{"id":"https://openalex.org/W4408311532","doi":"https://doi.org/10.1142/s0218001425550043","title":"STSODNet: Scale Transformer Small Object Detection Network","display_name":"STSODNet: Scale Transformer Small Object Detection Network","publication_year":2025,"publication_date":"2025-03-11","ids":{"openalex":"https://openalex.org/W4408311532","doi":"https://doi.org/10.1142/s0218001425550043"},"language":"en","primary_location":{"id":"doi:10.1142/s0218001425550043","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001425550043","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","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":"Jincheng Li","orcid":"https://orcid.org/0009-0000-9004-0214"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jincheng Li","raw_affiliation_strings":["School of Computer and Electronic Information, Guangxi University, Nanning, Guangxi 530004, P.\u00a0R.\u00a0China"],"raw_orcid":"https://orcid.org/0009-0000-9004-0214","affiliations":[{"raw_affiliation_string":"School of Computer and Electronic Information, Guangxi University, Nanning, Guangxi 530004, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lina Yang","orcid":"https://orcid.org/0009-0009-2704-1914"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lina Yang","raw_affiliation_strings":["School of Computer and Electronic Information, Guangxi University, Nanning, Guangxi 530004, P.\u00a0R.\u00a0China"],"raw_orcid":"https://orcid.org/0009-0009-2704-1914","affiliations":[{"raw_affiliation_string":"School of Computer and Electronic Information, Guangxi University, Nanning, Guangxi 530004, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015709957","display_name":"Patrick Shen-Pei Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick Shen-Pei Wang","raw_affiliation_strings":["Computer and Information Science Northeasten University, Boston, MA 02115, USA"],"raw_orcid":"https://orcid.org/0000-0002-9336-3155","affiliations":[{"raw_affiliation_string":"Computer and Information Science Northeasten University, Boston, MA 02115, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7655,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.67627356,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"39","issue":"06","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.6872000098228455,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.6872000098228455,"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/T13382","display_name":"Robotics and Automated Systems","score":0.6833000183105469,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.6218000054359436,"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/computer-science","display_name":"Computer science","score":0.6689529418945312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6373705267906189},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6202548742294312},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.49730733036994934},{"id":"https://openalex.org/keywords/object-based","display_name":"Object based","score":0.461072713136673},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.45835649967193604},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3893882632255554},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.3830646276473999},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3610478937625885},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14754506945610046},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.1454765796661377},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.10601094365119934},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07574376463890076},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06477147340774536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6689529418945312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6373705267906189},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6202548742294312},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.49730733036994934},{"id":"https://openalex.org/C3019973339","wikidata":"https://www.wikidata.org/wiki/Q899523","display_name":"Object based","level":3,"score":0.461072713136673},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.45835649967193604},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3893882632255554},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3830646276473999},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3610478937625885},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14754506945610046},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.1454765796661377},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.10601094365119934},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07574376463890076},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06477147340774536}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218001425550043","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001425550043","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2565639579","https://openalex.org/W2625219738","https://openalex.org/W2884585870","https://openalex.org/W2896155169","https://openalex.org/W2928165649","https://openalex.org/W2962951509","https://openalex.org/W2963351448","https://openalex.org/W2985384565","https://openalex.org/W2993756598","https://openalex.org/W3035396860","https://openalex.org/W3109915642","https://openalex.org/W3114606989","https://openalex.org/W3157386596","https://openalex.org/W3177052299","https://openalex.org/W3177257155","https://openalex.org/W3205100603","https://openalex.org/W4214507171","https://openalex.org/W4226327087","https://openalex.org/W4313172897","https://openalex.org/W4405286907"],"related_works":["https://openalex.org/W4292830139","https://openalex.org/W4319309705","https://openalex.org/W3127668761","https://openalex.org/W2100786069","https://openalex.org/W4239112351","https://openalex.org/W4256166021","https://openalex.org/W2585146553","https://openalex.org/W2156352682","https://openalex.org/W1991139010","https://openalex.org/W4205448459"],"abstract_inverted_index":{"Dense":[0],"small":[1,36,60,152,196,248],"object":[2,25,244,249],"detection":[3,26,57,201,245],"in":[4,21,34,39,90,211],"complex":[5,50],"scenes":[6],"is":[7,203],"a":[8,75,99,140,157,178,212],"valuable":[9],"and":[10,49,97,146,183,214,229,239],"challenging":[11],"research":[12],"field.":[13],"While":[14],"deep":[15],"learning":[16],"has":[17],"driven":[18],"significant":[19],"advancements":[20],"computer":[22],"vision,":[23],"traditional":[24,199],"models":[27],"still":[28],"struggle":[29],"to":[30,53,79,111,138,176,189],"achieve":[31,190],"high":[32],"accuracy":[33],"detecting":[35],"objects,":[37,197],"particularly":[38],"large-scale":[40],"aerial":[41],"images.":[42],"Challenges":[43],"such":[44],"as":[45,93],"scale":[46,88,135],"variations,":[47],"occlusions,":[48],"backgrounds":[51],"continue":[52],"hinder":[54],"the":[55,67,86,107,133,148,198,219,227],"effective":[56],"of":[58,195,222],"dense":[59],"objects.":[61],"In":[62],"this":[63,113],"paper,":[64],"we":[65,84,155],"present":[66],"Scale":[68],"Transformer":[69,109],"Small":[70],"Object":[71],"Detection":[72],"Network":[73],"(STSODNet),":[74],"novel":[76],"architecture":[77],"designed":[78],"address":[80],"these":[81],"challenges.":[82],"First,":[83],"conceptualize":[85],"pronounced":[87],"variation":[89],"drone":[91],"images":[92],"an":[94],"anomalous":[95],"disturbance":[96],"propose":[98],"multiscale":[100,116],"feature":[101,117],"enhancement":[102,118],"module":[103,119],"(MSFEM),":[104],"built":[105],"upon":[106],"Spatial":[108,163],"Network,":[110],"mitigate":[112],"effect.":[114],"The":[115],"performs":[120],"learnable,":[121],"multi-point":[122],"magnification":[123],"on":[124,129,151,226],"regions":[125],"surrounding":[126],"objects":[127],"based":[128],"spatial":[130,159,174,193],"saliency,":[131],"enhancing":[132],"model\u2019s":[134,149],"invariance.":[136],"Second,":[137],"generate":[139],"more":[141,179,191],"accurate":[142,192],"global":[143],"saliency":[144,181],"map":[145,182],"heighten":[147],"focus":[150],"target":[153],"regions,":[154],"introduce":[156],"refined":[158],"attention":[160,171,175],"mechanism,":[161],"termed":[162],"Region":[164],"Attention.":[165],"This":[166],"mechanism":[167],"combines":[168],"coarse":[169],"region":[170],"with":[172],"fine":[173],"produce":[177],"detailed":[180],"improve":[184],"long-range":[185],"dependency":[186],"capture.":[187],"Third,":[188],"regression":[194],"three-layer":[200],"head":[202],"improved":[204],"by":[205],"expanding":[206],"its":[207],"output":[208,216],"layer,":[209],"resulting":[210],"finer":[213],"larger":[215],"while":[217],"maintaining":[218],"same":[220],"number":[221],"parameters.":[223],"Extensive":[224],"experiments":[225],"VisDrone":[228],"SeaPerson":[230],"benchmark":[231],"datasets":[232],"validate":[233],"that":[234],"STSODNet":[235],"achieves":[236],"superior":[237],"precision":[238],"robustness,":[240],"outperforming":[241],"current":[242],"state-of-the-art":[243],"methods":[246],"for":[247],"detection.":[250]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}