{"id":"https://openalex.org/W7083315027","doi":"https://doi.org/10.1109/tgrs.2025.3614370","title":"CAEM-DETR: Small Aerial Target Detection via Contrastive Attention-Enhanced Multidomain Fidelity Fusion","display_name":"CAEM-DETR: Small Aerial Target Detection via Contrastive Attention-Enhanced Multidomain Fidelity Fusion","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7083315027","doi":"https://doi.org/10.1109/tgrs.2025.3614370"},"language":"en","primary_location":{"id":"doi:10.1109/tgrs.2025.3614370","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2025.3614370","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"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 Transactions on Geoscience and Remote Sensing","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":"Zhangheng Han","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhangheng Han","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology (NJUST), Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology (NJUST), Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang Xu","orcid":"https://orcid.org/0000-0003-3514-9705"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Xu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology (NJUST), Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology (NJUST), Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jun Li","orcid":"https://orcid.org/0000-0003-1613-9448"},"institutions":[{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Li","raw_affiliation_strings":["School of Computer Science and Hubei Key Laboratory of Intelligent Geo-Information Processing, China University of Geosciences, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Hubei Key Laboratory of Intelligent Geo-Information Processing, China University of Geosciences, Wuhan, China","institution_ids":["https://openalex.org/I3124059619"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Javier Plaza","orcid":"https://orcid.org/0000-0002-2384-9141"},"institutions":[{"id":"https://openalex.org/I80606768","display_name":"Universidad de Extremadura","ror":"https://ror.org/0174shg90","country_code":"ES","type":"education","lineage":["https://openalex.org/I80606768"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Javier Plaza","raw_affiliation_strings":["Hyperspectral Computing Laboratory, University of Extremadura, C&#x00E1;ceres, Spain"],"affiliations":[{"raw_affiliation_string":"Hyperspectral Computing Laboratory, University of Extremadura, C&#x00E1;ceres, Spain","institution_ids":["https://openalex.org/I80606768"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Antonio Plaza","orcid":"https://orcid.org/0000-0002-9613-1659"},"institutions":[{"id":"https://openalex.org/I80606768","display_name":"Universidad de Extremadura","ror":"https://ror.org/0174shg90","country_code":"ES","type":"education","lineage":["https://openalex.org/I80606768"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Antonio Plaza","raw_affiliation_strings":["Hyperspectral Computing Laboratory, University of Extremadura, C&#x00E1;ceres, Spain"],"affiliations":[{"raw_affiliation_string":"Hyperspectral Computing Laboratory, University of Extremadura, C&#x00E1;ceres, Spain","institution_ids":["https://openalex.org/I80606768"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhihui Wei","orcid":"https://orcid.org/0000-0002-4841-6051"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihui Wei","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology (NJUST), Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology (NJUST), Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":null,"display_name":"Zebin Wu","orcid":"https://orcid.org/0000-0002-7162-0202"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zebin Wu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology (NJUST), Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology (NJUST), Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":6.1931,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.96819299,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"63","issue":null,"first_page":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T13608","display_name":"Advanced Computational Techniques in Science and Engineering","score":0.02290000021457672,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13608","display_name":"Advanced Computational Techniques in Science and Engineering","score":0.02290000021457672,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13398","display_name":"Data Analysis with R","score":0.01730000041425228,"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"}},{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.01640000008046627,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/upsampling","display_name":"Upsampling","score":0.8490999937057495},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6870999932289124},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.583899974822998},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5705000162124634},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.4997999966144562},{"id":"https://openalex.org/keywords/aerial-image","display_name":"Aerial image","score":0.49970000982284546},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4731999933719635},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.4275999963283539},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4203000068664551}],"concepts":[{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.8490999937057495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7986000180244446},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6870999932289124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5954999923706055},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.583899974822998},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5705000162124634},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.4997999966144562},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.49970000982284546},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4851999878883362},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4731999933719635},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.4275999963283539},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4203000068664551},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.40070000290870667},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.39989998936653137},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.3084999918937683},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.29809999465942383},{"id":"https://openalex.org/C151416825","wikidata":"https://www.wikidata.org/wiki/Q934791","display_name":"Quadtree","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C2988416141","wikidata":"https://www.wikidata.org/wiki/Q6031139","display_name":"Information