{"id":"https://openalex.org/W7162091916","doi":"https://doi.org/10.3390/jimaging12060219","title":"Visible\u2013Infrared Fusion Based on CNN and Deformable Transformer","display_name":"Visible\u2013Infrared Fusion Based on CNN and Deformable Transformer","publication_year":2026,"publication_date":"2026-05-22","ids":{"openalex":"https://openalex.org/W7162091916","doi":"https://doi.org/10.3390/jimaging12060219","pmid":"https://pubmed.ncbi.nlm.nih.gov/42346882"},"language":"en","primary_location":{"id":"doi:10.3390/jimaging12060219","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging12060219","pdf_url":null,"source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/jimaging12060219","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136781585","display_name":"Xiaoyi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I106645853","display_name":"Changchun University of Science and Technology","ror":"https://ror.org/007mntk44","country_code":"CN","type":"education","lineage":["https://openalex.org/I106645853"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210088164","display_name":"Changchun Institute of Optics, Fine Mechanics and Physics","ror":"https://ror.org/012rct222","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210088164"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyi Wang","raw_affiliation_strings":["College of Opto-Electronic Engineering, Changchun University of Science and Technology, Changchun 130022, China","State Key Laboratory of Dynamic Optical Imaging and Measurement, Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Opto-Electronic Engineering, Changchun University of Science and Technology, Changchun 130022, China","institution_ids":["https://openalex.org/I106645853"]},{"raw_affiliation_string":"State Key Laboratory of Dynamic Optical Imaging and Measurement, Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210088164"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081194493","display_name":"Xiansong Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I106645853","display_name":"Changchun University of Science and Technology","ror":"https://ror.org/007mntk44","country_code":"CN","type":"education","lineage":["https://openalex.org/I106645853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiansong Gu","raw_affiliation_strings":["College of Opto-Electronic Engineering, Changchun University of Science and Technology, Changchun 130022, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Opto-Electronic Engineering, Changchun University of Science and Technology, Changchun 130022, China","institution_ids":["https://openalex.org/I106645853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136756050","display_name":"Bin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210088164","display_name":"Changchun Institute of Optics, Fine Mechanics and Physics","ror":"https://ror.org/012rct222","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210088164"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Li","raw_affiliation_strings":["State Key Laboratory of Dynamic Optical Imaging and Measurement, Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Dynamic Optical Imaging and Measurement, Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210088164"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136759917","display_name":"Mingqiang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210088164","display_name":"Changchun Institute of Optics, Fine Mechanics and Physics","ror":"https://ror.org/012rct222","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210088164"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingqiang Zhang","raw_affiliation_strings":["State Key Laboratory of Dynamic Optical Imaging and Measurement, Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Dynamic Optical Imaging and Measurement, Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210088164"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136779586","display_name":"Panpan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I106645853","display_name":"Changchun University of Science and Technology","ror":"https://ror.org/007mntk44","country_code":"CN","type":"education","lineage":["https://openalex.org/I106645853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Panpan Yang","raw_affiliation_strings":["College of Opto-Electronic Engineering, Changchun University of Science and Technology, Changchun 130022, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Opto-Electronic Engineering, Changchun University of Science and Technology, Changchun 130022, China","institution_ids":["https://openalex.org/I106645853"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136774075","display_name":"Qiang Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I106645853","display_name":"Changchun University of Science and Technology","ror":"https://ror.org/007mntk44","country_code":"CN","type":"education","lineage":["https://openalex.org/I106645853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Fu","raw_affiliation_strings":["College of Opto-Electronic Engineering, Changchun University of Science and Technology, Changchun 130022, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Opto-Electronic Engineering, Changchun University of Science and Technology, Changchun 130022, China","institution_ids":["https://openalex.org/I106645853"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.62570271,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":"6","first_page":"219","last_page":"219"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.6230000257492065,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.6230000257492065,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.07530000060796738,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11659","display_name":"Advanced Image Fusion