{"id":"https://openalex.org/W4407139450","doi":"https://doi.org/10.2298/csis241110011y","title":"Multimodal deep learning-based feature fusion for object detection in remote sensing images","display_name":"Multimodal deep learning-based feature fusion for object detection in remote sensing images","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4407139450","doi":"https://doi.org/10.2298/csis241110011y"},"language":"en","primary_location":{"id":"doi:10.2298/csis241110011y","is_oa":true,"landing_page_url":"https://doi.org/10.2298/csis241110011y","pdf_url":"http://www.doiserbia.nb.rs/ft.aspx?id=1820-02142500011Y","source":{"id":"https://openalex.org/S206939107","display_name":"Computer Science and Information Systems","issn_l":"1820-0214","issn":["1820-0214","2406-1018"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310321031","host_organization_name":"ComSIS Consortium","host_organization_lineage":["https://openalex.org/P4310321031"],"host_organization_lineage_names":["ComSIS Consortium"],"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":"Computer Science and Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"http://www.doiserbia.nb.rs/ft.aspx?id=1820-02142500011Y","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041576447","display_name":"Shoulin Yin","orcid":"https://orcid.org/0000-0002-5367-1372"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shoulin Yin","raw_affiliation_strings":["College of Information and Communication Engineering, Harbin Engineering University, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information and Communication Engineering, Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005729523","display_name":"Qunming Wang","orcid":"https://orcid.org/0000-0002-5188-0939"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qunming Wang","raw_affiliation_strings":["College of Surveying and Geo-informatics, Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Surveying and Geo-informatics, Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100636411","display_name":"Liguo Wang","orcid":"https://orcid.org/0000-0001-9373-6233"},"institutions":[{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liguo Wang","raw_affiliation_strings":["College of Information and Communications Engineering, Dalian Minzu University, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information and Communications Engineering, Dalian Minzu University, Dalian, China","institution_ids":["https://openalex.org/I61565387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000856508","display_name":"Mirjana Ivanovi\u0107","orcid":"https://orcid.org/0000-0003-1946-0384"},"institutions":[{"id":"https://openalex.org/I170726198","display_name":"University of Novi Sad","ror":"https://ror.org/00xa57a59","country_code":"RS","type":"education","lineage":["https://openalex.org/I170726198"]}],"countries":["RS"],"is_corresponding":false,"raw_author_name":"Mirjana Ivanovic","raw_affiliation_strings":["Faculty of Sciences, University of Novi Sad, Serbia"],"raw_orcid":"https://orcid.org/0000-0003-1946-0384","affiliations":[{"raw_affiliation_string":"Faculty of Sciences, University of Novi Sad, Serbia","institution_ids":["https://openalex.org/I170726198"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100455129","display_name":"Hang Li","orcid":"https://orcid.org/0000-0002-1230-4007"},"institutions":[{"id":"https://openalex.org/I32399674","display_name":"Shenyang Normal University","ror":"https://ror.org/05cdfgm80","country_code":"CN","type":"education","lineage":["https://openalex.org/I32399674"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Li","raw_affiliation_strings":["Software College, Shenyang Normal University Shenyang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Software College, Shenyang Normal University Shenyang, China","institution_ids":["https://openalex.org/I32399674"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1231,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.73798287,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"22","issue":"1","first_page":"327","last_page":"344"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.993399977684021,"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":0.993399977684021,"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.9891999959945679,"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"}},{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.9886000156402588,"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":0.9083520174026489},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7005980014801025},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.574024498462677},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5594919323921204},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5519747138023376},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5419747233390808},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5003602504730225},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4948350787162781},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4489428997039795}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9083520174026489},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7005980014801025},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.574024498462677},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5594919323921204},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5519747138023376},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5419747233390808},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5003602504730225},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4948350787162781},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4489428997039795},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.2298/csis241110011y","is_oa":true,"landing_page_url":"https://doi.org/10.2298/csis241110011y","pdf_url":"http://www.doiserbia.nb.rs/ft.aspx?id=1820-02142500011Y","source":{"id":"https://openalex.org/S206939107","display_name":"Computer Science and Information