{"id":"https://openalex.org/W4213251678","doi":"https://doi.org/10.1145/3513133","title":"Towards Accurate Oriented Object Detection in Aerial Images with Adaptive Multi-level Feature Fusion","display_name":"Towards Accurate Oriented Object Detection in Aerial Images with Adaptive Multi-level Feature Fusion","publication_year":2022,"publication_date":"2022-02-18","ids":{"openalex":"https://openalex.org/W4213251678","doi":"https://doi.org/10.1145/3513133"},"language":"en","primary_location":{"id":"doi:10.1145/3513133","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3513133","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5075845993","display_name":"Peining Zhen","orcid":"https://orcid.org/0000-0002-8439-876X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Peining Zhen","raw_affiliation_strings":["Shanghai Jiao Tong University, Minhang District, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Minhang District, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100439205","display_name":"Shuqi Wang","orcid":"https://orcid.org/0000-0002-1384-4830"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuqi Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, Minhang District, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Minhang District, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004938651","display_name":"Suming Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suming Zhang","raw_affiliation_strings":["Beijing Institute of Astronautical Systems Engineering, Fengtai District, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Astronautical Systems Engineering, Fengtai District, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016422137","display_name":"Xiaotao Yan","orcid":"https://orcid.org/0000-0001-6590-3647"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaotao Yan","raw_affiliation_strings":["Beijing Institute of Astronautical Systems Engineering, Fengtai District, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Astronautical Systems Engineering, Fengtai District, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100776068","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-2298-3429"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Beijing Institute of Astronautical Systems Engineering, Fengtai District, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Astronautical Systems Engineering, Fengtai District, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058083493","display_name":"Zhigang Ji","orcid":"https://orcid.org/0000-0003-1138-804X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhigang Ji","raw_affiliation_strings":["Shanghai Jiao Tong University, Minhang District, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Minhang District, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030264455","display_name":"Hai\u2010Bao Chen","orcid":"https://orcid.org/0000-0001-7046-3455"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hai-Bao Chen","raw_affiliation_strings":["Shanghai Jiao Tong University, Minhang District, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Minhang District, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5075845993"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":2.6171,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.91093759,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"19","issue":"1","first_page":"1","last_page":"22"},"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":0.9993000030517578,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9937000274658203,"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":0.7404354810714722},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.72838294506073},{"id":"https://openalex.org/keywords/aerial-image","display_name":"Aerial image","score":0.6770020723342896},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6762874126434326},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.6216456890106201},{"id":"https://openalex.org/keywords/orientation","display_name":"Orientation (vector space)","score":0.6120014786720276},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.601507842540741},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5992934703826904},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.5902012586593628},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4821593165397644},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4407501518726349},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43285149335861206},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.41778337955474854},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41657155752182007},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.33338791131973267},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15148040652275085},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.12934157252311707},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.07432222366333008}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7404354810714722},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.72838294506073},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.6770020723342896},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6762874126434326},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.6216456890106201},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.6120014786720276},