{"id":"https://openalex.org/W7118531514","doi":"https://doi.org/10.1109/indin64977.2025.11279055","title":"GTNet: A Graph-Based Transformer with Cross-Modal Attention Mechanism","display_name":"GTNet: A Graph-Based Transformer with Cross-Modal Attention Mechanism","publication_year":2025,"publication_date":"2025-07-12","ids":{"openalex":"https://openalex.org/W7118531514","doi":"https://doi.org/10.1109/indin64977.2025.11279055"},"language":null,"primary_location":{"id":"doi:10.1109/indin64977.2025.11279055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/indin64977.2025.11279055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 23rd International Conference on Industrial Informatics (INDIN)","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/A5122000963","display_name":"Qi Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qi Yao","raw_affiliation_strings":["Beijing University of Technology,School of Information Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,School of Information Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051517054","display_name":"Hongyan Yang","orcid":"https://orcid.org/0000-0003-4755-1857"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyan Yang","raw_affiliation_strings":["Beijing University of Technology,School of Information Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,School of Information Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018610556","display_name":"Huisheng Ma","orcid":"https://orcid.org/0009-0001-8256-8163"},"institutions":[{"id":"https://openalex.org/I2800372957","display_name":"China Electronics Technology Group Corporation","ror":"https://ror.org/0098hst83","country_code":"CN","type":"company","lineage":["https://openalex.org/I2800372957"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huisheng Ma","raw_affiliation_strings":["The 15th Research Institute of China Electronics Technology Group Corporation,Beijing,China"],"affiliations":[{"raw_affiliation_string":"The 15th Research Institute of China Electronics Technology Group Corporation,Beijing,China","institution_ids":["https://openalex.org/I2800372957"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5122000963"],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.65792547,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9495000243186951,"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":0.9495000243186951,"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":0.016100000590085983,"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":0.011699999682605267,"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/hypergraph","display_name":"Hypergraph","score":0.6165000200271606},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5849999785423279},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5751000046730042},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49889999628067017},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4887000024318695},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.4722999930381775},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.3797000050544739}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7224000096321106},{"id":"https://openalex.org/C2781221856","wikidata":"https://www.wikidata.org/wiki/Q840247","display_name":"Hypergraph","level":2,"score":0.6165000200271606},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5849999785423279},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5830000042915344},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5751000046730042},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49889999628067017},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4887000024318695},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4722999930381775},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.3797000050544739},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3521000146865845},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33480000495910645},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28040000796318054},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.2745000123977661},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.26930001378059387},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/indin64977.2025.11279055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/indin64977.2025.11279055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 23rd International Conference on Industrial Informatics (INDIN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321793","display_name":"Beijing Municipal Education Commission","ror":"https://ror.org/04bpn6s66"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2767290858","https://openalex.org/W2963191264","https://openalex.org/W2963518342","https://openalex.org/W2963877604","https://openalex.org/W2964247799","https://openalex.org/W2966683369","https://openalex.org/W2979404943","https://openalex.org/W2998008435","https://openalex.org/W3015821169","https://openalex.org/W3040450405","https://openalex.org/W4312971868","https://openalex.org/W4392104271","https://openalex.org/W4399158158","https://openalex.org/W4401011972"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,29,78,91,103,119,149,154,159,171,175,182,187],"rapid":[2],"development":[3],"of":[4,33,50,95,156],"deep":[5],"learning,":[6],"traditional":[7],"neural":[8,52,126],"networks":[9],"have":[10],"made":[11],"significant":[12,38],"progress":[13],"in":[14,23,115,145,174],"single":[15],"modal":[16,121],"tasks":[17],"such":[18],"as":[19],"image":[20,104],"recognition.":[21],"However,":[22],"Visual":[24],"Question":[25],"Answering":[26],"(VQA)":[27],"tasks,":[28],"complex":[30,198],"interaction":[31],"relationships":[32],"multimodal":[34],"data":[35],"still":[36],"pose":[37],"challenges.":[39],"To":[40],"address":[41],"this":[42,44,191],"issue,":[43],"paper":[45],"proposes":[46],"a":[47,71,85,130],"simplified":[48],"model":[49,77,160],"graph":[51,87,125,176],"network":[53,127],"based":[54,73],"on":[55,181],"combinatorial":[56],"attention":[57,74,132,157],"mechanism":[58,75,133],"(GTNet)":[59],"to":[60,76,109,117,136,147,197],"reduce":[61],"computational":[62,93,203],"complexity":[63],"and":[64,82,106,141,186],"improve":[65],"inference":[66],"efficiency.":[67],"This":[68],"method":[69,192],"adopts":[70],"Transformer":[72],"relationship":[79],"between":[80],"images":[81],"text":[83,107],"using":[84],"dynamic":[86,113],"structure,":[88],"thereby":[89],"avoiding":[90],"high":[92],"cost":[94],"Hypergraph":[96],"Neural":[97],"Networks":[98],"(HGNN).":[99],"Firstly,":[100],"we":[101],"map":[102],"scene":[105],"problem":[108],"an":[110],"initial":[111],"weighted":[112],"graph,":[114],"order":[116,146],"capture":[118],"inter":[120],"correlation":[122],"information":[123,167],"through":[124],"(GNN).":[128],"Subsequently,":[129],"combined":[131],"is":[134],"introduced":[135],"adaptively":[137],"process":[138],"each":[139],"modality":[140],"its":[142],"interactive":[143],"features,":[144],"enhance":[148],"model's":[150],"reasoning":[151],"ability.":[152],"Under":[153],"guidance":[155],"mechanism,":[158],"can":[161,193],"effectively":[162],"filter":[163],"out":[164],"key":[165],"semantic":[166],"by":[168],"dynamically":[169],"adjusting":[170],"edge":[172],"weights":[173],"structure.":[177],"We":[178],"conducted":[179],"experiments":[180],"public":[183],"VQA":[184],"dataset":[185],"results":[188],"showed":[189],"that":[190],"maintain":[194],"similar":[195],"performance":[196],"hypergraph":[199],"methods":[200],"while":[201],"reducing":[202],"costs.":[204]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-08T00:00:00"}