{"id":"https://openalex.org/W4416748891","doi":"https://doi.org/10.1109/iros60139.2025.11247159","title":"3D-MoRe: Unified Modal-Contextual Reasoning for Embodied Question Answering","display_name":"3D-MoRe: Unified Modal-Contextual Reasoning for Embodied Question Answering","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748891","doi":"https://doi.org/10.1109/iros60139.2025.11247159"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5038918940","display_name":"Rongtao Xu","orcid":"https://orcid.org/0000-0003-4619-9679"},"institutions":[{"id":"https://openalex.org/I2800497579","display_name":"CRC for Spatial information","ror":"https://ror.org/022482e21","country_code":"AU","type":"facility","lineage":["https://openalex.org/I2800497579"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Rongtao Xu","raw_affiliation_strings":["Spatialtemporal AI"],"affiliations":[{"raw_affiliation_string":"Spatialtemporal AI","institution_ids":["https://openalex.org/I2800497579"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087291850","display_name":"Han Gao","orcid":"https://orcid.org/0000-0002-6021-2764"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Gao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088326086","display_name":"Mingming Yu","orcid":"https://orcid.org/0000-0002-4081-7774"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingming Yu","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000446896","display_name":"Dong An","orcid":"https://orcid.org/0000-0002-5133-6562"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong An","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112328631","display_name":"Shunpeng Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shunpeng Chen","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020628396","display_name":"Changwei Wang","orcid":"https://orcid.org/0000-0001-8259-7717"},"institutions":[{"id":"https://openalex.org/I4210150840","display_name":"Ministry of Education","ror":"https://ror.org/04a3gjw65","country_code":"BD","type":"government","lineage":["https://openalex.org/I4210150840"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Changwei Wang","raw_affiliation_strings":["Shandong Computer Science Center,Key Laboratory of Computing Power Network and Information Security, Ministry of Education"],"affiliations":[{"raw_affiliation_string":"Shandong Computer Science Center,Key Laboratory of Computing Power Network and Information Security, Ministry of Education","institution_ids":["https://openalex.org/I4210150840"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675165","display_name":"Li Guo","orcid":"https://orcid.org/0000-0002-9723-3294"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Guo","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057585043","display_name":"Xiaodan Liang","orcid":"https://orcid.org/0000-0003-3767-2444"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodan Liang","raw_affiliation_strings":["Sun Yat-Sen University,China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011919230","display_name":"Shibiao Xu","orcid":"https://orcid.org/0000-0003-4037-9900"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shibiao Xu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5038918940"],"corresponding_institution_ids":["https://openalex.org/I2800497579"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36923249,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5924","last_page":"5929"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9829000234603882,"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":0.9829000234603882,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0031999999191612005,"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/T10028","display_name":"Topic Modeling","score":0.0027000000700354576,"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/question-answering","display_name":"Question answering","score":0.7946000099182129},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6064000129699707},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.5701000094413757},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5636000037193298},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5609999895095825},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.531499981880188},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5127999782562256},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.41830000281333923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8202999830245972},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7946000099182129},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6064000129699707},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5701000094413757},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5636000037193298},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5609999895095825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5485000014305115},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.531499981880188},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5141000151634216},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5127999782562256},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.41830000281333923},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4074000120162964},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.35109999775886536},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3174999952316284},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C102993220","wikidata":"https://www.wikidata.org/wiki/Q387196","display_name":"Description logic","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26739999651908875},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.2554999887943268},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321125","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56"},{"id":"https://openalex.org/F4320326839","display_name":"State Key Laboratory of Virtual Reality Technology and Systems","ror":null},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2194775991","https://openalex.org/W2594519801","https://openalex.org/W3107521863","https://openalex.org/W4221167937","https://openalex.org/W4226376247","https://openalex.org/W4298357738","https://openalex.org/W4312377093","https://openalex.org/W4312650216","https://openalex.org/W4384917104","https://openalex.org/W4386066792","https://openalex.org/W4386076628","https://openalex.org/W4389474301","https://openalex.org/W4390872240","https://openalex.org/W4390872495","https://openalex.org/W4391462706","https://openalex.org/W4391853818","https://openalex.org/W4394773594","https://openalex.org/W4401991200","https://openalex.org/W4402690602","https://openalex.org/W4402703032","https://openalex.org/W4402716423","https://openalex.org/W4402753874","https://openalex.org/W4409366443","https://openalex.org/W4413788337"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,34,76,128,164,172],"growing":[2],"need":[3],"for":[4],"diverse":[5],"and":[6,17,49,59,68,87,95,109,155,166],"scalable":[7],"data":[8,106],"in":[9,71,143,150],"indoor":[10],"scene":[11,61,79],"tasks,":[12],"such":[13],"as":[14],"question":[15],"answering":[16],"dense":[18],"captioning,":[19],"we":[20],"propose":[21],"3D-MoRe,":[22],"a":[23,50,140],"novel":[24],"paradigm":[25],"designed":[26],"to":[27,54,113,162],"generate":[28],"large-scale":[29],"3D-language":[30],"datasets":[31,157],"by":[32,132,145],"lever-aging":[33],"strengths":[35],"of":[36],"foundational":[37],"models.":[38],"The":[39],"framework":[40],"integrates":[41],"key":[42],"components,":[43],"including":[44],"multi-modal":[45],"embedding,":[46],"cross-modal":[47],"interaction,":[48],"language":[51,57],"model":[52],"decoder,":[53],"process":[55],"natural":[56],"instructions":[58],"3D":[60,73,78],"data.":[62,116],"This":[63],"approach":[64,138],"facilitates":[65],"enhanced":[66],"reasoning":[67],"response":[69],"generation":[70],"complex":[72],"environments.":[74],"Using":[75],"ScanNet":[77],"dataset,":[80],"along":[81],"with":[82,127],"text":[83],"annotations":[84],"from":[85],"ScanQA":[86,119],"ScanRefer,":[88,136],"3D-MoRe":[89,122],"generates":[90],"62,000":[91],"question-answer":[92],"(QA)":[93],"pairs":[94],"73,000":[96],"object":[97],"descriptions":[98],"across":[99],"1,513":[100],"scenes.":[101],"We":[102],"also":[103],"employ":[104],"various":[105],"augmentation":[107],"techniques":[108],"implement":[110],"semantic":[111],"filtering":[112],"ensure":[114],"high-quality":[115],"Experiments":[117],"on":[118,135,171],"demonstrate":[120],"that":[121],"significantly":[123],"outperforms":[124],"state-of-the-art":[125],"baselines,":[126],"CIDEr":[129],"score":[130],"improving":[131],"2.15%.":[133],"Similarly,":[134],"our":[137],"achieves":[139],"notable":[141],"increase":[142],"CIDEr@0.5":[144],"1.84%,":[146],"highlighting":[147],"its":[148],"effectiveness":[149],"both":[151,167],"tasks.":[152],"Our":[153],"code":[154],"generated":[156],"will":[158],"be":[159,169],"publicly":[160],"released":[161],"benefit":[163],"community,":[165],"can":[168],"accessed":[170],"https://3D-MoRe.github.io.":[173]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}