{"id":"https://openalex.org/W4396738701","doi":"https://doi.org/10.1007/s40747-024-01448-6","title":"TA-YOLO: a lightweight small object detection model based on multi-dimensional trans-attention module for remote sensing images","display_name":"TA-YOLO: a lightweight small object detection model based on multi-dimensional trans-attention module for remote sensing images","publication_year":2024,"publication_date":"2024-05-08","ids":{"openalex":"https://openalex.org/W4396738701","doi":"https://doi.org/10.1007/s40747-024-01448-6"},"language":"en","primary_location":{"id":"doi:10.1007/s40747-024-01448-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-024-01448-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01448-6.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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & 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/s40747-024-01448-6.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103279435","display_name":"Minze Li","orcid":"https://orcid.org/0009-0004-2537-9982"},"institutions":[{"id":"https://openalex.org/I4210106541","display_name":"Chengdu Organic Chemicals (China)","ror":"https://ror.org/01nmxvn49","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210106541"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Minze Li","raw_affiliation_strings":["Chengdu Techman Sofeware Co., Ltd, Chengdu, 610100, People\u2019s Republic of China","Chengdu Techman Sofeware Co., Ltd, Chengdu, 610100, People's Republic of China"],"affiliations":[{"raw_affiliation_string":"Chengdu Techman Sofeware Co., Ltd, Chengdu, 610100, People\u2019s Republic of China","institution_ids":["https://openalex.org/I4210106541"]},{"raw_affiliation_string":"Chengdu Techman Sofeware Co., Ltd, Chengdu, 610100, People's Republic of China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028173524","display_name":"Yuling Chen","orcid":"https://orcid.org/0000-0003-0628-1651"},"institutions":[{"id":"https://openalex.org/I1297991670","display_name":"Southwest University of Science and Technology","ror":"https://ror.org/04d996474","country_code":"CN","type":"education","lineage":["https://openalex.org/I1297991670"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuling Chen","raw_affiliation_strings":["School of Information Engineering, Southwest University of Science and Technology, Mianyang, 621010, People\u2019s Republic of China","School of Information Engineering, Southwest University of Science and Technology, Mianyang, 621010, People's Republic of China"],"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Southwest University of Science and Technology, Mianyang, 621010, People\u2019s Republic of China","institution_ids":["https://openalex.org/I1297991670"]},{"raw_affiliation_string":"School of Information Engineering, Southwest University of Science and Technology, Mianyang, 621010, People's Republic of China","institution_ids":["https://openalex.org/I1297991670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100626204","display_name":"Tao Zhang","orcid":"https://orcid.org/0000-0003-0750-0123"},"institutions":[{"id":"https://openalex.org/I4210106541","display_name":"Chengdu Organic Chemicals (China)","ror":"https://ror.org/01nmxvn49","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210106541"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Zhang","raw_affiliation_strings":["Chengdu Techman Sofeware Co., Ltd, Chengdu, 610100, People\u2019s Republic of China","Chengdu Techman Sofeware Co., Ltd, Chengdu, 610100, People's Republic of China"],"affiliations":[{"raw_affiliation_string":"Chengdu Techman Sofeware Co., Ltd, Chengdu, 610100, People\u2019s Republic of China","institution_ids":["https://openalex.org/I4210106541"]},{"raw_affiliation_string":"Chengdu Techman Sofeware Co., Ltd, Chengdu, 610100, People's Republic of China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034420107","display_name":"Wu Huang","orcid":"https://orcid.org/0000-0002-2525-6454"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]},{"id":"https://openalex.org/I4210106541","display_name":"Chengdu Organic Chemicals (China)","ror":"https://ror.org/01nmxvn49","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210106541"]},{"id":"https://openalex.org/I4210125143","display_name":"Chengdu