{"id":"https://openalex.org/W7146936979","doi":"https://doi.org/10.1109/cw68232.2025.00042","title":"RMC-YOLO: A Small Object Detection Framework with Routing Attention and Multi-Scale Context Modulation","display_name":"RMC-YOLO: A Small Object Detection Framework with Routing Attention and Multi-Scale Context Modulation","publication_year":2025,"publication_date":"2025-10-14","ids":{"openalex":"https://openalex.org/W7146936979","doi":"https://doi.org/10.1109/cw68232.2025.00042"},"language":null,"primary_location":{"id":"doi:10.1109/cw68232.2025.00042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cw68232.2025.00042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Cyberworlds (CW\uff09","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100333011","display_name":"Jie Chen","orcid":"https://orcid.org/0000-0003-3435-0351"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jimeng Chen","raw_affiliation_strings":["Ningbo University,Faculty of Information Science and Engineering,Ningbo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ningbo University,Faculty of Information Science and Engineering,Ningbo,China","institution_ids":["https://openalex.org/I109935558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043949438","display_name":"X. Rosalind Wang","orcid":"https://orcid.org/0000-0001-5454-6197"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong Wang","raw_affiliation_strings":["Ningbo University,Faculty of Information Science and Engineering,Ningbo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ningbo University,Faculty of Information Science and Engineering,Ningbo,China","institution_ids":["https://openalex.org/I109935558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006533844","display_name":"Lianjun Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianjun Zhang","raw_affiliation_strings":["Ningbo University,Faculty of Information Science and Engineering,Ningbo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ningbo University,Faculty of Information Science and Engineering,Ningbo,China","institution_ids":["https://openalex.org/I109935558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132563358","display_name":"Yuli Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuli Liu","raw_affiliation_strings":["Ningbo University,Faculty of Information Science and Engineering,Ningbo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ningbo University,Faculty of Information Science and Engineering,Ningbo,China","institution_ids":["https://openalex.org/I109935558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132720147","display_name":"Min Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I159389169","display_name":"Ningbo University of Technology","ror":"https://ror.org/037dym702","country_code":"CN","type":"education","lineage":["https://openalex.org/I159389169"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Luo","raw_affiliation_strings":["College of Digital Technology and Engineering, Ningbo University of Finance and Economics,Ningbo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Digital Technology and Engineering, Ningbo University of Finance and Economics,Ningbo,China","institution_ids":["https://openalex.org/I159389169"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.71355208,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"248","last_page":"255"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9320999979972839,"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":0.9320999979972839,"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/T11133","display_name":"UAV Applications and Optimization","score":0.012900000438094139,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.004800000227987766,"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/feature","display_name":"Feature (linguistics)","score":0.6881999969482422},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5799999833106995},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5625},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.5253999829292297},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.5102999806404114},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.46389999985694885},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.43470001220703125},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.42719998955726624},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4043000042438507}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7508999705314636},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6881999969482422},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5799999833106995},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5625},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.5253999829292297},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.5102999806404114},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.46389999985694885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46149998903274536},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.43470001220703125},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.42719998955726624},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4043000042438507},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39629998803138733},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3878999948501587},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3650999963283539},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.3490999937057495},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.34850001335144043},{"id":"https://openalex.org/C180505990","wikidata":"https://www.wikidata.org/wiki/Q498267","display_name":"News aggregator","level":2,"score":0.34630000591278076},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3422999978065491},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2637999951839447},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2596000134944916},{"id":"https://openalex.org/C2781368080","wikidata":"https://www.wikidata.org/wiki/Q501688","display_name":"Context awareness","level":3,"score":0.2574000060558319},{"id":"https://openalex.org/C19247436","wikidata":"https://www.wikidata.org/wiki/Q192727","display_name":"Physical layer","level":3,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cw68232.2025.00042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cw68232.2025.00042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Cyberworlds (CW\uff09","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7519511831","display_name":null,"funder_award_id":"2022Z186","funder_id":"https://openalex.org/F4320336552","funder_display_name":"Science and Technology Innovation 2025 Major Project of Ningbo"}],"funders":[{"id":"https://openalex.org/F4320336552","display_name":"Science and Technology Innovation 2025 Major Project of Ningbo","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2102605133","https://openalex.org/W2565639579","https://openalex.org/W2963037989","https://openalex.org/W3048644861","https://openalex.org/W4313172897","https://openalex.org/W4385760871","https://openalex.org/W4386072246","https://openalex.org/W4386075524","https://openalex.org/W4386076325","https://openalex.org/W4386931641","https://openalex.org/W4402753731","https://openalex.org/W4402865423","https://openalex.org/W4406335268","https://openalex.org/W4411086345","https://openalex.org/W4416248293"],"related_works":[],"abstract_inverted_index":{"Detecting":[0],"small":[1,61],"objects":[2],"in":[3,29,122],"UAV":[4],"images":[5],"is":[6,42,68,101,145],"challenging":[7],"due":[8],"to":[9,26,56,93,110,147],"their":[10],"limited":[11],"size":[12],"and":[13,59,78,131],"the":[14,72,79,90,97,104,112,123,133,137,155,160,170],"complexity":[15],"of":[16,66,114],"background.":[17],"This":[18],"work":[19],"introduces":[20],"an":[21,127],"improved":[22],"YOLOv8nbased":[23],"approach":[24],"designed":[25],"enhance":[27],"performance":[28],"such":[30],"environments.":[31],"Specifically,":[32],"a":[33,46,51,166],"feature":[34,129,151],"modeling":[35,113],"framework,":[36],"named":[37],"RMC":[38],"(Routing-aware":[39],"Modulated":[40],"Context)":[41],"designed,":[43],"which":[44,144],"integrates":[45],"routing-aware":[47],"attention":[48],"mechanism":[49],"with":[50,136],"multi-scale":[52,150],"context":[53],"modulation":[54],"strategy":[55],"better":[57],"capture":[58],"distinguish":[60],"object":[62],"features.":[63],"The":[64],"backbone":[65],"YOLOv8n":[67],"restructured":[69],"by":[70,103,125],"introducing":[71,126],"Omni-dimensional":[73],"Dynamic":[74],"Convolution":[75],"(ODConv)":[76],"module":[77,100,109],"Routing":[80],"Attention":[81],"Spatial":[82,139],"Aggregator":[83],"(RASA)":[84],"module,":[85,143],"both":[86],"aimed":[87],"at":[88],"improving":[89],"model's":[91],"sensitivity":[92],"target":[94],"regions.":[95],"Meanwhile,":[96],"original":[98,171],"SPPF":[99],"replaced":[102],"Multi-Scale":[105],"Context":[106],"Modulation":[107],"(MSCM)":[108],"strengthen":[111],"complex":[115],"contextual":[116],"information.":[117],"Further":[118],"improvements":[119],"are":[120],"made":[121],"neck":[124],"extra":[128],"layer":[130],"replacing":[132],"detection":[134],"head":[135],"Adaptive":[138],"Feature":[140],"Fusion":[141],"(ASFF)":[142],"incorporated":[146],"enable":[148],"effective":[149],"fusion.":[152],"Validation":[153],"on":[154],"VisDrone2019":[156],"dataset":[157],"demonstrates":[158],"that":[159],"RMC-YOLO":[161],"method":[162],"reaches":[163],"38.9%$\\text{mAP}@0.5$,":[164],"representing":[165],"4.9%":[167],"improvement":[168],"over":[169],"YOLOv8n.":[172]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-04-02T00:00:00"}