{"id":"https://openalex.org/W7140460390","doi":"https://doi.org/10.1109/aixvr67263.2026.00048","title":"Frame-First AR: Egocentric Scene Graphs with VLM-Augmented Semantics and Spatial Reasoning","display_name":"Frame-First AR: Egocentric Scene Graphs with VLM-Augmented Semantics and Spatial Reasoning","publication_year":2026,"publication_date":"2026-01-26","ids":{"openalex":"https://openalex.org/W7140460390","doi":"https://doi.org/10.1109/aixvr67263.2026.00048"},"language":null,"primary_location":{"id":"doi:10.1109/aixvr67263.2026.00048","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aixvr67263.2026.00048","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality (AIxVR)","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/A5120678049","display_name":"Faraz Badali Naghadeh","orcid":"https://orcid.org/0000-0003-0262-5699"},"institutions":[{"id":"https://openalex.org/I134235054","display_name":"Sabanc\u0131 \u00dcniversitesi","ror":"https://ror.org/049asqa32","country_code":"TR","type":"education","lineage":["https://openalex.org/I134235054"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Faraz Badali Naghadeh","raw_affiliation_strings":["Sabanci University BAVLAB, Sabanci University,Istanbul,Türkiye"],"affiliations":[{"raw_affiliation_string":"Sabanci University BAVLAB, Sabanci University,Istanbul,Türkiye","institution_ids":["https://openalex.org/I134235054"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130691300","display_name":"Selim Balcisoy","orcid":null},"institutions":[{"id":"https://openalex.org/I134235054","display_name":"Sabanc\u0131 \u00dcniversitesi","ror":"https://ror.org/049asqa32","country_code":"TR","type":"education","lineage":["https://openalex.org/I134235054"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Selim Balcisoy","raw_affiliation_strings":["Sabanci University BAVLAB, Sabanci University,Istanbul,Türkiye"],"affiliations":[{"raw_affiliation_string":"Sabanci University BAVLAB, Sabanci University,Istanbul,Türkiye","institution_ids":["https://openalex.org/I134235054"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5120678049"],"corresponding_institution_ids":["https://openalex.org/I134235054"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93823886,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"276","last_page":"280"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8873000144958496,"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":0.8873000144958496,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.03530000150203705,"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"}},{"id":"https://openalex.org/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.015799999237060547,"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/semantics","display_name":"Semantics (computer science)","score":0.6033999919891357},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.365200012922287},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.3619999885559082},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3165000081062317},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3125999867916107},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.2743000090122223}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6154000163078308},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6033999919891357},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6011000275611877},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4185999929904938},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.365200012922287},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.3619999885559082},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32829999923706055},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aixvr67263.2026.00048","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aixvr67263.2026.00048","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality (AIxVR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.48001420497894287}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2889396891","https://openalex.org/W3018353706","https://openalex.org/W3039925688","https://openalex.org/W3159619744","https://openalex.org/W3176840310","https://openalex.org/W4225595226","https://openalex.org/W4311304680","https://openalex.org/W4386076325","https://openalex.org/W4386352770","https://openalex.org/W4396827142","https://openalex.org/W4396833067","https://openalex.org/W4402615802","https://openalex.org/W4402716288","https://openalex.org/W4402727108","https://openalex.org/W4406266242","https://openalex.org/W4407015737","https://openalex.org/W4407781755","https://openalex.org/W4409258837","https://openalex.org/W4409761465","https://openalex.org/W4413156058","https://openalex.org/W4415800665","https://openalex.org/W4416036208"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3,36],"opportunistic,":[4],"frame-first":[5],"augmented":[6],"reality":[7],"(AR)":[8],"pipeline":[9,72],"for":[10],"first-responder":[11],"support":[12],"that":[13,99,117],"departs":[14],"from":[15,82],"scan-first":[16,69],"approaches.":[17],"The":[18],"system":[19],"anchors":[20],"real-time":[21],"object":[22,65],"detections":[23],"into":[24],"world":[25],"coordinates":[26],"via":[27],"the":[28],"Meta":[29],"Quest":[30],"3":[31],"depth":[32],"API":[33],"and":[34,42,61,92,95,106],"maintains":[35],"egocentric":[37],"scene":[38],"graph":[39],"encoding":[40],"human\u2013object":[41],"object\u2013object":[43],"relations.":[44],"A":[45],"multimodal":[46],"vision\u2013language":[47],"model":[48],"(VLM)":[49],"operates":[50],"over":[51],"this":[52],"structured":[53],"snapshot":[54],"to":[55,110,126],"infer":[56],"geometric":[57],"relations,":[58],"functional":[59],"groupings,":[60],"semantic":[62],"context":[63],"beyond":[64],"detection":[66],"alone.":[67],"Unlike":[68],"designs,":[70],"our":[71],"avoids":[73],"long":[74],"initialization":[75],"delays":[76],"by":[77],"incrementally":[78],"building":[79],"spatial":[80,104],"awareness":[81],"partial":[83],"observations":[84],"while":[85],"leveraging":[86],"schematic":[87],"priors.":[88],"We":[89],"report":[90],"stage-wise":[91],"end-to-end":[93],"latency,":[94],"comparative":[96],"evaluations":[97],"showing":[98],"geometry-augmented":[100],"VLM":[101],"reasoning":[102],"improves":[103],"accuracy":[105],"relational":[107],"reliability":[108],"relative":[109],"VLM-only":[111],"baselines.":[112],"Together,":[113],"these":[114],"findings":[115],"demonstrate":[116],"grounding":[118],"semantics":[119],"in":[120,131],"geometry":[121],"offers":[122],"a":[123],"practical":[124],"path":[125],"responsive,":[127],"low-latency":[128],"AR":[129],"assistance":[130],"safety-critical":[132],"scenarios.":[133]},"counts_by_year":[],"updated_date":"2026-03-28T06:11:35.319607","created_date":"2026-03-27T00:00:00"}