{"id":"https://openalex.org/W4417438442","doi":"https://doi.org/10.1109/lsp.2025.3644313","title":"ESGN-YOLO: Enhancing Multi-Scale Small Object Detection via Efficient Feature Fusion and Adaptive Spatial Modeling","display_name":"ESGN-YOLO: Enhancing Multi-Scale Small Object Detection via Efficient Feature Fusion and Adaptive Spatial Modeling","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W4417438442","doi":"https://doi.org/10.1109/lsp.2025.3644313"},"language":null,"primary_location":{"id":"doi:10.1109/lsp.2025.3644313","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3644313","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","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":null,"display_name":"Zihao Guo","orcid":"https://orcid.org/0009-0003-7092-4567"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zihao Guo","raw_affiliation_strings":["School of Artificial Intelligence, Southwest University, Chongqing, China"],"raw_orcid":"https://orcid.org/0009-0003-7092-4567","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Southwest University, Chongqing, China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111189228","display_name":"MeiLing Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"MeiLing Zhong","raw_affiliation_strings":["School of Artificial Intelligence, Southwest University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Southwest University, Chongqing, China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shukai Duan","orcid":"https://orcid.org/0000-0002-0040-3796"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shukai Duan","raw_affiliation_strings":["School of Artificial Intelligence, Southwest University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0002-0040-3796","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Southwest University, Chongqing, China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100640128","display_name":"Lidan Wang","orcid":"https://orcid.org/0000-0003-0730-4202"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lidan Wang","raw_affiliation_strings":["School of Artificial Intelligence, Southwest University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0003-0730-4202","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Southwest University, Chongqing, China","institution_ids":["https://openalex.org/I142108993"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I142108993"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39918078,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"426","last_page":"430"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9751999974250793,"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":0.9751999974250793,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.0038999998942017555,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0038999998942017555,"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/object-detection","display_name":"Object detection","score":0.7929999828338623},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6586999893188477},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6550999879837036},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5568000078201294},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5220999717712402},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4625999927520752},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.447299987077713},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.42899999022483826},{"id":"https://openalex.org/keywords/viola\u2013jones-object-detection-framework","display_name":"Viola\u2013Jones object detection framework","score":0.42309999465942383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8134999871253967},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7929999828338623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7141000032424927},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6586999893188477},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6550999879837036},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5849999785423279},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5568000078201294},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5220999717712402},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4625999927520752},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.447299987077713},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.42899999022483826},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.42309999465942383},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4205999970436096},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3856000006198883},{"id":"https://openalex.org/C32653426","wikidata":"https://www.wikidata.org/wiki/Q3813641","display_name":"Background subtraction","level":3,"score":0.3806000053882599},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C2779769447","wikidata":"https://www.wikidata.org/wiki/Q3813641","display_name":"Foreground detection","level":4,"score":0.29010000824928284},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2736000120639801},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.2621000111103058},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.2531999945640564},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3644313","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3644313","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3085241009","display_name":null,"funder_award_id":"CSTB2024NSCQ-MSX0586","funder_id":"https://openalex.org/F4320323172","funder_display_name":"Natural Science Foundation of Chongqing"},{"id":"https://openalex.org/G348915440","display_name":null,"funder_award_id":"SWU-XDZD22009","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G384472945","display_name":null,"funder_award_id":"62576291","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G579355339","display_name":null,"funder_award_id":"62306246","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G597519024","display_name":null,"funder_award_id":"SWU-XDJH202319","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323172","display_name":"Natural Science Foundation of Chongqing","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2161969291","https://openalex.org/W2163352848","https://openalex.org/W2577537809","https://openalex.org/W2794377509","https://openalex.org/W3092663126","https://openalex.org/W3116626500","https://openalex.org/W3132191748","https://openalex.org/W3165816055","https://openalex.org/W3171660447","https://openalex.org/W3205100603","https://openalex.org/W4293584584","https://openalex.org/W4312541503","https://openalex.org/W4312674029","https://openalex.org/W4365453031","https://openalex.org/W4386072246","https://openalex.org/W4386822273","https://openalex.org/W4388263918","https://openalex.org/W4388469898","https://openalex.org/W4393207085","https://openalex.org/W4400266963","https://openalex.org/W4402754006","https://openalex.org/W4403422383","https://openalex.org/W4403770406","https://openalex.org/W4404228250","https://openalex.org/W4406457610","https://openalex.org/W4407692228","https://openalex.org/W4408941254","https://openalex.org/W4410967082","https://openalex.org/W4411990067","https://openalex.org/W4413147621","https://openalex.org/W7083315027"],"related_works":[],"abstract_inverted_index":{"Object":[0],"detection":[1,73,114],"is":[2],"crucial":[3],"in":[4],"remote":[5],"sensing,":[6],"surveillance,":[7],"and":[8,22,26,49,61,75,80,89,97,112],"autonomous":[9],"driving.":[10],"Detecting":[11],"small":[12],"objects":[13],"remains":[14],"challenging":[15],"due":[16],"to":[17],"limited":[18],"pixels,":[19],"redundant":[20],"backgrounds,":[21],"noise":[23],"from":[24],"viewpoint":[25],"illumination":[27],"variations.":[28],"To":[29],"address":[30],"these,":[31],"we":[32],"propose":[33],"ESGN-YOLO,":[34],"a":[35,92],"lightweight":[36],"model":[37],"with":[38,91],"three":[39],"improvements.":[40],"The":[41,53,65],"Efficient":[42],"Feature":[43],"Fusion":[44],"Module":[45],"(EFFM)":[46],"enhances":[47],"multi-scale":[48],"directional":[50],"feature":[51],"extraction.":[52],"Shift-Wise":[54],"Convolution":[55],"(SWC)":[56],"Bottleneck":[57],"refines":[58],"fine-grained":[59],"features":[60],"suppresses":[62],"background":[63],"redundancy.":[64],"Group":[66],"Normalisation":[67],"Scale":[68],"Head":[69],"(GNSH)":[70],"further":[71],"improves":[72],"accuracy":[74],"efficiency.":[76],"Experiments":[77],"on":[78],"VisDrone2019":[79],"RS":[81],"STOD":[82],"show":[83],"ESGN-YOLO":[84],"achieves":[85],"superior":[86],"mAP@0.5":[87],"(34.5%":[88],"76%)":[90],"compact":[93],"size":[94],"(3.7M":[95],"parameters)":[96],"moderate":[98],"computational":[99],"cost":[100],"(12.3":[101],"GFLOPs).":[102],"Fast":[103],"inference":[104],"confirms":[105],"its":[106],"practicality":[107],"for":[108],"real-time":[109],"UAV":[110],"deployment":[111],"small-object":[113],"under":[115],"resource-constrained":[116],"conditions.":[117]},"counts_by_year":[],"updated_date":"2026-01-10T23:39:48.068659","created_date":"2025-12-17T00:00:00"}