loss","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.2728999853134155},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.26249998807907104},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.25609999895095825},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tgrs.2025.3614370","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2025.3614370","pdf_url":null,"source":{"id":"https://openalex.org/S111326731","display_name":"IEEE Transactions on Geoscience and Remote Sensing","issn_l":"0196-2892","issn":["0196-2892","1558-0644"],"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 Transactions on Geoscience and Remote Sensing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2602230785","display_name":null,"funder_award_id":"62375133","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2839394068","display_name":null,"funder_award_id":"62471233","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3874465566","display_name":null,"funder_award_id":"30925020214","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G4891962969","display_name":null,"funder_award_id":"BE2022065-2","funder_id":"https://openalex.org/F4320327777","funder_display_name":"Jiangsu Provincial Key Research and Development Program"},{"id":"https://openalex.org/G8684068698","display_name":null,"funder_award_id":"U23B2006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327777","display_name":"Jiangsu Provincial Key Research and Development Program","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2565639579","https://openalex.org/W2601564443","https://openalex.org/W2962749812","https://openalex.org/W2962766617","https://openalex.org/W2963037989","https://openalex.org/W2963346150","https://openalex.org/W2963351448","https://openalex.org/W2963840672","https://openalex.org/W2963857746","https://openalex.org/W2964241181","https://openalex.org/W2988916019","https://openalex.org/W2989611864","https://openalex.org/W2989676862","https://openalex.org/W3013211776","https://openalex.org/W3014641072","https://openalex.org/W3016641475","https://openalex.org/W3033282154","https://openalex.org/W3034971973","https://openalex.org/W3092151103","https://openalex.org/W3096609285","https://openalex.org/W3122799380","https://openalex.org/W3168844623","https://openalex.org/W3208645658","https://openalex.org/W4213147678","https://openalex.org/W4214507171","https://openalex.org/W4283717190","https://openalex.org/W4289752563","https://openalex.org/W4312823573","https://openalex.org/W4317727254","https://openalex.org/W4321608682","https://openalex.org/W4327652243","https://openalex.org/W4379928223","https://openalex.org/W4383753161","https://openalex.org/W4387197137","https://openalex.org/W4390873840","https://openalex.org/W4391974567","https://openalex.org/W4392667193","https://openalex.org/W4393150006","https://openalex.org/W4396564062","https://openalex.org/W4401415788","https://openalex.org/W4402754006","https://openalex.org/W4402754177","https://openalex.org/W4403606929","https://openalex.org/W4406261673","https://openalex.org/W4413145332"],"related_works":[],"abstract_inverted_index":{"Small":[0],"objects":[1],"in":[2,209,213],"Unmanned":[3],"Aerial":[4],"Vehicle":[5],"(UAV)":[6],"imagery,":[7],"often":[8],"vanishing":[9],"amidst":[10],"limited":[11],"pixels,":[12],"dynamic":[13],"views,":[14],"and":[15,66,94,109,130,154,163,191,196,211],"complex":[16],"backgrounds,":[17],"present":[18],"a":[19,54,88,121,143,149,166,204],"critical":[20,139],"detection":[21,72],"challenge.":[22],"State-of-the-art":[23],"Transformer-based":[24],"detectors,":[25],"despite":[26],"their":[27,40,99],"strong":[28],"general":[29],"performance,":[30],"frequently":[31],"struggle":[32],"to":[33,62,105,137,158],"detect":[34],"these":[35,64],"small":[36,70,179],"aerial":[37,75],"targets,":[38],"with":[39,102,127],"effectiveness":[41,195],"noticeably":[42],"decreasing.":[43],"This":[44],"paper":[45],"introduces":[46],"CAEM-DETR":[47,77,202],"(Contrastive":[48],"Attention":[49],"Enhanced":[50],"Multi-domain":[51],"Detection":[52],"Transformer),":[53],"novel":[55,167],"framework":[56],"derived":[57],"from":[58,74,142],"RT-DETR,":[59],"specifically":[60],"designed":[61],"master":[63],"intricacies":[65],"deliver":[67],"significantly":[68],"improved":[69],"object":[71,180],"accuracy":[73],"perspectives.":[76],"incorporates":[78],"several":[79],"key":[80],"innovations:":[81],"(1)":[82],"DLCA":[83],"(Dynamic":[84],"Linear":[85],"Contrastive":[86],"Attention),":[87],"mechanism":[89],"that":[90,123,171],"distinctively":[91],"leverages":[92],"positive":[93],"negative":[95],"feature":[96,107],"polarities,":[97],"modeling":[98],"diverse":[100,186],"interactions":[101],"linear":[103],"complexity":[104],"enhance":[106],"contrast":[108],"refine":[110],"semantic":[111],"representations":[112],"for":[113,177],"subsequent":[114],"fusion;":[115],"(2)":[116],"MDFF":[117],"(Multi-Domain":[118],"Fidelity":[119],"Fusion),":[120],"module":[122],"synergizes":[124],"high-fidelity":[125],"downsampling":[126],"dual-domain":[128],"(spatial":[129],"frequency)":[131],"analysis,":[132],"integrating":[133],"DLCA-enhanced":[134],"polarity":[135],"information":[136],"recover":[138],"high-frequency":[140],"details":[141],"comprehensive":[144],"four-dimensional":[145],"perspective;":[146],"(3)":[147],"GRACE-Net,":[148],"backbone":[150],"employing":[151],"synergistic":[152],"multi-attention":[153],"selective":[155],"channel":[156],"modulation":[157],"capture":[159],"fine-grained":[160],"multi-scale":[161],"details;":[162],"(4)":[164],"Wise-FocalerIoU,":[165],"composite":[168],"loss":[169],"function":[170],"provides":[172],"robust,":[173],"difficulty-aware":[174],"gradient":[175],"guidance":[176],"precise":[178],"localization.":[181],"Experimental":[182],"results":[183],"on":[184],"four":[185],"datasets":[187],"(VisDrone,":[188],"AI-TOD,":[189],"SIMD,":[190],"DOTA)":[192],"demonstrate":[193],"CAEM-DETR\u2019s":[194],"generalization.":[197],"On":[198],"the":[199,218],"VisDrone":[200],"dataset,":[201],"achieves":[203],"relative":[205],"improvement":[206],"of":[207],"13.7%":[208],"AP":[210],"11.6%":[212],"AP<sub":[214],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[215],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">50</sub>":[216],"over":[217],"baseline.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}