{"id":"https://openalex.org/W4415539019","doi":"https://doi.org/10.1145/3746027.3758219","title":"Open3D-VQA: A Benchmark for Embodied Spatial Concept Reasoning with Multimodal Large Language Model in Open Space","display_name":"Open3D-VQA: A Benchmark for Embodied Spatial Concept Reasoning with Multimodal Large Language Model in Open Space","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539019","doi":"https://doi.org/10.1145/3746027.3758219"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3758219","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758219","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3758219","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024468450","display_name":"Weichen Zhang","orcid":"https://orcid.org/0009-0008-8892-9389"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weichen Zhang","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China and Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0008-8892-9389","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China and Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053038102","display_name":"Zhi-Feng Zhou","orcid":"https://orcid.org/0009-0002-6979-4761"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Zile Zhou","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0002-6979-4761","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xin Zeng","orcid":"https://orcid.org/0009-0008-2543-1495"},"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":"Xin Zeng","raw_affiliation_strings":["Sun Yat-sen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0008-2543-1495","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103120117","display_name":"Xuchen Liu","orcid":"https://orcid.org/0009-0008-9076-4819"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu Xuchen","raw_affiliation_strings":["Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0008-9076-4819","affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049683420","display_name":"Jihua Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianjie Fang","raw_affiliation_strings":["Northeastern University, Qinhuangdao, China"],"raw_orcid":"https://orcid.org/0009-0008-2599-9929","affiliations":[{"raw_affiliation_string":"Northeastern University, Qinhuangdao, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078622343","display_name":"Chen Gao","orcid":"https://orcid.org/0000-0002-7561-5646"},"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":"Chen Gao","raw_affiliation_strings":["BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7561-5646","affiliations":[{"raw_affiliation_string":"BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062631244","display_name":"Jinqiang Cui","orcid":"https://orcid.org/0000-0002-7833-1876"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinqiang Cui","raw_affiliation_strings":["Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-7833-1876","affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100355277","display_name":"Yong Li","orcid":"https://orcid.org/0000-0001-5617-1659"},"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":"Yong Li","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China and BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5617-1659","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China and BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016095713","display_name":"Xinlei Chen","orcid":"https://orcid.org/0000-0001-8271-5023"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"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":"Xinlei Chen","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-8271-5023","affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100363146","display_name":"Xiao\u2013Ping Zhang","orcid":"https://orcid.org/0000-0001-5241-0069"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Ping Zhang","raw_affiliation_strings":["Shenzhen Key Laboratory of Ubiquitous Data Enabling, Tsinghua University, Shenzhen, China and Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-5241-0069","affiliations":[{"raw_affiliation_string":"Shenzhen Key Laboratory of Ubiquitous Data Enabling, Tsinghua University, Shenzhen, China and Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12784","last_page":"12791"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9829000234603882,"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/T12031","display_name":"Speech and dialogue systems","score":0.9818000197410583,"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/benchmark","display_name":"Benchmark (surveying)","score":0.8384000062942505},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.7537000179290771},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5187000036239624},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.5145999789237976},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.512499988079071},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.46630001068115234},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.41999998688697815},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4174000024795532},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.41510000824928284}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8384000062942505},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.7537000179290771},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7210999727249146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5875999927520752},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5187000036239624},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.5145999789237976},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.512499988079071},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.46630001068115234},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.41999998688697815},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4174000024795532},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.41510000824928284},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4027000069618225},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37940001487731934},{"id":"https://openalex.org/C166088908","wikidata":"https://www.wikidata.org/wiki/Q308495","display_name":"Abductive reasoning","level":2,"score":0.3747999966144562},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.364300012588501},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.36390000581741333},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.2655999958515167},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3758219","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758219","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3758219","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758219","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2561715562","https://openalex.org/W3034758614","https://openalex.org/W3109085430","https://openalex.org/W3210997132","https://openalex.org/W4320059944","https://openalex.org/W4366967222","https://openalex.org/W4381802186","https://openalex.org/W4392866731","https://openalex.org/W4394862905","https://openalex.org/W4402716272","https://openalex.org/W4402716288","https://openalex.org/W4412889658","https://openalex.org/W4412889756"],"related_works":[],"abstract_inverted_index":{"Spatial":[0],"reasoning":[1,54,134],"is":[2],"a":[3,27],"fundamental":[4],"capability":[5],"of":[6],"multimodal":[7],"large":[8],"language":[9],"models":[10],"(MLLMs),":[11],"yet":[12],"their":[13],"performance":[14,135],"in":[15,57,136],"open":[16],"aerial":[17,42,85],"environments":[18],"remains":[19],"underexplored.":[20],"In":[21],"this":[22,149],"work,":[23],"we":[24],"present":[25],"Open3D-VQA,":[26],"novel":[28],"benchmark":[29,45],"for":[30],"evaluating":[31],"MLLMs'":[32],"ability":[33],"to":[34,113],"reason":[35],"about":[36,102],"complex":[37],"spatial":[38,53,77,104,133],"relationships":[39],"from":[40,76,80],"an":[41],"perspective.":[43],"The":[44,71,139],"comprises":[46],"73k":[47],"QA":[48],"pairs":[49],"across":[50],"seven":[51],"general":[52],"tasks,":[55],"offered":[56],"multiple-choice,":[58],"true/false,":[59],"and":[60,63,67,83,120,143],"short-answer":[61],"formats,":[62],"supports":[64],"both":[65,81],"visual":[66],"point":[68],"cloud":[69],"modalities.":[70],"questions":[72,101],"are":[73,96,146],"automatically":[74],"generated":[75],"relations":[78,105],"extracted":[79],"real-world":[82,137],"simulated":[84,126],"scenes.":[86],"Evaluation":[87],"on":[88,124,148],"13":[89],"popular":[90],"MLLMs":[91],"reveals":[92],"that:":[93],"1)":[94],"Models":[95],"generally":[97],"better":[98],"at":[99],"answering":[100],"relative":[103],"than":[106],"absolute":[107],"distances,":[108],"2)":[109],"3D":[110],"LLMs":[111],"fail":[112],"demonstrate":[114],"significant":[115],"advantages":[116],"over":[117],"2D":[118],"LLMs,":[119],"3)":[121],"Fine-tuning":[122],"solely":[123],"the":[125,131],"dataset":[127],"can":[128],"significantly":[129],"improve":[130],"model's":[132],"scenarios.":[138],"benchmark,":[140],"generation":[141],"pipeline,":[142],"evaluation":[144],"toolkit":[145],"released":[147],"page.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}