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.601507842540741},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5992934703826904},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.5902012586593628},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4821593165397644},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4407501518726349},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43285149335861206},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.41778337955474854},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41657155752182007},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.33338791131973267},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15148040652275085},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.12934157252311707},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.07432222366333008},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3513133","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3513133","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.5600000023841858,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2249069931","https://openalex.org/W2559655401","https://openalex.org/W2565639579","https://openalex.org/W2593539516","https://openalex.org/W2949058942","https://openalex.org/W2962749812","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963351448","https://openalex.org/W2964241181","https://openalex.org/W2964294787","https://openalex.org/W2967487473","https://openalex.org/W2989678931","https://openalex.org/W2991363140","https://openalex.org/W2993501994","https://openalex.org/W2995801068","https://openalex.org/W2999452014","https://openalex.org/W3013436129","https://openalex.org/W3015331846","https://openalex.org/W3016536844","https://openalex.org/W3022917557","https://openalex.org/W3028729812","https://openalex.org/W3046174881","https://openalex.org/W3083166649","https://openalex.org/W3086049282","https://openalex.org/W3106228955","https://openalex.org/W3106250896","https://openalex.org/W3136761610","https://openalex.org/W3167363556","https://openalex.org/W3171395710","https://openalex.org/W4205432963","https://openalex.org/W4242177601","https://openalex.org/W4301409532","https://openalex.org/W4304206535","https://openalex.org/W4376502449","https://openalex.org/W6760424586","https://openalex.org/W6782137339"],"related_works":["https://openalex.org/W3197089899","https://openalex.org/W4327500857","https://openalex.org/W4311223090","https://openalex.org/W1689909837","https://openalex.org/W2965994363","https://openalex.org/W4205729548","https://openalex.org/W4301521271","https://openalex.org/W1895541646","https://openalex.org/W2889698616","https://openalex.org/W2953362004"],"abstract_inverted_index":{"Detecting":[0],"objects":[1,13],"in":[2,14,19,40,81,111,165],"aerial":[3,15,41,82],"images":[4,16,42],"is":[5,94,181],"a":[6,62,68,88,118,177],"long-standing":[7],"and":[8,21,53,146,187,197,216],"challenging":[9],"problem":[10],"since":[11,43],"the":[12,48,97,101,107,112,127,134,149,162,169,173,185,195,202],"vary":[17],"dramatically":[18],"size":[20],"orientation.":[22],"Most":[23],"existing":[24],"neural":[25],"network":[26,143,170],"based":[27,171],"methods":[28],"are":[29,137,192],"not":[30,46],"robust":[31],"enough":[32],"to":[33,105,125,139,183,200],"provide":[34],"accurate":[35,76],"oriented":[36,77,120,131],"object":[37,78],"detection":[38,210],"results":[39,211],"they":[44],"do":[45],"consider":[47],"correlations":[49],"between":[50],"different":[51,166],"levels":[52,145],"scales":[54],"of":[55,100,168,204],"features.":[56,114],"In":[57],"this":[58],"paper,":[59],"we":[60],"propose":[61,117],"novel":[63],"two-stage":[64],"network-based":[65],"detector":[66],"with":[67],"daptive":[69],"f":[70,72],"eature":[71],"usion":[73],"towards":[74],"highly":[75],"det":[79],"ection":[80],"images,":[83],"named":[84],"AFF-Det":[85],".":[86],"First,":[87],"multi-scale":[89],"feature":[90,103,141,152,163],"fusion":[91],"module":[92],"(MSFF)":[93],"built":[95],"on":[96,172,194,220],"top":[98],"layer":[99],"extracted":[102],"pyramids":[104],"mitigate":[106],"semantic":[108],"information":[109],"loss":[110],"small-scale":[113],"We":[115],"also":[116],"cascaded":[119],"bounding":[121],"box":[122],"regression":[123],"method":[124],"transform":[126],"horizontal":[128],"proposals":[129,136],"into":[130],"ones.":[132],"Then":[133],"transformed":[135],"assigned":[138],"all":[140],"pyramid":[142],"(FPN)":[144],"aggregated":[147],"by":[148],"weighted":[150],"RoI":[151],"aggregation":[153],"(WRFA)":[154],"module.":[155],"The":[156,208],"above":[157],"modules":[158],"can":[159,212],"adaptively":[160],"enhance":[161],"representations":[164],"stages":[167],"attention":[174],"mechanism.":[175],"Finally,":[176],"rotated":[178],"decoupled-RCNN":[179],"head":[180],"introduced":[182],"obtain":[184],"classification":[186],"localization":[188],"results.":[189],"Extensive":[190],"experiments":[191],"conducted":[193],"DOTA":[196],"HRSC2016":[198],"datasets":[199],"demonstrate":[201],"advantages":[203],"our":[205],"proposed":[206],"AFF-Det.":[207],"best":[209],"achieve":[213],"80.73%":[214],"mAP":[215],"90.48%":[217],"mAP,":[218],"respectively,":[219],"these":[221],"two":[222],"datasets,":[223],"outperforming":[224],"recent":[225],"state-of-the-art":[226],"methods.":[227]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}