{"id":"https://openalex.org/W4416378720","doi":"https://doi.org/10.1109/iccv51701.2025.00847","title":"SITE: Towards Spatial Intelligence Thorough Evaluation","display_name":"SITE: Towards Spatial Intelligence Thorough Evaluation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416378720","doi":"https://doi.org/10.1109/iccv51701.2025.00847"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00847","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00847","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.05456","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120605155","display_name":"Wenqi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenqi Wang","raw_affiliation_strings":["Boston University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120412614","display_name":"Reuben Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Reuben Tan","raw_affiliation_strings":["Microsoft Research,Redmond"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research,Redmond","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120364554","display_name":"Pengyue Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengyue Zhu","raw_affiliation_strings":["Boston University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101607140","display_name":"Jianwei Yang","orcid":"https://orcid.org/0000-0002-2167-2880"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jianwei Yang","raw_affiliation_strings":["Microsoft Research,Redmond"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research,Redmond","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120506967","display_name":"Zhengyuan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhengyuan Yang","raw_affiliation_strings":["Microsoft Research,Redmond"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research,Redmond","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120364555","display_name":"Lijuan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lijuan Wang","raw_affiliation_strings":["Microsoft Research,Redmond"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research,Redmond","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120555524","display_name":"Andrey Kolobov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrey Kolobov","raw_affiliation_strings":["Microsoft Research,Redmond"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research,Redmond","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047233371","display_name":"Jianfeng Gao","orcid":"https://orcid.org/0000-0002-6371-505X"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jianfeng Gao","raw_affiliation_strings":["Microsoft Research,Redmond"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research,Redmond","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120364556","display_name":"Boqing Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boqing Gong","raw_affiliation_strings":["Boston University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3280462,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9058","last_page":"9069"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11904","display_name":"Spatial Cognition and Navigation","score":0.448199987411499,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11904","display_name":"Spatial Cognition and Navigation","score":0.448199987411499,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3736000061035156,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.08380000293254852,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/spatial-intelligence","display_name":"Spatial intelligence","score":0.858299970626831},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.6883000135421753},{"id":"https://openalex.org/keywords/underpinning","display_name":"Underpinning","score":0.6294000148773193},{"id":"https://openalex.org/keywords/spatial-cognition","display_name":"Spatial cognition","score":0.6279000043869019},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5922999978065491},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.5774999856948853},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5153999924659729},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5126000046730042},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.47859999537467957}],"concepts":[{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.858299970626831},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.6883000135421753},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6639999747276306},{"id":"https://openalex.org/C2780871342","wikidata":"https://www.wikidata.org/wiki/Q7883752","display_name":"Underpinning","level":2,"score":0.6294000148773193},{"id":"https://openalex.org/C2777371692","wikidata":"https://www.wikidata.org/wiki/Q2178611","display_name":"Spatial cognition","level":3,"score":0.6279000043869019},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5922999978065491},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5774999856948853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.557200014591217},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5153999924659729},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5126000046730042},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.47859999537467957},{"id":"https://openalex.org/C2778662690","wikidata":"https://www.wikidata.org/wiki/Q3125339","display_name":"Spatial ability","level":3,"score":0.45980000495910645},{"id":"https://openalex.org/C170494330","wikidata":"https://www.wikidata.org/wiki/Q1778434","display_name":"Cognitive map","level":3,"score":0.42579999566078186},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.41819998621940613},{"id":"https://openalex.org/C105409693","wikidata":"https://www.wikidata.org/wiki/Q5937824","display_name":"Human intelligence","level":2,"score":0.4117000102996826},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34850001335144043},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3474999964237213},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3409999907016754},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.33820000290870667},{"id":"https://openalex.org/C43729271","wikidata":"https://www.wikidata.org/wiki/Q3560550","display_name":"Spatial memory","level":4,"score":0.31220000982284546},{"id":"https://openalex.org/C36964233","wikidata":"https://www.wikidata.org/wiki/Q7920942","display_name":"Verbal reasoning","level":3,"score":0.30790001153945923},{"id":"https://openalex.org/C517642484","wikidata":"https://www.wikidata.org/wiki/Q2388514","display_name":"Intelligence analysis","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.3028999865055084},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.27649998664855957},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C9770341","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Geospatial analysis","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C14669888","wikidata":"https://www.wikidata.org/wiki/Q4014850","display_name":"Creative visualization","level":3,"score":0.2700999975204468},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00847","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00847","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.05456","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.05456","pdf_url":"https://arxiv.org/pdf/2505.05456","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.05456","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.05456","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.05456","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.05456","pdf_url":"https://arxiv.org/pdf/2505.05456","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416378720.pdf","grobid_xml":"https://content.openalex.org/works/W4416378720.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Spatial":[0],"intelligence":[1,47],"(SI)":[2],"represents":[3],"a":[4,25,33,80,88,128,135,139],"cognitive":[5,97],"ability":[6],"encompassing":[7],"the":[8,77],"visualization,":[9],"manipulation,":[10],"and":[11,54,56,65,68,71,87,111,144],"reasoning":[12,142],"about":[13,83,109],"spatial":[14,46,63,126,141],"relationships,":[15],"underpinning":[16],"disciplines":[17],"from":[18],"neuroscience":[19],"to":[20,41,60,75,102],"robotics.":[21],"We":[22],"introduce":[23],"SITE,":[24],"benchmark":[26,78],"dataset":[27],"towards":[28],"SI":[29,57,130],"Thorough":[30],"Evaluation":[31],"in":[32,96,125],"standardized":[34],"format":[35],"of":[36,107],"multi-choice":[37],"visual":[38,50],"question-answering,":[39],"designed":[40],"assess":[42],"large":[43],"vision-language":[44],"models'":[45],"across":[48],"diverse":[49],"modalities":[51],"(single-image,":[52],"multi-image,":[53],"video)":[55],"factors":[58],"(figural":[59],"environmental":[61],"scales,":[62],"visualization":[64],"orientation,":[66,127],"intrinsic":[67],"extrinsic,":[69],"static":[70],"dynamic).":[72],"Our":[73],"approach":[74],"curating":[76],"combines":[79],"bottom-up":[81],"survey":[82],"31":[84],"existing":[85],"datasets":[86],"top-down":[89],"strategy":[90],"drawing":[91],"upon":[92],"three":[93],"classification":[94],"systems":[95],"science,":[98],"which":[99],"prompt":[100],"us":[101],"design":[103],"two":[104],"novel":[105],"types":[106],"tasks":[108],"view-taking":[110],"dynamic":[112],"scenes.":[113],"Extensive":[114],"experiments":[115],"reveal":[116],"that":[117],"leading":[118],"models":[119],"fall":[120],"behind":[121],"human":[122],"experts":[123],"especially":[124],"fundamental":[129],"factor.":[131],"Moreover,":[132],"we":[133],"demonstrate":[134],"positive":[136],"correlation":[137],"between":[138],"model's":[140],"proficiency":[143],"its":[145],"performance":[146],"on":[147],"an":[148],"embodied":[149],"AI":[150],"task.":[151]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}