{"id":"https://openalex.org/W4407223103","doi":"https://doi.org/10.3390/sym17020242","title":"Unified Spatial-Frequency Modeling and Alignment for Multi-Scale Small Object Detection","display_name":"Unified Spatial-Frequency Modeling and Alignment for Multi-Scale Small Object Detection","publication_year":2025,"publication_date":"2025-02-06","ids":{"openalex":"https://openalex.org/W4407223103","doi":"https://doi.org/10.3390/sym17020242"},"language":"en","primary_location":{"id":"doi:10.3390/sym17020242","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym17020242","pdf_url":null,"source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/sym17020242","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009252600","display_name":"Jing Liu","orcid":"https://orcid.org/0009-0008-5192-3653"},"institutions":[{"id":"https://openalex.org/I4210162994","display_name":"Xijing University","ror":"https://ror.org/05xsjkb63","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162994"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jing Liu","raw_affiliation_strings":["Xi\u2019an Key Laboratory of Human-Machine Integration and Control Technology for Intelligent Rehabilitation, School of Computer Science, Xijing University, Xi\u2019an 710123, China"],"raw_orcid":"https://orcid.org/0009-0008-5192-3653","affiliations":[{"raw_affiliation_string":"Xi\u2019an Key Laboratory of Human-Machine Integration and Control Technology for Intelligent Rehabilitation, School of Computer Science, Xijing University, Xi\u2019an 710123, China","institution_ids":["https://openalex.org/I4210162994"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106406582","display_name":"Ying Wang","orcid":"https://orcid.org/0009-0007-3655-9702"},"institutions":[{"id":"https://openalex.org/I4210121573","display_name":"Wuchang University of Technology","ror":"https://ror.org/02mqsna37","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210121573"]},{"id":"https://openalex.org/I4400600924","display_name":"Wuchang Shouyi University","ror":"https://ror.org/02ny5za58","country_code":null,"type":"education","lineage":["https://openalex.org/I4400600924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Wang","raw_affiliation_strings":["School of Information Science and Engineering, Wuchang Shouyi University, Wuhan 430072, China"],"raw_orcid":"https://orcid.org/0009-0007-3655-9702","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Wuchang Shouyi University, Wuhan 430072, China","institution_ids":["https://openalex.org/I4210121573","https://openalex.org/I4400600924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100311483","display_name":"Yanyan Cao","orcid":"https://orcid.org/0009-0002-4735-0668"},"institutions":[{"id":"https://openalex.org/I4210162994","display_name":"Xijing University","ror":"https://ror.org/05xsjkb63","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162994"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyan Cao","raw_affiliation_strings":["Xi\u2019an Key Laboratory of Human-Machine Integration and Control Technology for Intelligent Rehabilitation, School of Computer Science, Xijing University, Xi\u2019an 710123, China"],"raw_orcid":"https://orcid.org/0009-0002-4735-0668","affiliations":[{"raw_affiliation_string":"Xi\u2019an Key Laboratory of Human-Machine Integration and Control Technology for Intelligent Rehabilitation, School of Computer Science, Xijing University, Xi\u2019an 710123, China","institution_ids":["https://openalex.org/I4210162994"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102422259","display_name":"Chaoping Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162994","display_name":"Xijing University","ror":"https://ror.org/05xsjkb63","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162994"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoping Guo","raw_affiliation_strings":["Xi\u2019an Key Laboratory of Human-Machine Integration and Control Technology for Intelligent Rehabilitation, School of Computer Science, Xijing University, Xi\u2019an 710123, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi\u2019an Key Laboratory of Human-Machine Integration and Control Technology for Intelligent Rehabilitation, School of Computer Science, Xijing University, Xi\u2019an 710123, China","institution_ids":["https://openalex.org/I4210162994"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053353190","display_name":"Peijun Shi","orcid":"https://orcid.org/0000-0002-2968-7331"},"institutions":[{"id":"https://openalex.org/I4210162994","display_name":"Xijing University","ror":"https://ror.org/05xsjkb63","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162994"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peijun