{"id":"https://openalex.org/W7130550011","doi":"https://doi.org/10.1007/s44443-026-00525-9","title":"YOLO-RECAP: reassembly with channel attention for perception","display_name":"YOLO-RECAP: reassembly with channel attention for perception","publication_year":2026,"publication_date":"2026-02-19","ids":{"openalex":"https://openalex.org/W7130550011","doi":"https://doi.org/10.1007/s44443-026-00525-9"},"language":"en","primary_location":{"id":"doi:10.1007/s44443-026-00525-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-026-00525-9","pdf_url":null,"source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"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 King Saud University Computer and Information Sciences","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1007/s44443-026-00525-9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126379935","display_name":"Heon-Ju Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I199143407","display_name":"Sunchon National University","ror":"https://ror.org/043jqrs76","country_code":"KR","type":"education","lineage":["https://openalex.org/I199143407"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Heon-Ju Kim","raw_affiliation_strings":["Interdisciplinary Program in IT-Bio Convergence System, Sunchon National University, Suncheon, 57922, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Program in IT-Bio Convergence System, Sunchon National University, Suncheon, 57922, Republic of Korea","institution_ids":["https://openalex.org/I199143407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126443763","display_name":"Sung-Wook Park","orcid":null},"institutions":[{"id":"https://openalex.org/I199143407","display_name":"Sunchon National University","ror":"https://ror.org/043jqrs76","country_code":"KR","type":"education","lineage":["https://openalex.org/I199143407"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sung-Wook Park","raw_affiliation_strings":["Interdisciplinary Program in IT-Bio Convergence System, Sunchon National University, Suncheon, 57922, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Program in IT-Bio Convergence System, Sunchon National University, Suncheon, 57922, Republic of Korea","institution_ids":["https://openalex.org/I199143407"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017207286","display_name":"Chun-Bo Sim","orcid":"https://orcid.org/0000-0003-0802-6355"},"institutions":[{"id":"https://openalex.org/I199143407","display_name":"Sunchon National University","ror":"https://ror.org/043jqrs76","country_code":"KR","type":"education","lineage":["https://openalex.org/I199143407"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Chun-Bo Sim","raw_affiliation_strings":["Interdisciplinary Program in IT-Bio Convergence System, Sunchon National University, Suncheon, 57922, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Program in IT-Bio Convergence System, Sunchon National University, Suncheon, 57922, Republic of Korea","institution_ids":["https://openalex.org/I199143407"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126367108","display_name":"Se-Hoon Jung","orcid":null},"institutions":[{"id":"https://openalex.org/I199143407","display_name":"Sunchon National University","ror":"https://ror.org/043jqrs76","country_code":"KR","type":"education","lineage":["https://openalex.org/I199143407"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Se-Hoon Jung","raw_affiliation_strings":["Department of Computer Engineering, Sunchon National University, Suncheon, 57922, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Sunchon National University, Suncheon, 57922, Republic of Korea","institution_ids":["https://openalex.org/I199143407"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5017207286"],"corresponding_institution_ids":["https://openalex.org/I199143407"],"apc_list":{"value":1350,"currency":"USD","value_usd":1350},"apc_paid":{"value":1350,"currency":"USD","value_usd":1350},"fwci":22.8522,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.98563643,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"38","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5734999775886536,"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":0.5734999775886536,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.05550000071525574,"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":0.04989999905228615,"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/latency","display_name":"Latency (audio)","score":0.5981000065803528},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5740000009536743},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.5504999756813049},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.4796000123023987},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4147999882698059},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3968000113964081},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.37229999899864197},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.367900013923645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8047999739646912},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6474999785423279},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6392999887466431},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5981000065803528},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5740000009536743},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.5504999756813049},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.4796000123023987},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4147999882698059},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3968000113964081},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.37229999899864197},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.31150001287460327},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.290800005197525},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.27639999985694885},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.26429998874664307},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C3020199158","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"High