{"id":"https://openalex.org/W4399418778","doi":"https://doi.org/10.1145/3651671.3651745","title":"Context-Aware Gridding Non-local Block for Improving Object Detection in UAV Images","display_name":"Context-Aware Gridding Non-local Block for Improving Object Detection in UAV Images","publication_year":2024,"publication_date":"2024-02-02","ids":{"openalex":"https://openalex.org/W4399418778","doi":"https://doi.org/10.1145/3651671.3651745"},"language":"en","primary_location":{"id":"doi:10.1145/3651671.3651745","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3651671.3651745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 16th International Conference on Machine Learning and Computing","raw_type":"proceedings-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/A5053695187","display_name":"Ruilin Yao","orcid":"https://orcid.org/0009-0002-6654-2294"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruilin Yao","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Wuhan University of Technology, China"],"raw_orcid":"https://orcid.org/0009-0002-6654-2294","affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Wuhan University of Technology, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011707621","display_name":"Shengwu Xiong","orcid":"https://orcid.org/0000-0002-4006-7029"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengwu Xiong","raw_affiliation_strings":["School of Computer Science and Artificial Intelligence, Wuhan University of Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-4006-7029","affiliations":[{"raw_affiliation_string":"School of Computer Science and Artificial Intelligence, Wuhan University of Technology, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101967703","display_name":"Yi Rong","orcid":"https://orcid.org/0000-0003-4867-6811"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Rong","raw_affiliation_strings":["Sanya Science and Education Innovation Park of Wuhan University of Technology, China and School of Computer Science and Artificial Intelligence, Wuhan University of Technology, China"],"raw_orcid":"https://orcid.org/0000-0003-4867-6811","affiliations":[{"raw_affiliation_string":"Sanya Science and Education Innovation Park of Wuhan University of Technology, China and School of Computer Science and Artificial Intelligence, Wuhan University of Technology, China","institution_ids":["https://openalex.org/I196699116"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053695187"],"corresponding_institution_ids":["https://openalex.org/I196699116"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06973877,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"257","last_page":"263"},"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":0.9987000226974487,"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":0.9986000061035156,"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":0.8192896842956543},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.7310296893119812},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.6829773187637329},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6813146471977234},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6733689308166504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6120209693908691},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5950033664703369},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.579964816570282},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5612479448318481},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5548713803291321},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5244684219360352},{"id":"https://openalex.org/keywords/division","display_name":"Division (mathematics)","score":0.4724184572696686},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47133326530456543},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.41665688157081604},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.4106849730014801},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.41005846858024597},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32592377066612244},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08321061730384827},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06825718283653259}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8192896842956543},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.7310296893119812},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.6829773187637329},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6813146471977234},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6733689308166504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6120209693908691},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5950033664703369},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.579964816570282},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5612479448318481},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5548713803291321},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5244684219360352},{"id":"https://openalex.org/C60798267","wikidata":"https://www.wikidata.org/wiki/Q1226939","display_name":"Division (mathematics)","level":2,"score":0.4724184572696686},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47133326530456543},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41665688157081604},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.4106849730014801},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.41005846858024597},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32592377066612244},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08321061730384827},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06825718283653259},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3651671.3651745","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3651671.3651745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 16th International Conference on Machine Learning and Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2884585870","https://openalex.org/W2962777203","https://openalex.org/W2963857746","https://openalex.org/W2981766846","https://openalex.org/W3116963012","https://openalex.org/W3138516171","https://openalex.org/W3175126800","https://openalex.org/W3176346992","https://openalex.org/W3179888767","https://openalex.org/W3184439416","https://openalex.org/W3210997132","https://openalex.org/W4221040873","https://openalex.org/W4285253679","https://openalex.org/W4320009770"],"related_works":["https://openalex.org/W2087502554","https://openalex.org/W3042882560","https://openalex.org/W2330973770","https://openalex.org/W4252317921","https://openalex.org/W2038973998","https://openalex.org/W4236696036","https://openalex.org/W4213091376","https://openalex.org/W1979495818","https://openalex.org/W1975640583","https://openalex.org/W3094080891"],"abstract_inverted_index":{"In":[0,38],"this":[1,39,53,148],"paper,":[2,40],"we":[3,41,132],"explore":[4],"object":[5,17,113],"detection":[6,18,36],"in":[7,24,117],"unmanned":[8],"aerial":[9],"vehicle":[10],"(UAV)":[11],"captured":[12],"images.":[13],"Different":[14],"from":[15],"general":[16],"tasks,":[19],"the":[20,59,81,112,124,154],"large":[21],"scale":[22,82,114],"differences":[23,83],"each":[25,85,118],"UAV":[26,119],"single":[27],"image":[28],"often":[29],"lead":[30],"to":[31,51,73],"a":[32,43,101,134],"significant":[33],"reduction":[34],"of":[35,156],"accuracy.":[37],"propose":[42],"novel":[44],"Context-aware":[45],"Gridding":[46],"Non-local":[47],"Block":[48],"(CGNLB)":[49],"module":[50],"handle":[52],"problem.":[54],"Specifically,":[55],"CGNLB":[56,130,159],"first":[57],"divides":[58],"input":[60],"feature":[61],"map":[62],"into":[63],"multiple":[64],"local":[65,75],"grids":[66],"and":[67,128,143],"then":[68],"applies":[69],"different":[70,74],"non-local":[71],"operations":[72],"grids.":[76],"The":[77],"grid":[78,86],"division":[79,97],"makes":[80],"within":[84],"become":[87],"relatively":[88],"small,":[89],"thereby":[90],"reducing":[91],"their":[92],"influences.":[93],"To":[94],"make":[95],"such":[96],"process":[98],"more":[99],"flexible,":[100],"context-aware":[102],"gridding":[103],"strategy":[104],"is":[105],"also":[106],"proposed,":[107],"which":[108],"can":[109],"adaptively":[110],"utilize":[111],"variation":[115],"information":[116],"image.":[120],"Finally,":[121],"by":[122],"combining":[123],"original":[125],"YoloX":[126,136],"model":[127],"our":[129,157],"module,":[131],"design":[133],"Context-Aware":[135],"(CA-YoloX)":[137],"detector.":[138],"Experimental":[139],"results":[140],"on":[141],"Vidsrone":[142],"UAVDT":[144],"datasets":[145],"show":[146],"that":[147],"detector":[149],"outperforms":[150],"state-of-the-art":[151],"methods,":[152],"indicating":[153],"effectiveness":[155],"proposed":[158],"module.":[160]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}