Shi","raw_affiliation_strings":["Xi\u2019an Key Laboratory of Human-Machine Integration and Control Technology for Intelligent Rehabilitation, School of Computer Science, Xijing University, Xi\u2019an 710123, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi\u2019an Key Laboratory of Human-Machine Integration and Control Technology for Intelligent Rehabilitation, School of Computer Science, Xijing University, Xi\u2019an 710123, China","institution_ids":["https://openalex.org/I4210162994"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100455209","display_name":"Pan Li","orcid":"https://orcid.org/0000-0002-9861-8305"},"institutions":[{"id":"https://openalex.org/I4210162994","display_name":"Xijing University","ror":"https://ror.org/05xsjkb63","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162994"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pan Li","raw_affiliation_strings":["Xi\u2019an Key Laboratory of Human-Machine Integration and Control Technology for Intelligent Rehabilitation, School of Computer Science, Xijing University, Xi\u2019an 710123, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi\u2019an Key Laboratory of Human-Machine Integration and Control Technology for Intelligent Rehabilitation, School of Computer Science, Xijing University, Xi\u2019an 710123, China","institution_ids":["https://openalex.org/I4210162994"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5009252600"],"corresponding_institution_ids":["https://openalex.org/I4210162994"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2165},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2165},"fwci":12.2011,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.98661705,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"17","issue":"2","first_page":"242","last_page":"242"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9922999739646912,"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":0.9922999739646912,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9911999702453613,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9901000261306763,"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":0.6828530430793762},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6008715033531189},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.41517508029937744},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3873666524887085},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.336597204208374},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32666903734207153},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3225618600845337},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.16306114196777344},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.13809412717819214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6828530430793762},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6008715033531189},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.41517508029937744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3873666524887085},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.336597204208374},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32666903734207153},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3225618600845337},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.16306114196777344},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.13809412717819214}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3390/sym17020242","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym17020242","pdf_url":null,"source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3390/sym17020242","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym17020242","pdf_url":null,"source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2102605133","https://openalex.org/W2193145675","https://openalex.org/W2560023338","https://openalex.org/W2565639579","https://openalex.org/W2963037989","https://openalex.org/W2963351448","https://openalex.org/W2963604034","https://openalex.org/W2963857746","https://openalex.org/W2964444661","https://openalex.org/W2989676862","https://openalex.org/W3009396058","https://openalex.org/W3034573343","https://openalex.org/W3034971973","https://openalex.org/W3036271496","https://openalex.org/W3042011474","https://openalex.org/W3092151103","https://openalex.org/W3096609285","https://openalex.org/W3106250896","https://openalex.org/W3107331169","https://openalex.org/W3113522598","https://openalex.org/W3119129845","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3172752666","https://openalex.org/W4214507171","https://openalex.org/W4226410