{"id":"https://openalex.org/W7128910981","doi":"https://doi.org/10.1145/3788731.3788755","title":"CMUNeXt-YOLO: Enhancing Small Object Detection by Integrating Global Context and Fine-Grained Detection Heads","display_name":"CMUNeXt-YOLO: Enhancing Small Object Detection by Integrating Global Context and Fine-Grained Detection Heads","publication_year":2025,"publication_date":"2025-12-19","ids":{"openalex":"https://openalex.org/W7128910981","doi":"https://doi.org/10.1145/3788731.3788755"},"language":null,"primary_location":{"id":"doi:10.1145/3788731.3788755","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788731.3788755","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Embodied Intelligence and Large Models","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3788731.3788755","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126016463","display_name":"Yuqiang He","orcid":null},"institutions":[{"id":"https://openalex.org/I2801441622","display_name":"China Railway Corporation","ror":"https://ror.org/044wv3489","country_code":"CN","type":"government","lineage":["https://openalex.org/I2801441622","https://openalex.org/I4210122102"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqiang He","raw_affiliation_strings":["CHN Guoneng Shuohuang Railway Development Co.,Ltd, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-6407-9682","affiliations":[{"raw_affiliation_string":"CHN Guoneng Shuohuang Railway Development Co.,Ltd, Beijing, China","institution_ids":["https://openalex.org/I2801441622"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126002076","display_name":"Shuaipeng Han","orcid":null},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuaipeng Han","raw_affiliation_strings":["Southwest Jiaotong University, Chengdu, Sichuan, China"],"raw_orcid":"https://orcid.org/0009-0004-6947-6637","affiliations":[{"raw_affiliation_string":"Southwest Jiaotong University, Chengdu, Sichuan, China","institution_ids":["https://openalex.org/I4800084"]}]}],"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":0.64415682,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"152","last_page":"158"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9327999949455261,"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":0.9327999949455261,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.007400000002235174,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.006000000052154064,"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/object-detection","display_name":"Object detection","score":0.8057000041007996},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6086000204086304},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.6031000018119812},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5961999893188477},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.5536999702453613},{"id":"https://openalex.org/keywords/object-class-detection","display_name":"Object-class detection","score":0.5289000272750854},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.525600016117096},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5253000259399414},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4546000063419342}],"concepts":[{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.8057000041007996},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7677000164985657},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7537999749183655},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6866999864578247},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6086000204086304},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.6031000018119812},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5961999893188477},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5536999702453613},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.5289000272750854},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.525600016117096},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5253000259399414},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4546000063419342},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45320001244544983},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.4447000026702881},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.43880000710487366},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.43639999628067017},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.43309998512268066},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C3019361169","wikidata":"https://www.wikidata.org/wiki/Q2609467","display_name":"Detection threshold","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C70710897","wikidata":"https://www.wikidata.org/wiki/Q680081","display_name":"Separable space","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C3020199158","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"High resolution","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2759999930858612},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2694999873638153},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3788731.3788755","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788731.3788755","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Embodied Intelligence and Large Models","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3788731.3788755","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788731.3788755","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Embodied Intelligence and Large Models","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2963037989","https://openalex.org/W2982770724","https://openalex.org/W3138516171","https://openalex.org/W3171660447","https://openalex.org/W3176659256","https://openalex.org/W4312349930","https://openalex.org/W4312443924","https://openalex.org/W4312628331","https://openalex.org/W4390872937","https://openalex.org/W4401749301"],"related_works":[],"abstract_inverted_index":{"Small":[0],"object":[1,90,138],"detection":[2,36,84,139],"faces":[3],"significant":[4],"challenges":[5],"due":[6],"to":[7,20,130],"the":[8,15,54,75,106,118,131],"limited":[9],"pixel":[10],"proportion":[11],"of":[12,17,65],"targets":[13],"and":[14,34,63,115],"susceptibility":[16],"deep":[18],"features":[19],"loss.":[21],"While":[22],"YOLOv8":[23,76],"serves":[24],"as":[25],"an":[26],"efficient":[27],"baseline":[28,107],"model,":[29],"its":[30,40],"constrained":[31],"receptive":[32],"field":[33],"insufficient":[35],"head":[37,85],"resolution":[38],"limit":[39],"performance":[41],"on":[42,93],"small":[43,89,137],"objects.":[44],"To":[45],"address":[46],"these":[47],"issues,":[48],"we":[49,80],"propose":[50],"CMUNeXt-YOLO,":[51],"which":[52],"integrates":[53],"lightweight":[55],"CMUNeXt":[56],"module\u2014originally":[57],"designed":[58],"for":[59,88],"medical":[60],"image":[61],"segmentation":[62],"capable":[64],"effectively":[66],"capturing":[67],"global":[68],"context":[69],"through":[70],"large-kernel":[71],"depthwise":[72],"separable":[73],"convolutions\u2014into":[74],"backbone":[77],"network.":[78],"Furthermore,":[79],"introduce":[81],"a":[82,125],"high-resolution":[83],"specifically":[86],"tailored":[87],"detection.":[91],"Experiments":[92],"our":[94,99],"custom-built":[95],"dataset":[96],"demonstrate":[97],"that":[98],"method":[100],"improves":[101],"mAP":[102,127],"by":[103],"4.6%":[104],"over":[105],"YOLOv8.":[108],"The":[109],"proposed":[110],"approach":[111],"exhibits":[112],"strong":[113],"generalizability":[114],"transferability;":[116],"under":[117],"same":[119],"experimental":[120],"conditions,":[121],"it":[122],"also":[123],"achieves":[124],"2.1%":[126],"improvement":[128],"compared":[129],"YOLOv12":[132],"baseline.":[133],"This":[134],"significantly":[135],"enhances":[136],"accuracy":[140],"while":[141],"maintaining":[142],"excellent":[143],"computational":[144],"efficiency.":[145]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-15T00:00:00"}