Techniques","score":0.05849999934434891,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6599000096321106},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6144000291824341},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5449000000953674},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.491100013256073},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4659000039100647},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4368000030517578},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3831000030040741},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.3671000003814697}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8845000267028809},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.675599992275238},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6599000096321106},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6144000291824341},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5449000000953674},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.491100013256073},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4659000039100647},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4368000030517578},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4115999937057495},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3831000030040741},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3179999887943268},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.30379998683929443},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.28450000286102295},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2583000063896179},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/jimaging12060219","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging12060219","pdf_url":null,"source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},{"id":"pmid:42346882","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42346882","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of imaging","raw_type":"Journal Article"},{"id":"pmh:oai:doaj.org/article:b8ca43bc54b2470ab2974d56e199017d","is_oa":false,"landing_page_url":"https://doaj.org/article/b8ca43bc54b2470ab2974d56e199017d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Imaging, Vol 12, Iss 6, p 219 (2026)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13302084","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13302084/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Imaging","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/jimaging12060219","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging12060219","pdf_url":null,"source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1138809020","display_name":null,"funder_award_id":"No. U2341226","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7436620157","display_name":null,"funder_award_id":"No. 62127813","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2330906727","https://openalex.org/W2757470902","https://openalex.org/W2798987894","https://openalex.org/W2809795042","https://openalex.org/W2963037989","https://openalex.org/W2963787388","https://openalex.org/W3027780899","https://openalex.org/W3046194589","https://openalex.org/W3107054677","https://openalex.org/W3110670586","https://openalex.org/W3181367324","https://openalex.org/W3203284270","https://openalex.org/W3206748188","https://openalex.org/W3213472242","https://openalex.org/W4206713196","https://openalex.org/W4220893768","https://openalex.org/W4281898289","https://openalex.org/W4283732315","https://openalex.org/W4285407753","https://openalex.org/W4312594135","https://openalex.org/W4320484932","https://openalex.org/W4320802741","https://openalex.org/W4376126900","https://openalex.org/W4382119107","https://openalex.org/W4386498911","https://openalex.org/W4386748204","https://openalex.org/W4386938118","https://openalex.org/W4387903826","https://openalex.org/W4389319234","https://openalex.org/W4390277127","https://openalex.org/W4390787329","https://openalex.org/W4391468033","https://openalex.org/W4399939098","https://openalex.org/W4400090301","https://openalex.org/W4401733781","https://openalex.org/W4402125080","https://openalex.org/W4402576334","https://openalex.org/W4402979802","https://openalex.org/W4404099423","https://openalex.org/W4404936032","https://openalex.org/W4416582733"],"related_works":[],"abstract_inverted_index":{"To":[0],"address":[1],"the":[2,35,44,54,71,98,107,120,124,133,139,143,155,163],"limitations":[3],"of":[4,37,46,56,130,159],"traditional":[5],"methods":[6,109,126],"in":[7,39,48,76,110,162],"feature":[8,41],"extraction":[9],"and":[10,29,43,59,84,94,136,148,157],"multi-modal":[11],"information":[12],"fusion,":[13],"this":[14],"paper":[15],"proposes":[16],"an":[17,128],"infrared-visible":[18],"image":[19],"object":[20,74],"detection":[21,75],"architecture":[22],"that":[23,97],"integrates":[24],"Convolutional":[25],"Neural":[26],"Networks":[27],"(CNNs)":[28],"Deformable":[30],"Transformers.":[31],"This":[32],"method":[33,100,118],"leverages":[34],"advantages":[36],"CNN":[38],"local":[40],"modeling":[42],"capabilities":[45],"Transformer":[47],"capturing":[49],"global":[50],"contextual":[51],"information,":[52],"facilitating":[53],"fusion":[55],"semantic":[57],"consistency":[58],"structural":[60],"details":[61],"across":[62],"modalities.":[63],"By":[64],"introducing":[65],"a":[66],"detection-aware":[67],"multi-task":[68],"optimization":[69],"mechanism,":[70],"model":[72],"improves":[73],"challenging":[77],"scenarios":[78],"such":[79,113],"as":[80,114],"low-light":[81],"conditions,":[82],"occlusion,":[83],"complex":[85,165],"backgrounds.":[86],"Experiments":[87],"on":[88,132,138],"multiple":[89],"standard":[90],"datasets,":[91],"including":[92],"M3FD":[93,134],"LLVIP,":[95],"indicate":[96],"proposed":[99],"achieves":[101],"competitive":[102],"or":[103],"better":[104],"performance":[105],"than":[106],"compared":[108],"key":[111],"metrics":[112],"mAP.":[115],"Specifically,":[116],"our":[117,160],"obtains":[119],"best":[121],"mAP50":[122,129],"among":[123],"evaluated":[125,164],"with":[127],"74.2%":[131],"dataset":[135],"98.6%":[137],"LLVIP":[140],"dataset,":[141],"surpassing":[142],"second-best":[144],"PIAFusion":[145],"by":[146],"4.3%":[147],"2.5%":[149],"respectively.":[150],"These":[151],"quantitative":[152],"results":[153],"support":[154],"practicality":[156],"effectiveness":[158],"approach":[161],"environments.":[166]},"counts_by_year":[],"updated_date":"2026-07-27T08:26:11.824852","created_date":"2026-05-23T00:00:00"}