{"id":"https://openalex.org/W7138304778","doi":"https://doi.org/10.1609/aaai.v40i9.37677","title":"View-on-Graph: Zero-Shot 3D Visual Grounding via Vision-Language Reasoning on Scene Graphs","display_name":"View-on-Graph: Zero-Shot 3D Visual Grounding via Vision-Language Reasoning on Scene Graphs","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138304778","doi":"https://doi.org/10.1609/aaai.v40i9.37677"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i9.37677","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37677","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i9.37677","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129726183","display_name":"Yuanyuan Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yuanyuan Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129722563","display_name":"Haiyang Mei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haiyang Mei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038927310","display_name":"Dongyang Zhan","orcid":"https://orcid.org/0000-0003-1981-5878"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongyang Zhan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129641136","display_name":"Jiayue Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiayue Zhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129653965","display_name":"Dongsheng Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongsheng Zhou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129746731","display_name":"Bo Dong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Dong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129661812","display_name":"Xin Yu Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Yang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5129726183"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.66517524,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"9","first_page":"7386","last_page":"7394"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.986299991607666,"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":0.986299991607666,"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":0.002400000113993883,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0012000000569969416,"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/exploit","display_name":"Exploit","score":0.7789999842643738},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7319999933242798},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.7293999791145325},{"id":"https://openalex.org/keywords/structuring","display_name":"Structuring","score":0.5598999857902527},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5478000044822693},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.546500027179718},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.49050000309944153},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.47429999709129333},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4672999978065491}],"concepts":[{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7789999842643738},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7498000264167786},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7319999933242798},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.7293999791145325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6532999873161316},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.5598999857902527},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5478000044822693},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.546500027179718},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5320000052452087},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.49050000309944153},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.47429999709129333},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4672999978065491},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.3849000036716461},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33169999718666077},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.303600013256073},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.3034000098705292},{"id":"https://openalex.org/C197654239","wikidata":"https://www.wikidata.org/wiki/Q7430757","display_name":"Scene statistics","level":3,"score":0.3012999892234802},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2678999900817871},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C15759828","wikidata":"https://www.wikidata.org/wiki/Q165074","display_name":"Parallax","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.25679999589920044},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.25459998846054077},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i9.37677","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37677","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i9.37677","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37677","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"3D":[0,7,22,88,154],"visual":[1,55,172],"grounding":[2],"(3DVG)":[3],"identifies":[4],"objects":[5],"in":[6],"scenes":[8],"from":[9],"language":[10],"descriptions.":[11],"Existing":[12],"zero-shot":[13,207,219],"approaches":[14],"leverage":[15],"2D":[16],"vision\u2013language":[17],"models":[18],"(VLMs)":[19],"by":[20,152,182],"converting":[21],"spatial":[23],"information":[24],"(SI)":[25],"into":[26,90,119,156],"forms":[27],"amenable":[28],"to":[29,61,69,96,129],"VLM":[30,49,60,81,95,128,168],"processing,":[31],"typically":[32],"as":[33,37,131,140,213],"composite":[34],"inputs":[35],"such":[36],"specified-view":[38],"renderings":[39],"or":[40],"video":[41],"sequences":[42],"with":[43,109,169],"overlaid":[44],"object":[45],"markers.":[46],"However,":[47],"this":[48,75,107],"\u2295":[50],"SI":[51,83,89],"paradigm":[52,84,108],"yields":[53],"entangled":[54,171],"representations":[56],"that":[57,85,135,203],"compel":[58],"the":[59,87,94,117,127,143,167,176,188],"process":[62],"entire":[63],"cluttered":[64],"cues,":[65],"making":[66],"it":[67,101,141,174,191],"hard":[68],"exploit":[70],"spatial\u2013semantic":[71],"relationships":[72],"effectively.":[73],"In":[74],"work,":[76],"we":[77],"propose":[78],"a":[79,91,110,120,157,214],"new":[80],"\u2297":[82],"externalizes":[86],"form":[92],"enabling":[93],"incrementally":[97],"retrieve":[98],"only":[99],"what":[100],"needs":[102],"during":[103],"reasoning.":[104],"We":[105],"instantiate":[106],"novel":[111],"View-on-Graph":[112],"(VoG)":[113],"method,":[114],"which":[115],"organizes":[116],"scene":[118,123,162,189,211],"multi-modal,":[121],"multi-layer":[122],"graph":[124,163],"and":[125,159,180,185],"allows":[126],"operate":[130],"an":[132],"active":[133],"agent":[134],"selectively":[136],"accesses":[137],"necessary":[138],"cues":[139],"traverses":[142],"scene.":[144],"This":[145],"design":[146],"offers":[147],"two":[148],"intrinsic":[149],"advantages:":[150],"(i)":[151],"structuring":[153],"context":[155],"spatially":[158],"semantically":[160],"coherent":[161],"rather":[164],"than":[165],"confounding":[166],"densely":[170],"inputs,":[173],"lowers":[175],"VLM's":[177],"reasoning":[178,186],"difficulty;":[179],"(ii)":[181],"actively":[183],"exploring":[184],"over":[187],"graph,":[190],"naturally":[192],"produces":[193],"transparent,":[194],"step-by-step":[195],"traces":[196],"for":[197,217],"interpretable":[198],"3DVG.":[199,220],"Extensive":[200],"experiments":[201],"show":[202],"VoG":[204],"achieves":[205],"state-of-the-art":[206],"performance,":[208],"establishing":[209],"structured":[210],"exploration":[212],"promising":[215],"strategy":[216],"advancing":[218]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}