{"id":"https://openalex.org/W4410586737","doi":"https://doi.org/10.1007/s40747-025-01904-x","title":"A lightweight mechanism for vision-transformer-based object detection","display_name":"A lightweight mechanism for vision-transformer-based object detection","publication_year":2025,"publication_date":"2025-05-22","ids":{"openalex":"https://openalex.org/W4410586737","doi":"https://doi.org/10.1007/s40747-025-01904-x"},"language":"en","primary_location":{"id":"doi:10.1007/s40747-025-01904-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-01904-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-01904-x.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex &amp; Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-01904-x.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057303083","display_name":"Yanming Ye","orcid":"https://orcid.org/0009-0001-8461-9956"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yanming Ye","raw_affiliation_strings":["School of Computer Science, Hangzhou Dianzi University, Hangzhou, 310018, Zhejiang, China","School of Information Engineering, Hangzhou Dianzi University, Hangzhou, 311305, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Hangzhou Dianzi University, Hangzhou, 310018, Zhejiang, China","institution_ids":["https://openalex.org/I50760025"]},{"raw_affiliation_string":"School of Information Engineering, Hangzhou Dianzi University, Hangzhou, 311305, Zhejiang, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101812855","display_name":"Qiang Sun","orcid":"https://orcid.org/0000-0002-4182-6533"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Sun","raw_affiliation_strings":["School of Information Engineering, Hangzhou Dianzi University, Hangzhou, 311305, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Hangzhou Dianzi University, Hangzhou, 311305, Zhejiang, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kailong Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kailong Cheng","raw_affiliation_strings":["School of Computer Science, Hangzhou Dianzi University, Hangzhou, 310018, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Hangzhou Dianzi University, Hangzhou, 310018, Zhejiang, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089504286","display_name":"Xingfa Shen","orcid":"https://orcid.org/0000-0002-6419-9149"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingfa Shen","raw_affiliation_strings":["School of Computer Science, Hangzhou Dianzi University, Hangzhou, 310018, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Hangzhou Dianzi University, Hangzhou, 310018, Zhejiang, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043738330","display_name":"Dongjing Wang","orcid":"https://orcid.org/0000-0003-2152-0446"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongjing Wang","raw_affiliation_strings":["School of Computer Science, Hangzhou Dianzi University, Hangzhou, 310018, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Hangzhou Dianzi University, Hangzhou, 310018, Zhejiang, China","institution_ids":["https://openalex.org/I50760025"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5057303083"],"corresponding_institution_ids":["https://openalex.org/I50760025"],"apc_list":{"value":1320,"currency":"GBP","value_usd":1619},"apc_paid":{"value":1320,"currency":"GBP","value_usd":1619},"fwci":4.6519,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.94779811,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"11","issue":"7","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9990000128746033,"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":0.9990000128746033,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T14319","display_name":"Currency Recognition and Detection","score":0.9957000017166138,"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/mechanism","display_name":"Mechanism (biology)","score":0.5704825520515442},{"id":"https://openalex.org/keywords/computational-intelligence","display_name":"Computational intelligence","score":0.5430975556373596},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5385260581970215},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5029682517051697},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46428051590919495},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.45208656787872314},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2655271291732788},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.12363195419311523},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11726009845733643},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.05649924278259277}],"concepts":[{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.5704825520515442},{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.5430975556373596},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5385260581970215},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5029682517051697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46428051590919495},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45208656787872314},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2655271291732788},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.12363195419311523},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11726009845733643},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.05649924278259277},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s40747-025-01904-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-01904-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-01904-x.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex &amp; Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:0d256830a6dd43c0a7ef04893be5f3fd","is_oa":true,"landing_page_url":"https://doaj.org/article/0d256830a6dd43c0a7ef04893be5f3fd","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Complex & Intelligent Systems, Vol 11, Iss 7, Pp 1-12 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s40747-025-01904-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-01904-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-01904-x.