University","ror":"https://ror.org/034z67559","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210125143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu Huang","raw_affiliation_strings":["Chengdu Techman Sofeware Co., Ltd, Chengdu, 610100, People\u2019s Republic of China","School of Computer Science, Sichuan University, Chengdu, 610065, People\u2019s Republic of China","Chengdu Techman Sofeware Co., Ltd, Chengdu, 610100, People's Republic of China"],"affiliations":[{"raw_affiliation_string":"Chengdu Techman Sofeware Co., Ltd, Chengdu, 610100, People\u2019s Republic of China","institution_ids":["https://openalex.org/I4210106541"]},{"raw_affiliation_string":"School of Computer Science, Sichuan University, Chengdu, 610065, People\u2019s Republic of China","institution_ids":["https://openalex.org/I24185976","https://openalex.org/I4210125143"]},{"raw_affiliation_string":"Chengdu Techman Sofeware Co., Ltd, Chengdu, 610100, People's Republic of China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103279435"],"corresponding_institution_ids":["https://openalex.org/I4210106541"],"apc_list":{"value":1320,"currency":"GBP","value_usd":1619},"apc_paid":{"value":1320,"currency":"GBP","value_usd":1619},"fwci":13.1876,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.99317627,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"10","issue":"4","first_page":"5459","last_page":"5473"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9980000257492065,"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/computer-science","display_name":"Computer science","score":0.8061658143997192},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5767515301704407},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5580356121063232},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5299105644226074},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.474398136138916},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4317498505115509},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.354489803314209}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8061658143997192},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5767515301704407},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5580356121063232},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5299105644226074},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.474398136138916},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4317498505115509},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.354489803314209},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s40747-024-01448-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-024-01448-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01448-6.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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:cac493ca70fb4bd29d25dbc2089b3562","is_oa":true,"landing_page_url":"https://doaj.org/article/cac493ca70fb4bd29d25dbc2089b3562","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 10, Iss 4, Pp 5459-5473 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s40747-024-01448-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-024-01448-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01448-6.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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396738701.pdf"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W2031489346","https://openalex.org/W2102605133","https://openalex.org/W2193145675","https://openalex.org/W2288122362","https://openalex.org/W2570343428","https://openalex.org/W2579152745","https://openalex.org/W2752782242","https://openalex.org/W2754198511","https://openalex.org/W2883780447","https://openalex.org/W2884585870","https://openalex.org/W2896155169","https://openalex.org/W2962849972","https://openalex.org/W2962858109","https://openalex.org/W2963037989","https://openalex.org/W2963125010","https://openalex.org/W2963150697","https://openalex.org/W2963163009","https://openalex.org/W2963351448","https://openalex.org/W2982083293","https://openalex.org/W2985384565","https://openalex.org/W2990230185","https://openalex.org/W2995484963","https://openalex.org/W3033983932","https://openalex.org/W3035414587","https://openalex.org/W3099576037","https://openalex.org/W3106250896","