},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7760071754455566},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.6721848249435425},{"id":"https://openalex.org/keywords/embodied-agent","display_name":"Embodied agent","score":0.6670398712158203},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5954553484916687},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.581147313117981},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5213443040847778},{"id":"https://openalex.org/keywords/cognitive-robotics","display_name":"Cognitive robotics","score":0.4391691982746124},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.423595666885376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3958154618740082},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14720436930656433},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06617289781570435}],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.966890811920166},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8200557827949524},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7760071754455566},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6721848249435425},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.6670398712158203},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5954553484916687},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.581147313117981},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5213443040847778},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.4391691982746124},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.423595666885376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3958154618740082},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14720436930656433},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06617289781570435},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10160748","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160748","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W2251512949","https://openalex.org/W2256948607","https://openalex.org/W2489434015","https://openalex.org/W2558535589","https://openalex.org/W2798556392","https://openalex.org/W2884565639","https://openalex.org/W2894964039","https://openalex.org/W2930283066","https://openalex.org/W2950697717","https://openalex.org/W2960655175","https://openalex.org/W2962684798","https://openalex.org/W2962732398","https://openalex.org/W2962884155","https://openalex.org/W2963109634","https://openalex.org/W2963800628","https://openalex.org/W2964345792","https://openalex.org/W2964487155","https://openalex.org/W2979727876","https://openalex.org/W2998012869","https://openalex.org/W3034578524","https://openalex.org/W3034730770","https://openalex.org/W3034758614","https://openalex.org/W3035097537","https://openalex.org/W3093025045","https://openalex.org/W3108503467","https://openalex.org/W3171547673","https://openalex.org/W3175891028","https://openalex.org/W3176495323","https://openalex.org/W3176814369","https://openalex.org/W4205161929","https://openalex.org/W4207072548","https://openalex.org/W4249013746","https://openalex.org/W4293566037","https://openalex.org/W6692355203","https://openalex.org/W6720468700","https://openalex.org/W6730250122","https://openalex.org/W6746518932","https://openalex.org/W6747106673","https://openalex.org/W6753516098","https://openalex.org/W6754725917","https://openalex.org/W6755525882","https://openalex.org/W6797397777"],"related_works":["https://openalex.org/W1570928019","https://openalex.org/W2068486122","https://openalex.org/W2044346275","https://openalex.org/W2964506265","https://openalex.org/W2513760693","https://openalex.org/W2169574110","https://openalex.org/W2354934853","https://openalex.org/W78319512","https://openalex.org/W2012344311","https://openalex.org/W381977300"],"abstract_inverted_index":{"Embodied":[0,17,26,75],"agents":[1],"are":[2],"expected":[3],"to":[4,47,80,92,94,105,147],"perform":[5,99],"more":[6],"complicated":[7],"tasks":[8,24,33],"in":[9,19,38,50,118],"an":[10],"interactive":[11],"environment,":[12],"with":[13,83,101,126],"the":[14,45,51,62,89,102,107,115,139],"progress":[15],"of":[16,40,138],"AI":[18],"recent":[20],"years.":[21],"Existing":[22],"embodied":[23,72],"including":[25],"Referring":[27],"Expression":[28],"(ERE)":[29],"and":[30,98,130],"other":[31],"QA-form":[32],"mainly":[34],"focuses":[35],"on":[36,142],"interaction":[37],"term":[39],"linguistic":[41],"instruction.":[42],"Therefore,":[43],"enabling":[44],"agent":[46,90],"manipulate":[48],"objects":[49],"environment":[52],"for":[53,61,114],"exploration":[54],"actively":[55],"has":[56],"become":[57],"a":[58,70,95,111,124],"challenging":[59],"problem":[60],"community.":[63],"To":[64,121],"solve":[65],"this":[66,122],"problem,":[67],"We":[68,109],"introduce":[69],"new":[71],"task:":[73],"Remote":[74],"Manipulation":[76],"Question":[77],"Answering":[78],"(REMQA)":[79],"combine":[81],"ERE":[82],"manipulation":[84,100],"tasks.":[85],"In":[86],"REMQA":[87,116,143],"task,":[88],"needs":[91],"navigate":[93],"remote":[96],"position":[97],"target":[103],"object":[104],"answer":[106],"question.":[108],"build":[110],"benchmark":[112],"dataset":[113,144],"task":[117],"AI2-THOR":[119],"simulator.":[120],"end,":[123],"framework":[125,141],"3D":[127],"semantic":[128],"reconstruction":[129],"modular":[131],"network":[132],"paradigms":[133],"is":[134,145],"proposed.":[135],"The":[136],"evaluation":[137],"proposed":[140],"presented":[146],"validate":[148],"its":[149],"effectiveness.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-24T08:23:43.765630","created_date":"2025-10-10T00:00:00"}
