{"id":"https://openalex.org/W4402351642","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651078","title":"A Temporal and Self-Attention Based Method for Small Object Detection in UAV Imagery","display_name":"A Temporal and Self-Attention Based Method for Small Object Detection in UAV Imagery","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402351642","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651078"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10651078","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10651078","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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/A5034321400","display_name":"Liang Zuo","orcid":null},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liang Zuo","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics,Nanjing,China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003317644","display_name":"Jie Hao","orcid":"https://orcid.org/0000-0002-1269-2097"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Hao","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics,Nanjing,China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111319798","display_name":"LingXiao Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"LingXiao Yu","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics,Nanjing,China","institution_ids":["https://openalex.org/I9842412"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5034321400"],"corresponding_institution_ids":["https://openalex.org/I9842412"],"apc_list":null,"apc_paid":null,"fwci":0.2624,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53122859,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994000196456909,"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":0.9994000196456909,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991000294685364,"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":0.7522717714309692},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6199823617935181},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5882970094680786},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5814200639724731},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5497626662254333},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.22234919667243958}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7522717714309692},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6199823617935181},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5882970094680786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5814200639724731},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5497626662254333},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.22234919667243958}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10651078","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10651078","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2117539524","https://openalex.org/W2565639579","https://openalex.org/W2798799804","https://openalex.org/W2952122856","https://openalex.org/W2962721361","https://openalex.org/W2963037989","https://openalex.org/W2964241181","https://openalex.org/W2982770724","https://openalex.org/W2985384565","https://openalex.org/W2988452521","https://openalex.org/W2989611864","https://openalex.org/W2993756598","https://openalex.org/W3009396058","https://openalex.org/W3034467781","https://openalex.org/W3036271496","https://openalex.org/W3114606989","https://openalex.org/W3125509312","https://openalex.org/W3157386596","https://openalex.org/W3172087149","https://openalex.org/W3208154594","https://openalex.org/W4221040873","https://openalex.org/W4226272687","https://openalex.org/W4285545380","https://openalex.org/W4288325606","https://openalex.org/W4311726887","https://openalex.org/W4382568144","https://openalex.org/W4385482848","https://openalex.org/W6620707391","https://openalex.org/W6750759024","https://openalex.org/W6764322716","https://openalex.org/W6802878479","https://openalex.org/W6810974023","https://openalex.org/W6847876731"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","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":{"Unmanned":[0],"aerial":[1],"vehicle":[2],"(UAV)":[3],"images":[4],"are":[5],"widely":[6],"applied":[7],"in":[8,131],"real-world":[9],"applications.":[10],"However,":[11],"traditional":[12],"object":[13],"detection":[14],"methods":[15],"have":[16],"encountered":[17],"a":[18,47,85],"sharp":[19],"performance":[20,116],"drop":[21],"on":[22,90,119],"UAV":[23],"images,":[24],"largely":[25],"due":[26],"to":[27,95,105,137],"the":[28,63,71,102,114,121],"presence":[29],"of":[30,117],"numerous":[31],"small":[32],"objects":[33,107],"with":[34,108],"low":[35],"resolution,":[36],"sparse":[37],"textures,":[38],"and":[39,78,100,123],"blurred":[40],"features.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45,83],"propose":[46],"novel":[48],"Adaptive":[49],"Anchor":[50],"Detection":[51],"Network":[52],"(AADN)":[53],"that":[54],"dynamically":[55],"generate":[56],"anchors":[57],"through":[58],"deep":[59],"neural":[60],"network.":[61],"Subsequently":[62],"proposed":[64],"Temporal":[65],"And":[66],"Self-Attention":[67],"(TAA)":[68],"module":[69],"enhances":[70],"extracted":[72],"image":[73],"features":[74],"by":[75],"capturing":[76],"temporal":[77],"internal":[79],"correlation":[80],"information.":[81],"Furthermore,":[82],"introduce":[84],"data":[86],"augmentation":[87],"method":[88],"based":[89],"category":[91],"k-means":[92],"clustering,":[93],"designed":[94],"reduce":[96],"irrelevant":[97],"background":[98],"regions":[99],"improve":[101],"network\u2019s":[103],"ability":[104],"distinguish":[106],"similar":[109],"categories.":[110],"Extensive":[111],"experiments":[112],"show":[113],"superior":[115],"AADN":[118],"both":[120],"VisDrone2019":[122],"TinyPerson":[124],"dataset,":[125],"achieving":[126],"an":[127],"impressive":[128],"2%":[129],"increase":[130],"mean":[132],"average":[133],"precision":[134],"(mAP)":[135],"compared":[136],"state-of-the-art":[138],"methods.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}