Systems","issn_l":"1820-0214","issn":["1820-0214","2406-1018"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310321031","host_organization_name":"ComSIS Consortium","host_organization_lineage":["https://openalex.org/P4310321031"],"host_organization_lineage_names":["ComSIS Consortium"],"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":"Computer Science and Information Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.2298/csis241110011y","is_oa":true,"landing_page_url":"https://doi.org/10.2298/csis241110011y","pdf_url":"http://www.doiserbia.nb.rs/ft.aspx?id=1820-02142500011Y","source":{"id":"https://openalex.org/S206939107","display_name":"Computer Science and Information Systems","issn_l":"1820-0214","issn":["1820-0214","2406-1018"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310321031","host_organization_name":"ComSIS Consortium","host_organization_lineage":["https://openalex.org/P4310321031"],"host_organization_lineage_names":["ComSIS Consortium"],"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":"Computer Science and Information Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407139450.pdf","grobid_xml":"https://content.openalex.org/works/W4407139450.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1617332088","https://openalex.org/W2012664213","https://openalex.org/W2089201654","https://openalex.org/W2115414933","https://openalex.org/W2152803642","https://openalex.org/W2170056261","https://openalex.org/W2271799811","https://openalex.org/W2798990097","https://openalex.org/W2884367402","https://openalex.org/W2910688461","https://openalex.org/W2987144017","https://openalex.org/W2989676862","https://openalex.org/W3004605831","https://openalex.org/W3009818596","https://openalex.org/W3013467123","https://openalex.org/W3034099097","https://openalex.org/W3087807709","https://openalex.org/W3088621547","https://openalex.org/W3092244643","https://openalex.org/W3117263089","https://openalex.org/W3158879875","https://openalex.org/W3200491398","https://openalex.org/W3201797941","https://openalex.org/W3207235916","https://openalex.org/W3212216520","https://openalex.org/W4210692332","https://openalex.org/W4214815245","https://openalex.org/W4223418560","https://openalex.org/W4280612217","https://openalex.org/W4285251596","https://openalex.org/W4291819654","https://openalex.org/W4319341864"],"related_works":["https://openalex.org/W4375867731","https://openalex.org/W2611989081","https://openalex.org/W2949096641","https://openalex.org/W2970686063","https://openalex.org/W4320729701","https://openalex.org/W4254103348","https://openalex.org/W3210378990","https://openalex.org/W3034745255","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"Object":[0,101],"detection":[1,81,99,102,161,288,302],"is":[2,9,17,20,82,136,140,172,180,234,283],"an":[3,32,48,227],"important":[4],"computer":[5,114],"vision":[6,115],"task,":[7],"which":[8],"developed":[10],"from":[11],"image":[12,49,119,121,224,300],"classification":[13,38],"task.":[14,303],"The":[15,263],"difference":[16],"that":[18,44,267],"it":[19,139],"no":[21],"longer":[22],"only":[23],"to":[24,35,56,60,66,142,185,192,213,236],"classify":[25],"a":[26,153,292],"single":[27],"type":[28],"of":[29,41,71,76,196,205],"object":[30,80,123,130,160,301],"in":[31,47,162,296],"image,":[33],"but":[34],"complete":[36],"the":[37,51,61,68,72,77,108,132,167,173,194,202,206,268,286,297],"and":[39,63,85,125,138,200,222,244,260,273,280],"positioning":[40,64],"multiple":[42],"objects":[43],"may":[45],"exist":[46],"at":[50],"same":[52],"time.":[53],"Classification":[54],"refers":[55,65],"assigning":[57],"category":[58],"labels":[59],"object,":[62],"determining":[67],"vertex":[69],"coordinates":[70],"peripheral":[73],"rectangular":[74],"box":[75],"object.":[78],"Therefore,":[79],"more":[83,112],"challenging":[84],"has":[86,291],"broader":[87],"application":[88,294],"prospects,":[89],"such":[90,117],"as":[91,107,118],"automatic":[92],"driving,":[93],"face":[94],"recognition,":[95],"pedestrian":[96],"detection,":[97,131],"medical":[98],"etc,.":[100],"can":[103],"also":[104],"be":[105,143],"used":[106,235],"research":[109],"basis":[110],"for":[111,159,182],"complex":[113],"task":[116],"segmentation,":[120],"description,":[122],"tracking":[124],"action":[126],"recognition.":[127],"In":[128,166,190],"traditional":[129],"feature":[133,157,183,187],"utilization":[134],"rate":[135],"low":[137],"easy":[141],"affected":[144],"by":[145],"other":[146,274],"environmental":[147],"factors.":[148],"Hence,":[149],"this":[150],"paper":[151],"proposes":[152],"multimodal":[154],"deep":[155],"learning-based":[156],"fusion":[158,184],"remote":[163,298],"sensing":[164,299],"images.":[165],"new":[168],"model,":[169],"cascade":[170,177],"RCNN":[171,178],"backbone":[174],"network.":[175],"Parallel":[176],"network":[179,207],"utilized":[181],"enhance":[186],"expression":[188],"ability.":[189],"order":[191],"solve":[193],"problem":[195],"different":[197],"segmentation":[198],"shapes":[199],"sizes,":[201],"central":[203],"part":[204],"adopts":[208],"multi-coefficient":[209],"cascaded":[210],"hollow":[211],"convolution":[212],"obtain":[214,237],"multi-receptive":[215],"field":[216,232],"features":[217,240,246],"without":[218],"using":[219],"pooling":[220],"mode":[221],"preserving":[223],"information.":[225],"Meanwhile,":[226],"improved":[228],"selfattention":[229],"combined":[230],"receptive":[231],"strategy":[233],"both":[238],"low-level":[239],"with":[241,247],"marginal":[242],"details":[243],"high-level":[245],"global":[248],"semantics.":[249],"Finally,":[250],"we":[251],"conduct":[252],"experiments":[253,259],"on":[254],"DOTA":[255],"set":[256],"including":[257],"ablation":[258],"comparison":[261],"experiments.":[262],"experimental":[264],"results":[265],"show":[266],"mean":[269],"Average":[270],"Precision":[271],"(mAP)":[272],"indexes":[275],"have":[276],"been":[277],"greatly":[278],"improved,":[279],"its":[281],"performance":[282],"better":[284],"than":[285],"state-of-the-art":[287],"algorithms.":[289],"It":[290],"good":[293],"prospect":[295]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}