{"id":"https://openalex.org/W7123363417","doi":"https://doi.org/10.1109/access.2026.3653660","title":"Contextual Fusion Strategies for Multimodal GNN-Based Reasoning: Performance and Computational Trade-Offs","display_name":"Contextual Fusion Strategies for Multimodal GNN-Based Reasoning: Performance and Computational Trade-Offs","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7123363417","doi":"https://doi.org/10.1109/access.2026.3653660"},"language":null,"primary_location":{"id":"doi:10.1109/access.2026.3653660","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3653660","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3653660","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006363230","display_name":"Sanggeon Yun","orcid":"https://orcid.org/0000-0002-0488-9666"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sanggeon Yun","raw_affiliation_strings":["Department of Computer Science, University of California, Irvine, Irvine, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069537375","display_name":"Ryozo Masukawa","orcid":null},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryozo Masukawa","raw_affiliation_strings":["Department of Computer Science, University of California, Irvine, Irvine, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122851584","display_name":"Raheeb Hassan","orcid":null},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raheeb Hassan","raw_affiliation_strings":["Department of Computer Science, University of California, Irvine, Irvine, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113270403","display_name":"Minhyoung Na","orcid":null},"institutions":[{"id":"https://openalex.org/I110273157","display_name":"Kookmin University","ror":"https://ror.org/0049erg63","country_code":"KR","type":"education","lineage":["https://openalex.org/I110273157"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minhyoung Na","raw_affiliation_strings":["Department of Computer Science, Kookmin University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Kookmin University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I110273157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046141850","display_name":"Mohsen Imani","orcid":"https://orcid.org/0000-0002-7934-0301"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohsen Imani","raw_affiliation_strings":["Department of Computer Science, University of California, Irvine, Irvine, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5006363230"],"corresponding_institution_ids":["https://openalex.org/I204250578"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17819521,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"13702","last_page":"13711"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.27790001034736633,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.27790001034736633,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.1525000035762787,"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":0.10189999639987946,"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/sensor-fusion","display_name":"Sensor fusion","score":0.539900004863739},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4943000078201294},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4659000039100647},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.46480000019073486},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.46470001339912415},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.427700012922287},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4047999978065491},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.39329999685287476},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.38940000534057617},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.3781999945640564}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.820900022983551},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.539900004863739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5202999711036682},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.511900007724762},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4943000078201294},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4659000039100647},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.46480000019073486},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.46470001339912415},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.427700012922287},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4047999978065491},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.39329999685287476},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.38940000534057617},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C2777480716","wikidata":"https://www.wikidata.org/wiki/Q23582796","display_name":"Resource consumption","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3303999900817871},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C127964446","wikidata":"https://www.wikidata.org/wiki/Q1092142","display_name":"Computational resource","level":3,"score":0.3158000111579895},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3111000061035156},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.31060001254081726},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C2982962833","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information fusion","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/access.2026.3653660","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3653660","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3653660","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3653660","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8224704265594482,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2053101950","https://openalex.org/W2619383789","https://openalex.org/W2767290858","https://openalex.org/W2907492528","https://openalex.org/W2960833983","https://openalex.org/W2964015378","https://openalex.org/W2965857891","https://openalex.org/W3003265726","https://openalex.org/W3012871709","https://openalex.org/W3089682612","https://openalex.org/W3092072718","https://openalex.org/W3111409722","https://openalex.org/W3152893301","https://openalex.org/W4285733177","https://openalex.org/W4386071707","https://openalex.org/W4399854644","https://openalex.org/W4402917098","https://openalex.org/W4410582747","https://openalex.org/W4410596019"],"related_works":[],"abstract_inverted_index":{"The":[0],"integration":[1],"of":[2,49,173],"multimodal":[3,80,193],"data":[4],"is":[5],"essential":[6],"for":[7,79,190],"mission-specific":[8],"tasks":[9],"requiring":[10],"comprehensive":[11],"reasoning":[12,88,195],"across":[13,121],"diverse":[14],"information":[15],"sources,":[16],"especially":[17],"in":[18,32,164,209],"resource-constrained":[19],"environments.":[20],"MissionGNN,":[21],"a":[22,53,85,134,161,204],"hierarchical":[23,86],"Graph":[24],"Neural":[25],"Network":[26],"(GNN)":[27],"framework,":[28],"has":[29],"shown":[30],"promise":[31],"deploying":[33],"complex":[34],"task":[35],"models":[36],"on":[37,114],"edge":[38],"devices":[39],"by":[40,145],"leveraging":[41],"knowledge":[42,75,105,131,151],"graphs":[43],"(KGs).":[44],"However,":[45],"optimizing":[46],"the":[47,60,115,170],"fusion":[48,77,132,168,211],"different":[50],"modalities":[51],"remains":[52],"key":[54],"challenge,":[55],"as":[56],"it":[57,180],"significantly":[58],"impacts":[59],"trade-off":[61],"between":[62],"computational":[63,123,165],"efficiency":[64,216],"and":[65,96,127,217,224],"performance":[66],"accuracy.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71],"propose":[72],"three":[73],"novel":[74],"graph-centric":[76],"strategies":[78,212],"video":[81],"anomaly":[82],"detection":[83],"within":[84],"GNN-based":[87,194],"framework\u2014<italic":[89],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[90,98,103],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">KG-based":[91],"early":[92],"fusion,":[93,152],"late":[94],"fusion,</i>":[95],"<italic":[97,102],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">reasoning":[99],"fusion</i>\u2014along":[100],"with":[101,160],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">modality-aware":[104],"graph":[106],"generation</i>":[107],"to":[108,206,221],"enhance":[109],"modality-specific":[110],"reasoning.":[111],"Extensive":[112],"experiments":[113],"XD-Violence":[116],"dataset":[117],"evaluate":[118],"their":[119],"trade-offs":[120],"performance,":[122,178],"cost,":[124],"energy":[125,143,215],"consumption,":[126],"LLM-basedKGgeneration":[128],"cost.":[129],"Early":[130],"offers":[133,203],"balanced":[135],"solution,":[136],"achieving":[137],"significant":[138],"accuracy":[139,159,172],"improvements":[140],"while":[141],"reducing":[142],"consumption":[144],"over":[146],"70%":[147],"per":[148],"frame.":[149],"Late":[150],"using":[153],"half-sized":[154],"modality-aware":[155],"KGs,":[156],"further":[157],"improves":[158],"modest":[162],"increase":[163],"costs.":[166],"Reasoning":[167],"achieves":[169],"highest":[171],"72.93%":[174],"mAP,":[175],"demonstrating":[176],"state-of-the-art":[177],"though":[179],"incurs":[181],"higher":[182],"resource":[183,226],"usage.":[184],"These":[185],"results":[186],"provide":[187],"valuable":[188],"insights":[189],"designing":[191],"efficient":[192],"systems.":[196],"By":[197],"exploring":[198],"these":[199],"trade-offs,":[200],"our":[201],"work":[202],"framework":[205],"guide":[207],"practitioners":[208],"selecting":[210],"that":[213],"balance":[214],"task-specific":[218],"accuracy,":[219],"tailored":[220],"mission-critical":[222],"applications":[223],"varying":[225],"constraints.":[227]},"counts_by_year":[],"updated_date":"2026-02-02T03:55:41.653505","created_date":"2026-01-14T00:00:00"}