{"id":"https://openalex.org/W7147455679","doi":"https://doi.org/10.1109/cnml68938.2026.11452550","title":"DCFM: A Dynamic Cross-Modal Fusion Mechanism Based on Adaptive Semantic Gating for Visual Question Answering","display_name":"DCFM: A Dynamic Cross-Modal Fusion Mechanism Based on Adaptive Semantic Gating for Visual Question Answering","publication_year":2026,"publication_date":"2026-01-30","ids":{"openalex":"https://openalex.org/W7147455679","doi":"https://doi.org/10.1109/cnml68938.2026.11452550"},"language":null,"primary_location":{"id":"doi:10.1109/cnml68938.2026.11452550","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cnml68938.2026.11452550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Communication Networks and Machine Learning (CNML)","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/A5084733114","display_name":"Jiahui Dong","orcid":"https://orcid.org/0000-0002-0053-6193"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"id":"https://openalex.org/I4210111163","display_name":"Shanghai Open University","ror":"https://ror.org/027r7gj11","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210111163"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiahui Dong","raw_affiliation_strings":["Shanghai University,Shanghai Film Academy,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai University,Shanghai Film Academy,Shanghai,China","institution_ids":["https://openalex.org/I4210111163","https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103243870","display_name":"Yi Zhu","orcid":"https://orcid.org/0000-0003-0291-452X"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"id":"https://openalex.org/I4210111163","display_name":"Shanghai Open University","ror":"https://ror.org/027r7gj11","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210111163"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghua Zhu","raw_affiliation_strings":["Shanghai University,Shanghai Film Academy,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai University,Shanghai Film Academy,Shanghai,China","institution_ids":["https://openalex.org/I4210111163","https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112739418","display_name":"Mingfu Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"id":"https://openalex.org/I4210111163","display_name":"Shanghai Open University","ror":"https://ror.org/027r7gj11","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210111163"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingfu Luo","raw_affiliation_strings":["Shanghai University,Shanghai Film Academy,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai University,Shanghai Film Academy,Shanghai,China","institution_ids":["https://openalex.org/I4210111163","https://openalex.org/I113940042"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5116298294","display_name":"Haolu Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]},{"id":"https://openalex.org/I4210111163","display_name":"Shanghai Open University","ror":"https://ror.org/027r7gj11","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210111163"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haolu Yu","raw_affiliation_strings":["Shanghai University,Shanghai Film Academy,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai University,Shanghai Film Academy,Shanghai,China","institution_ids":["https://openalex.org/I4210111163","https://openalex.org/I113940042"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5084733114"],"corresponding_institution_ids":["https://openalex.org/I113940042","https://openalex.org/I4210111163"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.91659636,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1406","last_page":"1409"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9939000010490417,"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":0.9939000010490417,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0013000000035390258,"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":0.0008999999845400453,"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/question-answering","display_name":"Question answering","score":0.7943999767303467},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5374000072479248},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5228999853134155},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.43160000443458557},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4230000078678131},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4196999967098236},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.3783000111579895}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8321999907493591},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7943999767303467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6309999823570251},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5374000072479248},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5228999853134155},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4481000006198883},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.43160000443458557},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4230000078678131},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4196999967098236},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3783000111579895},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.3752000033855438},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3237999975681305},{"id":"https://openalex.org/C194544171","wikidata":"https://www.wikidata.org/wiki/Q21105679","display_name":"Gating","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.25679999589920044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cnml68938.2026.11452550","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cnml68938.2026.11452550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Communication Networks and Machine Learning (CNML)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6677772402763367,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2745461083","https://openalex.org/W2966683369","https://openalex.org/W2970231061"],"related_works":[],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Answering":[2],"(VQA)":[3],"represents":[4],"a":[5,13,63,100,113],"fundamental":[6],"challenge":[7],"in":[8,51,112,156],"multimodal":[9,48],"artificial":[10],"intelligence,":[11],"requiring":[12],"fine-grained":[14,101],"understanding":[15],"of":[16,132,152],"both":[17],"visual":[18,42,85,108],"scenes":[19],"and":[20,109,142,147],"natural":[21],"language":[22],"queries.":[23],"Existing":[24],"approaches,":[25],"particularly":[26],"those":[27],"relying":[28],"on":[29,93,119],"static":[30],"attention":[31,36],"mechanisms,":[32],"often":[33],"suffer":[34],"from":[35],"dispersion":[37],"when":[38],"dealing":[39],"with":[40],"complex":[41],"backgrounds":[43],"or":[44],"fail":[45],"to":[46,82,105],"align":[47,107],"features":[49],"effectively":[50],"high-dimensional":[52],"spaces.":[53],"To":[54],"address":[55],"these":[56],"persistent":[57],"challenges,":[58],"this":[59],"paper":[60],"proposes":[61],"DCFM,":[62],"novel":[64],"Transformer-based":[65],"Dynamic":[66],"Cross-Modal":[67],"Fusion":[68],"Mechanism.":[69],"We":[70],"introduce":[71],"an":[72,129],"Adaptive":[73],"Semantic":[74],"Gating":[75],"(ASG)":[76],"module":[77],"that":[78,88,125],"utilizes":[79],"question":[80],"embeddings":[81],"dynamically":[83],"filter":[84],"noise,":[86],"ensuring":[87],"the":[89,120,150],"model":[90],"strictly":[91],"focuses":[92],"question-":[94],"relevant":[95],"regions.":[96],"Furthermore,":[97],"we":[98],"incorporate":[99],"image-text":[102],"contrastive":[103],"loss":[104],"explicitly":[106],"textual":[110],"representations":[111],"shared":[114],"semantic":[115],"space.":[116],"Experimental":[117],"results":[118],"VQA":[121],"v2.0":[122],"dataset":[123],"demonstrate":[124],"our":[126,153],"method":[127],"achieves":[128],"overall":[130],"accuracy":[131],"77.85%,":[133],"significantly":[134],"outperforming":[135],"state-":[136],"of-the-art":[137],"models":[138],"such":[139],"as":[140],"BLIP":[141],"LXMERT.":[143],"Extensive":[144],"ablation":[145],"studies":[146],"visualizations":[148],"confirm":[149],"effectiveness":[151],"proposed":[154],"modules":[155],"enhancing":[157],"reasoning":[158],"capabilities.":[159]},"counts_by_year":[],"updated_date":"2026-04-02T13:53:19.096889","created_date":"2026-04-02T00:00:00"}