{"id":"https://openalex.org/W4405784939","doi":"https://doi.org/10.1109/iros58592.2024.10801720","title":"EMBOSR: Embodied Spatial Reasoning for Enhanced Situated Question Answering in 3D Scenes","display_name":"EMBOSR: Embodied Spatial Reasoning for Enhanced Situated Question Answering in 3D Scenes","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405784939","doi":"https://doi.org/10.1109/iros58592.2024.10801720"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10801720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5100337968","display_name":"Hao Yu","orcid":"https://orcid.org/0000-0002-3944-3162"},"institutions":[{"id":"https://openalex.org/I4210141097","display_name":"T\u00e2n T\u1ea1o University","ror":"https://ror.org/03q6f0894","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210141097"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Yu Hao","raw_affiliation_strings":["NYU Tandon"],"affiliations":[{"raw_affiliation_string":"NYU Tandon","institution_ids":["https://openalex.org/I4210141097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089874335","display_name":"Fan Yang","orcid":"https://orcid.org/0000-0003-0359-1187"},"institutions":[{"id":"https://openalex.org/I4210141097","display_name":"T\u00e2n T\u1ea1o University","ror":"https://ror.org/03q6f0894","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210141097"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Fan Yang","raw_affiliation_strings":["NYU Tandon"],"affiliations":[{"raw_affiliation_string":"NYU Tandon","institution_ids":["https://openalex.org/I4210141097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062568215","display_name":"Nicholas X. Fang","orcid":"https://orcid.org/0000-0001-5713-629X"},"institutions":[{"id":"https://openalex.org/I4210134877","display_name":"AFC Energy (United Kingdom)","ror":"https://ror.org/02sftpz67","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210134877"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nicholas Fang","raw_affiliation_strings":["Cranleigh,Abu Dhabi,UAE"],"affiliations":[{"raw_affiliation_string":"Cranleigh,Abu Dhabi,UAE","institution_ids":["https://openalex.org/I4210134877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101691399","display_name":"Yu-Shen Liu","orcid":"https://orcid.org/0000-0001-7305-1915"},"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":"Yu-Shen Liu","raw_affiliation_strings":["Tsinghua University,School of Software"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,School of Software","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100337968"],"corresponding_institution_ids":["https://openalex.org/I4210141097"],"apc_list":null,"apc_paid":null,"fwci":0.5248,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6852606,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"9811","last_page":"9816"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9961000084877014,"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/T13382","display_name":"Robotics and Automated Systems","score":0.994700014591217,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.889704704284668},{"id":"https://openalex.org/keywords/situated","display_name":"Situated","score":0.8846141695976257},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.7174439430236816},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6161374449729919},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.571222186088562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4382185935974121},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.3215145468711853},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.16844594478607178}],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.889704704284668},{"id":"https://openalex.org/C132829578","wikidata":"https://www.wikidata.org/wiki/Q581151","display_name":"Situated","level":2,"score":0.8846141695976257},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.7174439430236816},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6161374449729919},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.571222186088562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4382185935974121},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3215145468711853},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.16844594478607178}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10801720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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":19,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2594519801","https://openalex.org/W2757393022","https://openalex.org/W3095319910","https://openalex.org/W3095974555","https://openalex.org/W3099655892","https://openalex.org/W3107521863","https://openalex.org/W4207072548","https://openalex.org/W4226376247","https://openalex.org/W4389520282","https://openalex.org/W4390872495","https://openalex.org/W4394773594","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6741002519","https://openalex.org/W6778883912","https://openalex.org/W6809646742","https://openalex.org/W6846381433","https://openalex.org/W6855425132"],"related_works":["https://openalex.org/W1964989911","https://openalex.org/W4387507518","https://openalex.org/W2015118488","https://openalex.org/W4230093006","https://openalex.org/W2753017648","https://openalex.org/W2513760693","https://openalex.org/W2062819913","https://openalex.org/W2149544884","https://openalex.org/W2133485962","https://openalex.org/W2001662723"],"abstract_inverted_index":{"3D":[0,26,41,134,167,192],"Embodied":[1],"Spatial":[2],"Reasoning,":[3],"emphasizing":[4],"an":[5,31],"agent\u2019s":[6],"interaction":[7],"with":[8,114,180],"its":[9,35,184,218],"surroundings":[10],"for":[11,105,158,204],"spatial":[12,102,159],"information":[13],"inference,":[14],"is":[15,122,142],"adeptly":[16],"facilitated":[17],"by":[18],"the":[19,57,109,115,143,155,197,201,211],"process":[20],"of":[21,111,117,133,139,145,148,214],"Situated":[22],"Question":[23],"Answering":[24],"in":[25,60,65,85,129,165,186,200],"Scenes":[27],"(SQA3D).":[28],"SQA3D":[29,190],"requires":[30],"agent":[32],"to":[33,53,82,124,217],"comprehend":[34],"position":[36],"and":[37,48,90,127,161,191,229],"orientation":[38],"within":[39],"a":[40,45,72,99,130,146],"scene":[42],"based":[43],"on":[44,74,77],"textual":[46],"situation":[47],"then":[49],"utilize":[50],"this":[51,66],"understanding":[52],"answer":[54],"questions":[55],"about":[56],"surrounding":[58],"environment":[59],"that":[61],"context.":[62],"Previous":[63],"methods":[64,179],"field":[67],"face":[68],"substantial":[69],"challenges,":[70,96],"including":[71,189],"dependency":[73],"constant":[75],"retraining":[76],"limited":[78,88],"datasets,":[79],"which":[80,152],"leads":[81],"poor":[83],"performance":[84],"unseen":[86],"scenarios,":[87],"expandability,":[89],"inadequate":[91],"generalization.":[92],"To":[93],"address":[94],"these":[95],"we":[97,173],"present":[98],"new":[100,137],"embodied":[101],"reasoning":[103,150,160],"paradigm":[104],"enhanced":[106],"SQA3D,":[107],"fusing":[108],"capabilities":[110],"foundation":[112],"models":[113],"chain":[116,147],"thought":[118,149],"methodology.":[119],"This":[120],"approach":[121,176],"designed":[123],"elevate":[125],"adaptability":[126],"scalability":[128],"wide":[131],"array":[132],"environments.":[135,168],"A":[136],"aspect":[138],"our":[140,170,175,215,225],"model":[141],"integration":[144],"process,":[151],"significantly":[153],"augments":[154],"model\u2019s":[156],"capability":[157],"complex":[162,205],"query":[163],"handling":[164],"diverse":[166],"In":[169],"structured":[171],"experiments,":[172],"compare":[174],"against":[177],"other":[178],"varying":[181],"architectures,":[182],"demonstrating":[183],"efficacy":[185],"multiple":[187],"tasks":[188],"captioning.":[193],"We":[194],"also":[195],"assess":[196],"informativeness":[198],"contained":[199],"generated":[202],"answers":[203],"queries.":[206],"Ablation":[207],"studies":[208],"further":[209],"delineate":[210],"individual":[212],"contributions":[213],"method":[216],"overall":[219],"performance.":[220],"The":[221],"results":[222],"consistently":[223],"affirm":[224],"proposed":[226],"method\u2019s":[227],"effectiveness":[228],"efficiency.":[230]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}