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex &amp; Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5501497924","display_name":null,"funder_award_id":"62072121","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G635663060","display_name":null,"funder_award_id":"62072121","funder_id":"https://openalex.org/F4320315254","funder_display_name":"Innovative Research Group Project of the National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320315254","display_name":"Innovative Research Group Project of the National Natural Science Foundation of China","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410586737.pdf","grobid_xml":"https://content.openalex.org/works/W4410586737.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2031489346","https://openalex.org/W2120432001","https://openalex.org/W2806070179","https://openalex.org/W2950952672","https://openalex.org/W2963037989","https://openalex.org/W2982770724","https://openalex.org/W2991044292","https://openalex.org/W3015220510","https://openalex.org/W3021542222","https://openalex.org/W3033529678","https://openalex.org/W3034971973","https://openalex.org/W3096609285","https://openalex.org/W3106728613","https://openalex.org/W3107331169","https://openalex.org/W3120031785","https://openalex.org/W3122239467","https://openalex.org/W3130976481","https://openalex.org/W3137648958","https://openalex.org/W3158661000","https://openalex.org/W3211490618","https://openalex.org/W4206961919","https://openalex.org/W4282982481","https://openalex.org/W4285531802","https://openalex.org/W4285787431","https://openalex.org/W4287393128","https://openalex.org/W4295838474","https://openalex.org/W4306291595","https://openalex.org/W4323654151","https://openalex.org/W4366779939","https://openalex.org/W4377241880","https://openalex.org/W4379386152","https://openalex.org/W4388540250","https://openalex.org/W6601076540"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Abstract":[0],"DETR":[1,42,209],"(DEtection":[2],"TRansformer)":[3],"is":[4],"a":[5,17,98,161,305,320],"CV":[6],"model":[7,102,152,233],"for":[8],"object":[9,49,100,239],"detection":[10,39,78,101],"that":[11,175],"replaces":[12],"traditional":[13],"complex":[14],"methods":[15],"with":[16,71,96,150],"Transformer":[18],"architecture,":[19,164],"and":[20,32,47,59,65,92,113,119,184,195,213,253,280],"has":[21],"achieved":[22],"significant":[23],"improvement":[24],"over":[25,293],"previous":[26],"methods,":[27],"particularly":[28],"in":[29,45,124,237],"handling":[30],"small":[31,46,58,238],"medium-sized":[33,48,60],"objects.":[34],"However,":[35],"the":[36,72,86,108,130,144,157],"attention":[37,109],"mechanism-based":[38],"framework":[40],"of":[41,57,322],"exhibits":[43],"limitations":[44],"detection.":[50],"It":[51],"struggles":[52],"to":[53,135,302,309,318],"extract":[54],"fine-grained":[55],"details":[56],"objects":[61],"from":[62,133,316],"low-resolution":[63],"features,":[64],"its":[66],"computational":[67,111,131,167,296,327],"complexity":[68,115,132],"increases":[69],"significantly":[70,165,325],"input":[73],"scale,":[74],"thereby":[75],"constraining":[76],"real-time":[77],"efficiency.":[79,328],"To":[80],"address":[81],"these":[82],"limitations,":[83],"we":[84],"introduce":[85],"Cross":[87],"Feature":[88],"Attention":[89],"(XFA)":[90],"mechanism":[91],"propose":[93],"XFCOS":[94,142,176,191,298],"(XFA-based":[95],"FCOS),":[97],"novel":[99],"built":[103],"upon":[104],"it.":[105],"XFA":[106,155],"simplifies":[107],"mechanism\u2019s":[110],"process":[112],"reduces":[114,129,299],"through":[116],"L2":[117],"normalization":[118],"two":[120],"one-dimensional":[121],"convolutions":[122],"applied":[123],"different":[125],"directions.":[126],"This":[127,324],"design":[128],"quadratic":[134],"linear":[136],"while":[137,180,312],"preserving":[138],"spatial":[139],"context":[140],"awareness.":[141],"enhances":[143,326],"original":[145],"TSP-FCOS":[146],"(Transformer-based":[147],"Set":[148],"Prediction":[149],"FCOS)":[151],"by":[153,210],"integrating":[154],"into":[156],"transformer":[158],"encoder,":[159],"creating":[160],"CNN-ViT":[162],"hybrid":[163],"reducing":[166],"costs":[168],"without":[169],"sacrificing":[170],"accuracy.":[171],"Extensive":[172],"experiments":[173],"demonstrate":[174],"achieves":[177],"state-of-the-art":[178],"performance":[179],"addressing":[181],"DETR\u2019s":[182],"convergence":[183],"efficiency":[185],"limitations.":[186],"On":[187],"Pascal":[188],"VOC":[189],"2007,":[190],"attains":[192],"54.7":[193],"AP":[194,197,212,215,243,255,270,282],"60.7":[196],"$$_\\textrm{75}$$":[198,216],"<mml:math":[199,217,245,257,272,284],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\">":[200,218,246,258,273,285],"<mml:mmultiscripts>":[201,219,247,259,274,286],"<mml:mrow/>":[202,204,220,222,248,250,260,262,275,277,287,289],"<mml:mtext>75</mml:mtext>":[203,221],"</mml:mmultiscripts>":[205,223,251,263,278,290],"</mml:math>":[206,224,252,264,279,291],"-":[207],"surpassing":[208],"4.5":[211],"7.9":[214],"respectively,":[225],"establishing":[226],"new":[227],"benchmarks":[228],"among":[229],"ResNet-50-based":[230],"detectors.":[231],"The":[232],"shows":[234],"particular":[235],"strength":[236],"detection,":[240],"achieving":[241],"24.0":[242],"$$_\\textrm{S}$$":[244,271],"<mml:mtext>S</mml:mtext>":[249,276],"43.9":[254],"$$_\\textrm{M}$$":[256],"<mml:mtext>M</mml:mtext>":[261,288],"on":[265],"COCO":[266],"2017,":[267],"representing":[268,304],"3.3":[269],"3.8":[281],"$$_{\\textrm{M}}$$":[283],"improvements":[292],"DETR.":[294],"Through":[295],"optimization,":[297],"encoder":[300],"FLOPs":[301],"13.5G,":[303],"17.2%":[306],"decrease":[307],"compared":[308],"TSP-FCOS\u2019s":[310],"16.3G,":[311],"cutting":[313],"activation":[314],"memory":[315],"285.78":[317],"264.64M,":[319],"reduction":[321],"7.4%.":[323]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
