{"id":"https://openalex.org/W4402353007","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651083","title":"Modular Method for Embodied Instruction Following with Environmental Context Adaptation","display_name":"Modular Method for Embodied Instruction Following with Environmental Context Adaptation","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402353007","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651083"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10651083","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10651083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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/A5065317043","display_name":"Zhuoqun Xu","orcid":"https://orcid.org/0000-0002-3535-4402"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhuoqun Xu","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering"],"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112119042","display_name":"Liubo Ouyang","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liubo Ouyang","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering"],"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100757367","display_name":"Liu Yang","orcid":"https://orcid.org/0000-0002-4816-5942"},"institutions":[{"id":"https://openalex.org/I4210155230","display_name":"Samsung (China)","ror":"https://ror.org/04yt00889","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210155230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Samsung Research China,Beijing"],"affiliations":[{"raw_affiliation_string":"Samsung Research China,Beijing","institution_ids":["https://openalex.org/I4210155230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100425448","display_name":"Li Zhang","orcid":"https://orcid.org/0000-0001-7914-0679"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhang","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering"],"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5065317043"],"corresponding_institution_ids":["https://openalex.org/I16609230"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16473973,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9574999809265137,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9574999809265137,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9470999836921692,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9416000247001648,"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":0.8943138122558594},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7607777118682861},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.7573193311691284},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6917629837989807},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6478219032287598},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39574429392814636},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24838659167289734},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.20113524794578552},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15039145946502686},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.05434712767601013}],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.8943138122558594},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7607777118682861},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.7573193311691284},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6917629837989807},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6478219032287598},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39574429392814636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24838659167289734},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20113524794578552},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15039145946502686},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.05434712767601013},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10651083","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10651083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1933349210","https://openalex.org/W2250539671","https://openalex.org/W2799002257","https://openalex.org/W2896457183","https://openalex.org/W2946260552","https://openalex.org/W2950697717","https://openalex.org/W2962684798","https://openalex.org/W2962887844","https://openalex.org/W2964289358","https://openalex.org/W2964487155","https://openalex.org/W2998903229","https://openalex.org/W3009928773","https://openalex.org/W3034201026","https://openalex.org/W3034758614","https://openalex.org/W3034999214","https://openalex.org/W3042040243","https://openalex.org/W3089887959","https://openalex.org/W3090814639","https://openalex.org/W3173781631","https://openalex.org/W3176814369","https://openalex.org/W3203663566","https://openalex.org/W4200523064","https://openalex.org/W4214700710","https://openalex.org/W4282981845","https://openalex.org/W4285306713","https://openalex.org/W4295312788","https://openalex.org/W4312647074","https://openalex.org/W4402776467","https://openalex.org/W6747106673","https://openalex.org/W6755207826","https://openalex.org/W6766978945","https://openalex.org/W6774815639","https://openalex.org/W6780091408","https://openalex.org/W6784429693"],"related_works":["https://openalex.org/W2380179524","https://openalex.org/W4283365723","https://openalex.org/W2963001125","https://openalex.org/W2091233881","https://openalex.org/W2352366064","https://openalex.org/W4250820896","https://openalex.org/W2124102101","https://openalex.org/W4250305970","https://openalex.org/W1484550171","https://openalex.org/W2333383158"],"abstract_inverted_index":{"Embodied":[0,9],"instruction":[1],"following":[2],"(EIF)":[3],"is":[4,62,125,134],"a":[5,16,50,55,74,100,104],"challenging":[6],"task":[7],"in":[8,41,68,93,150],"AI":[10],"that":[11,37,87,147],"requires":[12],"robots":[13],"to":[14,143],"possess":[15],"range":[17],"of":[18,82,139,158],"capabilities,":[19],"including":[20],"language":[21],"understanding,":[22],"object":[23],"identification,":[24],"environmental":[25],"exploration,":[26],"action":[27],"planning,":[28],"and":[29,70,96,116,131],"accurate":[30],"manipulation.":[31],"To":[32],"investigate":[33],"household":[34],"robot":[35],"tasks":[36,67],"are":[38],"considered":[39],"meaningful":[40],"the":[42,45,83,88,132,144,151,156],"near":[43],"future,":[44],"community":[46],"has":[47,91],"already":[48],"developed":[49],"primary":[51],"solution":[52],"based":[53],"on":[54,127],"modular":[56,89],"method,":[57],"but":[58],"its":[59],"overall":[60],"performance":[61,133],"far":[63],"from":[64],"human.":[65],"Completing":[66],"unfamiliar":[69],"unseen":[71],"environments":[72],"presents":[73],"significant":[75],"challenge":[76],"for":[77],"intelligent":[78],"robots.":[79,159],"Error":[80],"analysis":[81],"ALFRED":[84],"dataset":[85],"indicates":[86],"structure":[90],"shortcomings":[92],"target":[94],"comprehension":[95],"vision-based":[97],"interaction.":[98],"As":[99],"result,":[101],"we":[102],"propose":[103],"post-processing":[105],"optimization":[106],"approach,":[107],"which":[108],"includes":[109],"environment":[110,153],"information":[111,149],"alignment":[112],"using":[113],"semantic":[114],"match":[115],"visual":[117],"interaction":[118],"enhancement":[119],"with":[120],"pose":[121],"adjustment.":[122],"Our":[123],"paradigm":[124],"evaluated":[126],"two":[128],"interactive":[129],"datasets,":[130],"improved":[135],"by":[136],"an":[137],"average":[138],"37.12%":[140],"(relative)":[141],"compared":[142],"baseline,":[145],"suggesting":[146],"context":[148],"current":[152],"effectively":[154],"increases":[155],"adaptability":[157]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}