{"id":"https://openalex.org/W4416249582","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228131","title":"The Improved Algorithm of RT-DETR Based on Multi-Head Attention Mechanism","display_name":"The Improved Algorithm of RT-DETR Based on Multi-Head Attention Mechanism","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416249582","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228131"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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":"https://openalex.org/A5100391493","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-6976-4004"},"institutions":[{"id":"https://openalex.org/I168337820","display_name":"Chongqing University of Science and Technology","ror":"https://ror.org/03n3v6d52","country_code":"CN","type":"education","lineage":["https://openalex.org/I168337820"]},{"id":"https://openalex.org/I50632499","display_name":"Chongqing University of Technology","ror":"https://ror.org/04vgbd477","country_code":"CN","type":"education","lineage":["https://openalex.org/I50632499"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Chongqing University of Technology,School of Computer Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University of Technology,School of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I168337820","https://openalex.org/I50632499"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuntian Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I168337820","display_name":"Chongqing University of Science and Technology","ror":"https://ror.org/03n3v6d52","country_code":"CN","type":"education","lineage":["https://openalex.org/I168337820"]},{"id":"https://openalex.org/I50632499","display_name":"Chongqing University of Technology","ror":"https://ror.org/04vgbd477","country_code":"CN","type":"education","lineage":["https://openalex.org/I50632499"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuntian Jiang","raw_affiliation_strings":["Chongqing University of Technology,School of Computer Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University of Technology,School of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I168337820","https://openalex.org/I50632499"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058277555","display_name":"S. Wang","orcid":"https://orcid.org/0009-0006-1477-5343"},"institutions":[{"id":"https://openalex.org/I168337820","display_name":"Chongqing University of Science and Technology","ror":"https://ror.org/03n3v6d52","country_code":"CN","type":"education","lineage":["https://openalex.org/I168337820"]},{"id":"https://openalex.org/I50632499","display_name":"Chongqing University of Technology","ror":"https://ror.org/04vgbd477","country_code":"CN","type":"education","lineage":["https://openalex.org/I50632499"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shixinyu Wang","raw_affiliation_strings":["Chongqing University of Technology,School of Computer Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University of Technology,School of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I168337820","https://openalex.org/I50632499"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8295999765396118,"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":0.8295999765396118,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.045499999076128006,"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/T11038","display_name":"Advanced SAR Imaging Techniques","score":0.00800000037997961,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6488000154495239},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6363999843597412},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6323000192642212},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.536300003528595},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.4837000072002411},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.42309999465942383},{"id":"https://openalex.org/keywords/drone","display_name":"Drone","score":0.41920000314712524},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4050000011920929},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39809998869895935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7634000182151794},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6488000154495239},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6363999843597412},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6323000192642212},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5878999829292297},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.536300003528595},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.4837000072002411},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43470001220703125},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.42309999465942383},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.41920000314712524},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4050000011920929},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39809998869895935},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3959999978542328},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.391400009393692},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.38830000162124634},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.3822000026702881},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.37400001287460327},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32829999923706055},{"id":"https://openalex.org/C117623542","wikidata":"https://www.wikidata.org/wiki/Q621974","display_name":"Automatic target recognition","level":3,"score":0.32260000705718994},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.2815999984741211},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.262800008058548}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W2102605133","https://openalex.org/W2194775991","https://openalex.org/W2765793020","https://openalex.org/W2996492103","https://openalex.org/W3044338123","https://openalex.org/W3096609285","https://openalex.org/W3171038842","https://openalex.org/W4312312588","https://openalex.org/W4386076079","https://openalex.org/W4386076325","https://openalex.org/W4386076539","https://openalex.org/W4390872550","https://openalex.org/W4402754006"],"related_works":[],"abstract_inverted_index":{"Romote":[0],"sensing":[1],"image":[2],"target":[3,12,40,95],"detection":[4,41],"faces":[5],"challenges":[6],"such":[7],"as":[8],"complex":[9],"backgrounds,":[10],"small":[11,94],"sizes,":[13],"blurred":[14],"edges,":[15],"and":[16,74,141,149,151,191],"hardware":[17],"deployment":[18],"constraints.":[19],"This":[20],"requires":[21],"deep":[22],"learning-based":[23],"algorithms":[24],"to":[25,85,101,135,146],"maintain":[26],"high":[27],"efficiency":[28],"while":[29,184],"ensuring":[30],"lightweight":[31,53],"performance.":[32],"To":[33],"address":[34],"this,":[35],"we":[36,50,117],"propose":[37,118],"a":[38,52,130,169,174,179],"drone":[39],"algorithm":[42],"based":[43],"on":[44,199],"an":[45,193],"improved":[46],"RT-DETR":[47,91],"architecture\u2014CCD-DETR.":[48],"First,":[49],"introduce":[51],"backbone":[54],"feature":[55,99,114,126,157],"extraction":[56,127],"module,":[57,121],"CGAE,":[58],"which":[59,122],"provides":[60],"diverse":[61],"full-feature":[62],"segmentation":[63],"for":[64,93],"the":[65,70,76,86,90,98,103,107,119,124,154,165,186,200],"attention":[66],"heads,":[67],"significantly":[68],"reducing":[69,185],"model's":[71,125],"parameter":[72,187],"count":[73,188],"enhancing":[75,153],"diversity":[77],"of":[78,196],"attention.":[79],"Additionally,":[80],"structural":[81],"improvements":[82],"are":[83],"made":[84],"CCFM":[87],"module":[88],"in":[89,172,177,182],"encoder":[92],"detection,":[96],"allowing":[97],"layers":[100],"reach":[102],"S2":[104],"stage":[105],"during":[106],"fusion":[108,158],"process,":[109],"thereby":[110,143],"achieving":[111,192],"more":[112],"targeted":[113],"extraction.":[115],"Finally,":[116],"Fusion-D":[120],"enhances":[123],"capabilities":[128],"through":[129],"multi-branch":[131],"structure,":[132],"enabling":[133],"it":[134],"capture":[136],"information":[137],"from":[138],"multiple":[139],"angles":[140],"levels,":[142],"improving":[144],"sensitivity":[145],"different":[147],"targets":[148],"features":[150],"further":[152],"network's":[155],"scale":[156],"capabilities.":[159],"Comprehensive":[160],"experimental":[161],"results":[162],"show":[163],"that":[164],"CCD-DETR":[166],"model":[167],"achieves":[168],"2.2%":[170],"increase":[171,176,181],"mAP0.5,":[173],"1.8%":[175,180],"mAPs[0.5:0.95],":[178],"mAP[0.5:0.95],":[183],"by":[189],"29.1%,":[190],"inference":[194],"speed":[195],"67.1":[197],"FPS":[198],"VisDrone2019":[201],"dataset.":[202]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}