{"id":"https://openalex.org/W7225611656","doi":"https://doi.org/10.3390/jimaging12110563","title":"YOLO-GRAT: A Gated Residual Cross-Modal Fusion Network with Adaptive Triplet Attention for Visible\u2013Infrared Object Detection","display_name":"YOLO-GRAT: A Gated Residual Cross-Modal Fusion Network with Adaptive Triplet Attention for Visible\u2013Infrared Object Detection","publication_year":2026,"publication_date":"2026-11-09","ids":{"openalex":"https://openalex.org/W7225611656","doi":"https://doi.org/10.3390/jimaging12110563"},"language":"en","primary_location":{"id":"doi:10.3390/jimaging12110563","doi":"https://doi.org/10.3390/jimaging12110563","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging12110563","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,"listed_in":["cwts-core","doaj","norway-1","poland-20","russia-white-list-1","vabb-shw"],"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"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/jimaging12110563","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101437266","display_name":"Ting Liu","orcid":"https://orcid.org/0000-0002-6950-8086","observed_orcids":["https://orcid.org/0000-0002-6950-8086"]},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Liu","raw_affiliation_strings":["College of Marine Electrical Engineering, Dalian Maritime University, Dalian 116026, China"],"raw_orcid":"https://orcid.org/0000-0002-6950-8086","affiliations":[{"raw_affiliation_string":"College of Marine Electrical Engineering, Dalian Maritime University, Dalian 116026, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161361665","display_name":"Xu Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xu Yang","raw_affiliation_strings":["College of Marine Electrical Engineering, Dalian Maritime University, Dalian 116026, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Marine Electrical Engineering, Dalian Maritime University, Dalian 116026, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103014665","display_name":"Yupeng Jia","orcid":"https://orcid.org/0009-0001-2654-5629","observed_orcids":["https://orcid.org/0009-0001-2654-5629"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yupeng Jia","raw_affiliation_strings":["Dalian Scientific Test and Control Technology Institute, Dalian 116026, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian Scientific Test and Control Technology Institute, Dalian 116026, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5161361665"],"corresponding_institution_ids":["https://openalex.org/I43313876"],"apc_list":{"value":1800,"currency":"CHF","value_usd":2172},"apc_paid":{"value":1800,"currency":"CHF","value_usd":2172},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":"11","first_page":"563","last_page":"563"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9887999892234802,"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":0.9887999892234802,"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.0015999999595806003,"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"}},{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","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"}}],"keywords":[{"id":"https://openalex.org/keywords/cross-modal-fusion","display_name":"cross-modal fusion","score":0.9229999780654907},{"id":"https://openalex.org/keywords/triplet-attention","display_name":"triplet attention","score":0.9760000109672546},{"id":"https://openalex.org/keywords/yolov5","display_name":"YOLOv5","score":0.9419999718666077},{"id":"https://openalex.org/keywords/small-object-detection","display_name":"small object detection","score":0.6909999847412109},{"id":"https://openalex.org/keywords/flir-dataset","display_name":"FLIR dataset","score":0.4860000014305115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8222000002861023},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.8181999921798706},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.656000018119812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6205000281333923},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5831000208854675},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.49480000138282776},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.48179998993873596},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.461899995803833},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4596000015735626},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.43939998745918274},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.42489999532699585},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4205000102519989},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.3707999885082245},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.3463999927043915},{"id":"https://openalex.org/C88796919","wikidata":"https://www.wikidata.org/wiki/Q1142907","display_name":"Backbone