{"id":"https://openalex.org/W7164835379","doi":"https://doi.org/10.1145/3805622.3810830","title":"SKG-VLA: Scene Knowledge Graph Priors for Structured Scene Semantics and Multimodal Reasoning for Decision Making","display_name":"SKG-VLA: Scene Knowledge Graph Priors for Structured Scene Semantics and Multimodal Reasoning for Decision Making","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164835379","doi":"https://doi.org/10.1145/3805622.3810830"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810830","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810830","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 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810830","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057923247","display_name":"Zeyu Li","orcid":"https://orcid.org/0000-0003-0335-2469"},"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":"Zeyu Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0335-2469","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100440301","display_name":"Lei Li","orcid":"https://orcid.org/0000-0002-3204-6527"},"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":"Lei Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3204-6527","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94874978,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1045","last_page":"1054"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.43779999017715454,"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"}},"topics":[{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.43779999017715454,"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/T10028","display_name":"Topic Modeling","score":0.19760000705718994,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.07729999721050262,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/complaint","display_name":"Complaint","score":0.925599992275238},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.45969998836517334},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4487999975681305},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.37529999017715454},{"id":"https://openalex.org/keywords/evidential-reasoning-approach","display_name":"Evidential reasoning approach","score":0.3662000000476837}],"concepts":[{"id":"https://openalex.org/C2780838233","wikidata":"https://www.wikidata.org/wiki/Q836925","display_name":"Complaint","level":2,"score":0.925599992275238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6952999830245972},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5663999915122986},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.45969998836517334},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4487999975681305},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.37529999017715454},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3700000047683716},{"id":"https://openalex.org/C156201811","wikidata":"https://www.wikidata.org/wiki/Q5418360","display_name":"Evidential reasoning approach","level":4,"score":0.3662000000476837},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3555999994277954},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35010001063346863},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C59594135","wikidata":"https://www.wikidata.org/wiki/Q5249242","display_name":"Decision model","level":2,"score":0.273499995470047}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810830","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810830","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 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810830","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810830","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 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7639261484146118,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2953356739","https://openalex.org/W2963748384","https://openalex.org/W2964006684","https://openalex.org/W2979382951","https://openalex.org/W2988326850","https://openalex.org/W2998385486","https://openalex.org/W3004268082","https://openalex.org/W3120043490","https://openalex.org/W3134200545","https://openalex.org/W3151929433","https://openalex.org/W3156555225","https://openalex.org/W4304013646","https://openalex.org/W4312233877","https://openalex.org/W4389520779","https://openalex.org/W4402671983","https://openalex.org/W4402716477","https://openalex.org/W4408228023","https://openalex.org/W4412945260","https://openalex.org/W4412945734","https://openalex.org/W4413147844","https://openalex.org/W4415797504","https://openalex.org/W4415800738","https://openalex.org/W7133193597","https://openalex.org/W7133196460","https://openalex.org/W7133214447","https://openalex.org/W7133224126"],"related_works":[],"abstract_inverted_index":{"Decision":[0],"making":[1],"in":[2],"large-scale":[3,128],"complaint":[4,13,24,56,70,85,113,129,171],"handling":[5],"systems":[6,26],"increasingly":[7],"relies":[8],"on":[9,103],"heterogeneous":[10],"evidence,":[11],"including":[12],"narratives,":[14],"screenshots,":[15],"order":[16],"metadata,":[17],"historical":[18],"interactions,":[19],"and":[20,44,72,95,121,135,150,176],"platform":[21],"policies.":[22],"Existing":[23],"understanding":[25],"mainly":[27],"perform":[28],"shallow":[29],"classification":[30],"or":[31],"template":[32],"matching":[33],"over":[34],"isolated":[35],"modalities,":[36],"while":[37],"underutilizing":[38],"explicit":[39],"scene":[40,71,114,130,156],"structure,":[41],"rule":[42],"knowledge,":[43],"cross-evidence":[45],"dependencies.":[46],"To":[47],"address":[48],"this":[49],"limitation,":[50],"we":[51,105,140],"present":[52],"SKG-VLA":[53,166],"for":[54],"multimodal":[55,136,152,160],"decision":[57,122,161,172],"making.":[58],"The":[59],"core":[60],"idea":[61],"is":[62],"to":[63],"model":[64],"each":[65],"case":[66],"as":[67],"a":[68,78,99,107,127,142,159],"structured":[69,155],"represent":[73],"its":[74],"decision-relevant":[75],"semantics":[76],"with":[77,132],"Scene":[79],"Knowledge":[80],"Graph":[81],"(SKG),":[82],"which":[83],"organizes":[84],"entities,":[86],"evidence":[87],"items,":[88],"policy":[89],"clauses,":[90],"temporal":[91],"events,":[92],"transactional":[93],"states,":[94],"action-relevant":[96],"relations":[97],"into":[98,158],"unified":[100],"graph.":[101],"Based":[102],"SKG,":[104],"build":[106],"data":[108],"synthesis":[109],"pipeline":[110],"that":[111,165],"generates":[112],"descriptions,":[115],"rule-consistent":[116],"graph":[117],"generalizations,":[118],"question\u2013answer":[119],"supervision,":[120],"recommendations.":[123],"We":[124],"further":[125],"construct":[126],"dataset":[131],"both":[133],"text-only":[134],"in-domain":[137],"benchmarks.":[138],"Finally,":[139],"adopt":[141],"three-stage":[143],"training":[144],"strategy\u2014domain-adaptive":[145],"pre-training,":[146],"task-oriented":[147],"instruction":[148],"fine-tuning,":[149],"end-to-end":[151],"alignment\u2014to":[153],"inject":[154],"priors":[157],"model.":[162],"Experiments":[163],"show":[164],"consistently":[167],"improves":[168],"policy-grounded":[169],"reasoning,":[170],"accuracy,":[173],"long-tail":[174],"generalization,":[175],"robustness":[177],"under":[178],"incomplete":[179],"evidence.":[180]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}