https://openalex.org/W3177052299","https://openalex.org/W3217060323","https://openalex.org/W4285104158","https://openalex.org/W4312349930","https://openalex.org/W4313537271","https://openalex.org/W4315778358","https://openalex.org/W4319066581","https://openalex.org/W4319300947","https://openalex.org/W4320002812","https://openalex.org/W4360839569","https://openalex.org/W4385299230","https://openalex.org/W4386076325","https://openalex.org/W6600013530","https://openalex.org/W6604344240","https://openalex.org/W6610122945"],"related_works":["https://openalex.org/W3147584709","https://openalex.org/W2977677679","https://openalex.org/W1992327129","https://openalex.org/W2381986121","https://openalex.org/W2370918718","https://openalex.org/W2256933480","https://openalex.org/W2027854990","https://openalex.org/W2755342338","https://openalex.org/W2370081953","https://openalex.org/W2779427294"],"abstract_inverted_index":{"Abstract":[0],"Object":[1],"detection":[2,13,109,228,242],"plays":[3],"a":[4,46,66,95,134,161,183,226,238],"vital":[5],"role":[6],"in":[7,18,45,103,122,150,157,160,174,194],"remote":[8,30,76,118,247],"sensing":[9,31,34,119,248],"applications.":[10],"Although":[11],"object":[12,108,241],"has":[14,251],"achieved":[15],"proud":[16],"results":[17,44,278],"natural":[19,106],"images,":[20],"these":[21],"methods":[22],"are":[23],"difficult":[24],"to":[25,29,58,86,117,124,138,164,168,186,190,196,208],"be":[26,100],"directly":[27],"applied":[28],"images.":[32,120,249],"Remote":[33],"images":[35],"often":[36],"have":[37],"complex":[38,53],"backgrounds":[39],"and":[40,52,69,82,128,176,213,230,259,266,273,287],"small":[41,240],"objects,":[42],"which":[43,74],"highly":[47],"unbalanced":[48],"distribution":[49],"of":[50,144,172,283,291],"foreground":[51],"background":[54],"information.":[55],"In":[56,178],"order":[57,123,195],"solve":[59],"the":[60,80,88,145,165,170,220,232,255,263,280,284,288],"above":[61],"problems,":[62],"this":[63,179],"paper":[64],"proposes":[65],"multi-head":[67,184],"channel":[68,81],"spatial":[70,83],"trans-attention":[71,155,221,285],"(MCSTA)":[72],"module,":[73],"performs":[75],"pixel":[77],"interaction":[78],"from":[79],"dimensions":[84,159],"respectively":[85],"complete":[87],"attention":[89,205],"feature":[90,130,233],"capture":[91,169],"function.":[92],"It":[93,250],"is":[94],"plug-and-play":[96],"module":[97,222,286],"that":[98],"can":[99],"easily":[101],"embedded":[102,219],"any":[104],"other":[105],"image":[107],"convolutional":[110],"neural":[111],"network,":[112],"making":[113],"it":[114],"quickly":[115],"applicable":[116],"First,":[121],"reduce":[125,209],"computational":[126],"complexity":[127],"improve":[129,191],"richness,":[131],"we":[132,153,181,201,218],"use":[133,182],"special":[135],"linear":[136],"convolution":[137],"obtain":[139,154],"three":[140],"projection":[141],"features":[142,173],"instead":[143],"simple":[146],"matrix":[147,199],"multiplication":[148],"transformation":[149],"Transformer.":[151],"Second,":[152],"maps":[156],"different":[158],"manner":[162],"similar":[163],"self-attention":[166],"mechanism":[167,185],"interrelationships":[171],"channels":[175],"spaces.":[177],"process,":[180],"perform":[187],"parallel":[188],"operations":[189],"speed.":[192,216],"Furthermore,":[193],"avoid":[197],"large-scale":[198],"operations,":[200],"specially":[202],"designed":[203],"an":[204],"blocking":[206],"mode":[207],"computer":[210],"memory":[211],"usage":[212],"increase":[214],"operation":[215],"Finally,":[217],"into":[223],"YOLOv8,":[224,258],"added":[225],"new":[227],"head":[229],"optimized":[231],"fusion":[234],"method,":[235],"thus":[236],"designing":[237],"lightweight":[239],"model":[243,257],"named":[244],"TA-YOLO":[245],"for":[246],"fewer":[252],"parameters":[253],"than":[254],"benchmark":[256],"its":[260],"mAP":[261],"on":[262],"PASCAL":[264],"VOC":[265],"VisDrone":[267],"data":[268],"sets":[269],"increased":[270],"by":[271],"1.3%":[272],"6.2%":[274],"respectively.":[275],"The":[276],"experimental":[277],"prove":[279],"powerful":[281],"function":[282],"excellent":[289],"performance":[290],"TA-YOLO.":[292]},"counts_by_year":[{"year":2026,"cited_by_count":16},{"year":2025,"cited_by_count":30},{"year":2024,"cited_by_count":8}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}