{"id":"https://openalex.org/W4411867197","doi":"https://doi.org/10.1109/tgrs.2025.3584955","title":"MV-YOLO: An Efficient Small Object Detection Framework Based on Mamba","display_name":"MV-YOLO: An Efficient Small Object Detection Framework Based on Mamba","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411867197","doi":"https://doi.org/10.1109/tgrs.2025.3584955"},"language":"en","primary_location":{"id":"doi:10.1109/tgrs.2025.3584955","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2025.3584955","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":"https://openalex.org/A5102892179","display_name":"Shixiao Wu","orcid":"https://orcid.org/0000-0001-7110-2838"},"institutions":[{"id":"https://openalex.org/I4210111616","display_name":"Wuhan Business University","ror":"https://ror.org/0282ggx30","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210111616"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shixiao Wu","raw_affiliation_strings":["School of Information Engineering, Wuhan Business University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-7110-2838","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Wuhan Business University, Wuhan, China","institution_ids":["https://openalex.org/I4210111616"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106015030","display_name":"Xingyuan Lu","orcid":"https://orcid.org/0009-0006-1999-1395"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingyuan Lu","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","School of Computer Science & Technology, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-1999-1395","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"School of Computer Science & Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103063809","display_name":"Chengcheng Guo","orcid":"https://orcid.org/0000-0002-8948-0017"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengcheng Guo","raw_affiliation_strings":["School of Electronic Information, Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Information, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101409682","display_name":"Hong Guo","orcid":"https://orcid.org/0000-0002-5658-2244"},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Guo","raw_affiliation_strings":["School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China","institution_ids":["https://openalex.org/I136765683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5311,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.83220248,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"63","issue":null,"first_page":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9696999788284302,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9696999788284302,"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":0.6964893341064453},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5141870975494385},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4939780831336975},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.43547922372817993},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40200117230415344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3784099817276001},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.1895035207271576},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.14394015073776245}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6964893341064453},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5141870975494385},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4939780831336975},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.43547922372817993},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40200117230415344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3784099817276001},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.1895035207271576},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.14394015073776245}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tgrs.2025.3584955","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tgrs.2025.3584955","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2940459376","https://openalex.org/W3016641475","https://openalex.org/W3045700318","https://openalex.org/W4285117372","https://openalex.org/W4306916543","https://openalex.org/W4310119538","https://openalex.org/W4312576847","https://openalex.org/W4378222290","https://openalex.org/W4387350548","https://openalex.org/W4387806531","https://openalex.org/W4388096801","https://openalex.org/W4388240518","https://openalex.org/W4389300720","https://openalex.org/W4389524555","https://openalex.org/W4390357728","https://openalex.org/W4390395337","https://openalex.org/W4390873265","https://openalex.org/W4391095384","https://openalex.org/W4391559729","https://openalex.org/W4392963889","https://openalex.org/W4393185921","https://openalex.org/W4394010234","https://openalex.org/W4394938955","https://openalex.org/W4397011486","https://openalex.org/W4400353625","https://openalex.org/W4400448280","https://openalex.org/W4401672032","https://openalex.org/W4402899258","https://openalex.org/W6779709467","https://openalex.org/W6783944145","https://openalex.org/W6803444062","https://openalex.org/W6849787029","https://openalex.org/W6853816692","https://openalex.org/W6855009501","https://openalex.org/W6859298233"],"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":{"Small-object":[0],"detection":[1],"in":[2],"UAV":[3],"and":[4,23,91,101,129,143,151,157,162],"remote-sensing":[5,163],"imagery":[6],"remains":[7],"challenging":[8],"because":[9],"targets":[10],"occupy":[11],"only":[12],"a":[13,34,50],"few":[14],"pixels,":[15],"features":[16],"are":[17,20,25],"sparse,":[18],"objects":[19],"often":[21],"occluded,":[22],"backgrounds":[24],"complex.":[26],"To":[27],"tackle":[28],"these":[29],"issues,":[30],"we":[31],"propose":[32],"MV-YOLO,":[33],"lightweight,":[35],"one-stage":[36],"detector":[37],"built":[38],"from":[39],"three":[40],"complementary":[41],"modules.":[42],"First,":[43],"the":[44,59,78,94,114],"Mamba":[45],"Vision":[46],"Module":[47,118],"(MVM)":[48],"leverages":[49],"state-space":[51],"model":[52],"to":[53,73,97,105,123],"capture":[54],"global":[55],"contextual":[56],"dependencies":[57],"across":[58],"feature":[60,127],"map":[61],"with":[62,132],"linear":[63],"complexity,":[64],"while":[65],"its":[66],"variant":[67],"(MSAVM)":[68],"further":[69],"incorporates":[70],"multi-head":[71],"self-attention":[72],"enhance":[74],"long-range":[75],"interactions.":[76],"Second,":[77],"Bio-inspired":[79],"Hierarchical":[80],"Feature":[81],"Modulation":[82],"(BHFM)":[83],"module":[84],"decomposes":[85],"large":[86],"convolutional":[87],"kernels":[88],"into":[89],"asymmetric":[90],"dilated":[92],"convolutions\u2014expanding":[93],"receptive":[95],"field":[96],"19\u00d719\u2014alongside":[98],"parallel":[99],"spatial":[100],"channel":[102],"attention":[103],"branches":[104],"retain":[106],"high-frequency":[107],"details":[108],"crucial":[109],"for":[110,159],"small":[111],"objects.":[112],"Third,":[113],"Context":[115],"Clue":[116],"Guided":[117],"(CCGM)":[119],"learns":[120],"sampling":[121],"offsets":[122],"dynamically":[124],"upsample":[125],"low-resolution":[126],"maps":[128],"fuses":[130],"them":[131],"high-resolution":[133],"features,":[134],"sharpening":[135],"small-object":[136],"representations.":[137],"Extensive":[138],"experiments":[139],"on":[140],"VisDrone2019,":[141],"DIOR,":[142],"UCAS-AOD":[144],"achieve":[145],"mAP50":[146],"scores":[147],"of":[148],"50.6%,":[149],"89.7%,":[150],"97.6%,":[152],"respectively,":[153],"demonstrating":[154],"MV-YOLO\u2019s":[155],"efficiency":[156],"effectiveness":[158],"real-world":[160],"aerial":[161],"applications.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}