resolution","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44443-026-00525-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-026-00525-9","pdf_url":null,"source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"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 King Saud University Computer and Information Sciences","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:49a1cc1658a54a40b7520fdac14b3d1a","is_oa":true,"landing_page_url":"https://doaj.org/article/49a1cc1658a54a40b7520fdac14b3d1a","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of King Saud University: Computer and Information Sciences, Vol 38, Iss 4 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44443-026-00525-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-026-00525-9","pdf_url":null,"source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"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 King Saud University Computer and Information Sciences","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.521819531917572,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G117323084","display_name":null,"funder_award_id":"RS-2024-00407739","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W2031489346","https://openalex.org/W2102605133","https://openalex.org/W2151103935","https://openalex.org/W2161969291","https://openalex.org/W2183182206","https://openalex.org/W2565639579","https://openalex.org/W2752782242","https://openalex.org/W2884585870","https://openalex.org/W2963037989","https://openalex.org/W2963351448","https://openalex.org/W2963857746","https://openalex.org/W2971900262","https://openalex.org/W2982905682","https://openalex.org/W3034552520","https://openalex.org/W3034971973","https://openalex.org/W3042011474","https://openalex.org/W3122239467","https://openalex.org/W3155412868","https://openalex.org/W3170033848","https://openalex.org/W3177052299","https://openalex.org/W3208645658","https://openalex.org/W3215216361","https://openalex.org/W4213019189","https://openalex.org/W4221160129","https://openalex.org/W4287364075","https://openalex.org/W4320002812","https://openalex.org/W4366400469","https://openalex.org/W4385245566","https://openalex.org/W4386075524","https://openalex.org/W4386076325","https://openalex.org/W4392089963","https://openalex.org/W4398788555","https://openalex.org/W4398810114","https://openalex.org/W4404303854","https://openalex.org/W4409770779","https://openalex.org/W4417101775"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Object":[1,146,152],"detection":[2,47,76,276,284],"is":[3,60,163,295],"a":[4,19,94,181,267,271],"technology":[5],"that":[6,169],"automatically":[7],"identifies":[8],"and":[9,17,31,46,62,81,100,113,149,173,195,210,226,232,243,256,262,274,282,290],"locates":[10],"specific":[11],"objects":[12,80,289],"in":[13,22,49,67,74,154,260],"images":[14],"or":[15],"videos":[16],"plays":[18],"core":[20],"role":[21],"various":[23],"fields,":[24],"such":[25],"as":[26],"autonomous":[27],"driving,":[28],"security":[29],"surveillance,":[30],"medical":[32],"imaging.":[33],"You":[34],"Only":[35],"Look":[36],"Once":[37],"(YOLO)":[38],"has":[39],"gained":[40],"attention":[41],"for":[42,78,151,287],"achieving":[43],"both":[44],"accuracy":[45],"speed":[48],"real-time":[50],"applications;":[51],"however,":[52],"during":[53,115],"the":[54,68,116,279],"resolution":[55],"reduction":[56],"process,":[57],"detailed":[58],"information":[59],"lost,":[61],"unnecessary":[63],"signals":[64],"are":[65],"mixed":[66],"multi-scale":[69],"feature":[70],"fusion":[71],"stage,":[72],"resulting":[73],"limited":[75],"performance":[77,135,277],"small":[79,288],"complex":[82,291],"background":[83],"scenes.":[84,265],"To":[85],"alleviate":[86],"these":[87],"limitations,":[88],"we":[89],"propose":[90],"YOLO-RECAP,":[91],"which":[92],"integrates":[93],"Content-Aware":[95],"ReAssembly":[96],"of":[97,186,189,192,201,204,207,217,220,223,234,237,240],"FEatures":[98],"(CARAFE)":[99],"Efficient":[101],"Channel":[102],"Attention":[103],"(ECA)":[104],"modules":[105],"based":[106],"on":[107,198,213,229,246],"YOLOv11.":[108],"CARAFE":[109],"precisely":[110],"restores":[111],"boundaries":[112],"shapes":[114],"upsampling":[117],"stage":[118],"by":[119],"utilizing":[120],"position-specific":[121],"content":[122],"information,":[123],"whereas":[124],"ECA":[125],"effectively":[126],"models":[127],"interchannel":[128],"interactions":[129],"to":[130,175],"emphasize":[131],"important":[132],"signals.":[133],"For":[134],"verification,":[136],"VisDrone2019,":[137],"Store":[138],"Keeping":[139],"Unit-110":[140],"K":[141],"(SKU-110":[142],"K),":[143],"Pascal":[144,230],"Visual":[145],"Classes":[147],"(VOC),":[148],"Dataset":[150],"Detection":[153],"Aerial":[155],"Images":[156],"(DOTA)v1":[157],"were":[158],"used.":[159],"In":[160],"addition,":[161],"Latency":[162,191,206,222,239],"reported":[164],"under":[165],"an":[166],"end-to-end":[167],"setting":[168],"includes":[170],"pre-processing,":[171],"inference,":[172],"post-processing,":[174],"reflect":[176],"practical":[177],"deployment":[178],"conditions.":[179],"As":[180,266],"result,":[182,268],"YOLO-RECAP":[183,269],"achieved":[184],"mAP50":[185,200,216,233],"0.316,":[187],"mAP50@95":[188,203,219,236],"0.184,":[190],"16.5":[193],"ms,":[194,209,225,242],"60.6":[196],"FPS":[197,212,228,245],"VisDrone2019;":[199],"0.895,":[202],"0.572,":[205],"18.2":[208],"55.0":[211],"SKU-110":[214],"K;":[215],"0.770,":[218],"0.561,":[221],"15.6":[224],"63.9":[227],"VOC;":[231],"0.281,":[235],"0.157,":[238],"18.6":[241],"53.9":[244],"DOTAv1.":[247],"Qualitative":[248],"bounding-box":[249],"visualizations":[250],"further":[251],"indicate":[252],"reduced":[253],"missed":[254],"detections":[255],"more":[257,272],"stable":[258,273],"predictions":[259],"cluttered":[261],"densely":[263],"populated":[264],"provided":[270],"balanced":[275],"than":[278],"existing":[280],"YOLOv11":[281],"recent":[283],"models,":[285],"especially":[286],"backgrounds.":[292],"This":[293],"code":[294],"available":[296],"at":[297],"https://github.com/Heon-ju/YOLO-RECAP.git":[298],".":[299]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-02-20T00:00:00"}