{"id":"https://openalex.org/W4411015005","doi":"https://doi.org/10.1145/3728725.3728810","title":"DAT-YOLO: Small Object Detection Model from the Perspective of Drones","display_name":"DAT-YOLO: Small Object Detection Model from the Perspective of Drones","publication_year":2025,"publication_date":"2025-02-21","ids":{"openalex":"https://openalex.org/W4411015005","doi":"https://doi.org/10.1145/3728725.3728810"},"language":"en","primary_location":{"id":"doi:10.1145/3728725.3728810","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3728725.3728810","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3728725.3728810","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 2nd International Conference on Generative Artificial Intelligence and Information Security","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3728725.3728810","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100318355","display_name":"Wei Li","orcid":"https://orcid.org/0000-0003-0691-9133"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Li","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0003-0691-9133","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044641216","display_name":"Kangwei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kangwei Zhang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0009-0100-7996","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000920827","display_name":"Penglin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Penglin Li","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0005-2706-1326","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008511953","display_name":"Keyang Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]},{"id":"https://openalex.org/I103163165","display_name":"Florida State University","ror":"https://ror.org/05g3dte14","country_code":"US","type":"education","lineage":["https://openalex.org/I103163165"]},{"id":"https://openalex.org/I4391767959","display_name":"State of New Jersey","ror":"https://ror.org/03h381n69","country_code":null,"type":"government","lineage":["https://openalex.org/I4391767959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keyang Yan","raw_affiliation_strings":["College of Arts and Sciences, Rutgers University, State of New Jersey, USA"],"raw_orcid":"https://orcid.org/0009-0008-9944-327X","affiliations":[{"raw_affiliation_string":"College of Arts and Sciences, Rutgers University, State of New Jersey, USA","institution_ids":["https://openalex.org/I103163165","https://openalex.org/I102322142","https://openalex.org/I4391767959"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100318355"],"corresponding_institution_ids":["https://openalex.org/I55712492"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1000354,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"538","last_page":"545"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9954000115394592,"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":0.992900013923645,"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/drone","display_name":"Drone","score":0.7854658365249634},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.7440038919448853},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6605347394943237},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5152850151062012},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.48191168904304504},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3720155954360962},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36155495047569275},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.09557074308395386}],"concepts":[{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.7854658365249634},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.7440038919448853},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6605347394943237},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5152850151062012},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.48191168904304504},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3720155954360962},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36155495047569275},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.09557074308395386},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3728725.3728810","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3728725.3728810","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3728725.3728810","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 2nd International Conference on Generative Artificial Intelligence and Information Security","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3728725.3728810","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3728725.3728810","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3728725.3728810","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 2nd International Conference on Generative Artificial Intelligence and Information Security","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411015005.pdf","grobid_xml":"https://content.openalex.org/works/W4411015005.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1483870316","https://openalex.org/W2947603930","https://openalex.org/W2950628590","https://openalex.org/W2991015021","https://openalex.org/W3023254438","https://openalex.org/W4289705070","https://openalex.org/W4308758201","https://openalex.org/W4372279253","https://openalex.org/W4382795691","https://openalex.org/W4387757656","https://openalex.org/W4392231788","https://openalex.org/W6785652829","https://openalex.org/W6810167572"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W4229448053","https://openalex.org/W4247925126","https://openalex.org/W4327774218","https://openalex.org/W2059768187","https://openalex.org/W4312858960","https://openalex.org/W4386036939","https://openalex.org/W4379143281","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"A":[0],"DAT-YOLO":[1,129],"model":[2,34,48,73],"incorporating":[3],"deformable":[4,81],"attention":[5,82],"is":[6,35,85],"proposed":[7],"to":[8,50,69,74,96],"address":[9],"the":[10,27,41,47,72,88,94,103,113,131,143,146],"challenges":[11],"of":[12,29,66,108,128],"dense":[13],"target":[14,161],"distribution,":[15],"small":[16,60,120],"pixel":[17],"size,":[18],"and":[19,39,43,77,116,145,153],"uneven":[20],"sample":[21],"size":[22],"in":[23,53,122,140],"object":[24],"detection":[25,162],"from":[26],"perspective":[28],"unmanned":[30],"aerial":[31],"vehicles.":[32],"This":[33],"based":[36],"on":[37,59,130],"YOLOv8s":[38],"optimizes":[40],"Backbone":[42],"Neck":[44],"structures,":[45],"allowing":[46,93],"network":[49,95],"be":[51],"shallower":[52],"depth":[54],"while":[55,101],"being":[56],"more":[57,98],"focused":[58],"targets;":[61],"Using":[62],"RepNCSPELAN4":[63],"structure":[64,68],"instead":[65],"C2f":[67],"better":[70],"adapt":[71],"different":[75],"computing":[76],"hardware":[78],"requirements;":[79],"The":[80,106,125],"mechanism":[83],"DAT":[84],"integrated":[86],"into":[87],"spatial":[89],"pyramid":[90],"pooling":[91],"layer,":[92],"capture":[97],"effective":[99],"features":[100],"expanding":[102],"receptive":[104],"field;":[105],"use":[107],"inner-ShapeIoU":[109],"loss":[110],"function":[111],"improves":[112],"algorithm's":[114],"localization":[115],"classification":[117],"performance":[118],"for":[119,159],"targets":[121],"complex":[123],"environments.":[124],"experimental":[126],"results":[127],"VisDrone":[132],"dataset":[133],"show":[134],"that":[135],"with":[136],"a":[137],"57.5%":[138],"reduction":[139],"parameter":[141],"count,":[142],"mAP@50":[144],"mAP@50:95":[147],"has":[148],"also":[149],"increased":[150],"by":[151],"6.7%":[152],"5.0%":[154],"respectively,":[155],"making":[156],"it":[157],"suitable":[158],"drone":[160],"tasks.":[163]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}