580","https://openalex.org/W4229453634","https://openalex.org/W4312373555","https://openalex.org/W4382464354","https://openalex.org/W4382568144","https://openalex.org/W4385760871","https://openalex.org/W4386076053","https://openalex.org/W4386076325","https://openalex.org/W4390488653","https://openalex.org/W4390872447","https://openalex.org/W4391559729","https://openalex.org/W4392089963","https://openalex.org/W4395028341","https://openalex.org/W4396605538","https://openalex.org/W4396712913","https://openalex.org/W4399740907","https://openalex.org/W4401510007","https://openalex.org/W4401879614","https://openalex.org/W4402402063","https://openalex.org/W4402627318","https://openalex.org/W4402754006","https://openalex.org/W4402865423","https://openalex.org/W4404688003","https://openalex.org/W4404727653","https://openalex.org/W6739901393","https://openalex.org/W6761306150","https://openalex.org/W6840971909","https://openalex.org/W6860271582","https://openalex.org/W6860848577","https://openalex.org/W6866899357","https://openalex.org/W6872291102"],"related_works":["https://openalex.org/W2121524756","https://openalex.org/W782553550","https://openalex.org/W1987967678","https://openalex.org/W2633218168","https://openalex.org/W4235897794","https://openalex.org/W2737719445","https://openalex.org/W2059707233","https://openalex.org/W1983126463","https://openalex.org/W2139939267","https://openalex.org/W1974511032"],"abstract_inverted_index":{"Small":[0],"object":[1,96,237],"detection":[2,25],"in":[3,70,235],"aerial":[4],"imagery":[5],"remains":[6],"challenging":[7],"due":[8],"to":[9,34,159],"sparse":[10],"feature":[11,29,72,173],"representation,":[12],"limited":[13],"spatial":[14,129],"resolution,":[15],"and":[16,60,87,112,117,131,134,147,156,171,188,199,206,218,227],"complex":[17],"background":[18,169],"interference.":[19],"Current":[20],"deep":[21],"learning":[22],"approaches":[23],"enhance":[24,160],"performance":[26],"through":[27],"multi-scale":[28,88],"fusion,":[30],"leveraging":[31],"convolutional":[32],"operations":[33],"expand":[35],"the":[36,104,109,118,125,161,165,180,204,210],"receptive":[37],"field":[38],"or":[39,66,74],"self-attention":[40,55],"mechanisms":[41],"for":[42,94,128,136],"global":[43,145],"context":[44],"modeling.":[45,201],"However,":[46],"these":[47,79],"methods":[48,234],"primarily":[49],"rely":[50],"on":[51,203],"spatial-domain":[52],"features,":[53],"while":[54,224],"introduces":[56],"high":[57],"computational":[58,228],"costs,":[59],"conventional":[61],"fusion":[62,90,143],"strategies":[63],"(e.g.,":[64],"concatenation":[65],"addition)":[67],"often":[68],"result":[69],"weak":[71],"correlation":[73],"boundary":[75],"misalignment.":[76],"To":[77],"address":[78],"challenges,":[80],"we":[81],"propose":[82],"a":[83,141],"unified":[84],"spatial-frequency":[85],"modeling":[86],"alignment":[89,155],"framework,":[91],"termed":[92],"USF-DETR,":[93,213],"small":[95,236],"detection.":[97,238],"The":[98,122,150,177,230],"framework":[99,231],"comprises":[100],"three":[101],"key":[102],"modules:":[103],"Spatial-Frequency":[105],"Interaction":[106],"Backbone":[107],"(SFIB),":[108],"Dual":[110],"Alignment":[111],"Balance":[113],"Fusion":[114],"FPN":[115],"(DABF-FPN),":[116],"Efficient":[119],"Attention-AIFI":[120],"(EA-AIFI).":[121],"SFIB":[123],"integrates":[124],"Scharr":[126],"operator":[127],"edge":[130],"detail":[132],"extraction":[133],"FFT/IFFT":[135],"capturing":[137],"frequency-domain":[138],"patterns,":[139],"achieving":[140,214],"balanced":[142],"of":[144,164,212,216],"semantics":[146],"local":[148],"details.":[149],"DABF-FPN":[151],"employs":[152],"bidirectional":[153],"geometric":[154],"adaptive":[157],"attention":[158,182],"significance":[162],"expression":[163],"target":[166],"area,":[167],"suppress":[168],"noise,":[170],"improve":[172],"asymmetry":[174],"across":[175],"scales.":[176],"EA-AIFI":[178],"streamlines":[179],"Transformer":[181],"mechanism":[183],"by":[184],"removing":[185],"key-value":[186],"interactions":[187],"encoding":[189],"query":[190],"relationships":[191],"via":[192],"linear":[193],"projections,":[194],"significantly":[195],"boosting":[196],"inference":[197],"speed":[198],"contextual":[200],"Experiments":[202],"VisDrone":[205],"TinyPerson":[207],"datasets":[208],"demonstrate":[209],"effectiveness":[211],"improvements":[215],"2.3%":[217],"1.4%":[219],"mAP":[220],"over":[221],"baselines,":[222],"respectively,":[223],"balancing":[225],"accuracy":[226],"efficiency.":[229],"outperforms":[232],"state-of-the-art":[233]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":4}],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2025-10-10T00:00:00"}