network","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25940001010894775}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3390/jimaging12110563","doi":"https://doi.org/10.3390/jimaging12110563","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging12110563","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,"listed_in":["cwts-core","doaj","norway-1","poland-20","russia-white-list-1","vabb-shw"],"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"}],"best_oa_location":{"id":"doi:10.3390/jimaging12110563","doi":"https://doi.org/10.3390/jimaging12110563","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging12110563","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,"listed_in":["cwts-core","doaj","norway-1","poland-20","russia-white-list-1","vabb-shw"],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1910108985","https://openalex.org/W2031489346","https://openalex.org/W2752782242","https://openalex.org/W2884585870","https://openalex.org/W2929607865","https://openalex.org/W2963091558","https://openalex.org/W2963579094","https://openalex.org/W2988916019","https://openalex.org/W2997747012","https://openalex.org/W3034552520","https://openalex.org/W3036931590","https://openalex.org/W3046194589","https://openalex.org/W3118570274","https://openalex.org/W3119205652","https://openalex.org/W3126855404","https://openalex.org/W3138516171","https://openalex.org/W3170914694","https://openalex.org/W3177052299","https://openalex.org/W3209478434","https://openalex.org/W3213472242","https://openalex.org/W4200631567","https://openalex.org/W4312594135","https://openalex.org/W4313007055","https://openalex.org/W4321231176","https://openalex.org/W4322123798","https://openalex.org/W4367721788","https://openalex.org/W4376106313","https://openalex.org/W4379528676","https://openalex.org/W4382119971","https://openalex.org/W4385801610","https://openalex.org/W4386189887","https://openalex.org/W4399919431","https://openalex.org/W4401806723","https://openalex.org/W4402299909","https://openalex.org/W4402754006","https://openalex.org/W4406205540","https://openalex.org/W4409606658","https://openalex.org/W4410694760","https://openalex.org/W4416381448","https://openalex.org/W4417002649","https://openalex.org/W4417241645","https://openalex.org/W4417334972","https://openalex.org/W7160216670","https://openalex.org/W7164805007"],"related_works":["https://openalex.org/W7163921069","https://openalex.org/W4417491440","https://openalex.org/W4400946156","https://openalex.org/W7130927122","https://openalex.org/W4401567633","https://openalex.org/W7164480409","https://openalex.org/W7223960069","https://openalex.org/W7223701920","https://openalex.org/W7225040540","https://openalex.org/W7162298789"],"abstract_inverted_index":{"YOLO-GRAT":[0],"integrates":[1],"P3":[2],"Cross-Modal":[3],"Gated":[4],"Residual":[5],"Fusion":[6],"with":[7,142],"adaptively":[8],"weighted":[9,99],"Triplet":[10,100],"Attention":[11],"inside":[12],"backbone":[13],"C3":[14],"bottlenecks":[15],"of":[16],"a":[17,28,56],"YOLOv5-based":[18],"visible\u2013infrared":[19],"detector.":[20],"The":[21,114,129],"fusion":[22],"block":[23],"combines":[24],"input-dependent":[25],"modality":[26],"mixing,":[27],"mean-residual":[29],"path":[30],"and":[31,102,135,150],"pooled-token":[32],"Transformer":[33],"refinement;":[34],"the":[35,47,80,119,122,139,146],"attention":[36],"extension":[37],"learns":[38],"aggregation":[39],"weights":[40],"for":[41,66,91,94,98,104],"three":[42],"established":[43],"rotated":[44],"branches.":[45],"In":[46],"FLIR":[48,115],"comparison,":[49],"each":[50],"module":[51],"is":[52,89,109],"added":[53],"independently":[54],"to":[55,145],"common":[57],"dual-stream":[58],"baseline.":[59,68],"Full":[60,106],"gives":[61],"83.4/44.5%":[62],"AP50/AP50:95":[63],"versus":[64,111],"80.7/42.1%":[65],"that":[67],"A":[69],"separate":[70],"comparison":[71],"uses":[72],"four":[73],"identified":[74,123],"fixed-final":[75],"M3FD":[76,124],"seed-0":[77],"checkpoints":[78],"on":[79],"same":[81],"840":[82],"validation":[83],"pairs.":[84],"Their":[85],"official":[86],"COCO":[87],"AP":[88,108],"57.21%":[90],"CFT,":[92],"57.48%":[93],"CGRF":[95],"only,":[96],"57.40%":[97],"only":[101],"56.85%":[103],"Full;":[105],"small-object":[107],"35.46":[110],"CFT":[112],"35.95%.":[113],"configuration":[116,140],"results":[117,125],"motivate":[118],"combination,":[120],"while":[121],"reveal":[126],"metric-dependent":[127],"trade-offs.":[128],"study":[130],"evaluates":[131],"complementary":[132],"within-stream":[133],"recalibration":[134],"cross-modal":[136],"interaction":[137],"at":[138],"level,":[141],"conclusions":[143],"scoped":[144],"reported":[147],"datasets,":[148],"metrics":[149],"training":[151],"records.":[152]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-10T00:00:00"}