{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T00:13:04Z","timestamp":1778285584131,"version":"3.51.4"},"reference-count":49,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100002338","name":"Ministry of Education of the People's Republic of China","doi-asserted-by":"publisher","award":["2024ZY011"],"award-info":[{"award-number":["2024ZY011"]}],"id":[{"id":"10.13039\/501100002338","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018571","name":"Specific Research Project of Guangxi for Research Bases and Talents","doi-asserted-by":"publisher","award":["GuiKe23026264"],"award-info":[{"award-number":["GuiKe23026264"]}],"id":[{"id":"10.13039\/501100018571","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011343","name":"Key Laboratory of System Control and Information Processing, Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011343","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62388101"],"award-info":[{"award-number":["62388101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.engappai.2026.114626","type":"journal-article","created":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T09:22:46Z","timestamp":1775467366000},"page":"114626","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P1","title":["Improved noising training detection Transformer based drone image detector"],"prefix":"10.1016","volume":"176","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6316-8527","authenticated-orcid":false,"given":"Lu","family":"Ding","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinghua","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xun","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2266-214X","authenticated-orcid":false,"given":"Yong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.engappai.2026.114626_b1","series-title":"CVPR","first-page":"6154","article-title":"Cascade r-cnn: Delving into high quality object detection","author":"Cai","year":"2018"},{"key":"10.1016\/j.engappai.2026.114626_b2","series-title":"ECCV","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.engappai.2026.114626_b3","series-title":"ICCV","first-page":"6633","article-title":"Group detr: Fast detr training with group-wise one-to-many assignment","author":"Chen","year":"2023"},{"key":"10.1016\/j.engappai.2026.114626_b4","series-title":"CVPR","first-page":"4974","article-title":"Hybrid task cascade for instance segmentation","author":"Chen","year":"2019"},{"key":"10.1016\/j.engappai.2026.114626_b5","series-title":"ICCV Workshops","article-title":"Rrnet: A hybrid detector for object detection in drone-captured images","author":"Chen","year":"2019"},{"key":"10.1016\/j.engappai.2026.114626_b6","series-title":"CVPR","first-page":"7373","article-title":"Dynamic head: Unifying object detection heads with attentions","author":"Dai","year":"2021"},{"key":"10.1016\/j.engappai.2026.114626_b7","series-title":"ICCV","first-page":"2988","article-title":"Dynamic detr: End-to-end object detection with dynamic attention","author":"Dai","year":"2021"},{"key":"10.1016\/j.engappai.2026.114626_b8","doi-asserted-by":"crossref","first-page":"1556","DOI":"10.1109\/TIP.2020.3045636","article-title":"A global-local self-adaptive network for drone-view object detection","volume":"30","author":"Deng","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.engappai.2026.114626_b9","series-title":"CVPR","first-page":"304","article-title":"Pedestrian detection: A benchmark","author":"Doll\u00e1r","year":"2009"},{"key":"10.1016\/j.engappai.2026.114626_b10","unstructured":"Du, D., Zhu, P., Wen, L., Bian, X., Lin, H., Hu, Q., Peng, T., Zheng, J., Wang, X., Zhang, Y., et al., 2019. VisDrone-DET2019: The vision meets drone object detection in image challenge results. In: ICCV Workshops."},{"key":"10.1016\/j.engappai.2026.114626_b11","series-title":"ICCV","first-page":"6569","article-title":"Centernet: Keypoint triplets for object detection","author":"Duan","year":"2019"},{"key":"10.1016\/j.engappai.2026.114626_b12","series-title":"CVPR","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.engappai.2026.114626_b13","series-title":"CVPR","first-page":"4507","article-title":"Learning non-maximum suppression","author":"Hosang","year":"2017"},{"key":"10.1016\/j.engappai.2026.114626_b14","series-title":"Ultralytics YOLOv11: State-of-the-art object detection models","author":"Jocher","year":"2024"},{"key":"10.1016\/j.engappai.2026.114626_b15","series-title":"ACM Transactions on Multimedia Computing, Communications, and Applications","first-page":"19(6)","article-title":"Transformer-based visual grounding with cross-modality interaction","author":"Kun","year":"2023"},{"key":"10.1016\/j.engappai.2026.114626_b16","series-title":"Science China(Information Sciences)","first-page":"10:196","article-title":"ViGT: proposal-free video grounding with a learnable token in the transformer","author":"Kun","year":"2023"},{"key":"10.1016\/j.engappai.2026.114626_b17","series-title":"ACM MM","first-page":"19(6)","article-title":"Data augmentation for human behavior analysis in multi-person conversations","author":"Li","year":"2023"},{"key":"10.1016\/j.engappai.2026.114626_b18","series-title":"CVPR","first-page":"1","article-title":"PointSR: Self regularized point supervision for drone view object detection","author":"Li","year":"2025"},{"key":"10.1016\/j.engappai.2026.114626_b19","doi-asserted-by":"crossref","unstructured":"Li, C., Yang, T., Zhu, S., Chen, C., Guan, S., 2020. Density map guided object detection in aerial images. In: CVPR Workshops. pp. 190\u2013191.","DOI":"10.1109\/CVPRW50498.2020.00103"},{"key":"10.1016\/j.engappai.2026.114626_b20","series-title":"CVPR","first-page":"13619","article-title":"Dn-detr: Accelerate detr training by introducing query denoising","author":"Li","year":"2022"},{"key":"10.1016\/j.engappai.2026.114626_b21","series-title":"CVPR","first-page":"2117","article-title":"Feature pyramid networks for object detection","author":"Lin","year":"2017"},{"key":"10.1016\/j.engappai.2026.114626_b22","series-title":"ICCV","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"key":"10.1016\/j.engappai.2026.114626_b23","series-title":"ECCV","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.engappai.2026.114626_b24","series-title":"ICLR","article-title":"DAB-DETR: Dynamic anchor boxes are better queries for DETR","author":"Liu","year":"2021"},{"key":"10.1016\/j.engappai.2026.114626_b25","doi-asserted-by":"crossref","first-page":"145740","DOI":"10.1109\/ACCESS.2020.3014910","article-title":"Small-object detection in UAV-captured images via multi-branch parallel feature pyramid networks","volume":"8","author":"Liu","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.engappai.2026.114626_b26","series-title":"ICLR","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2018"},{"key":"10.1016\/j.engappai.2026.114626_b27","series-title":"ICCV","first-page":"3651","article-title":"Conditional detr for fast training convergence","author":"Meng","year":"2021"},{"key":"10.1016\/j.engappai.2026.114626_b28","series-title":"CVPR","first-page":"7263","article-title":"YOLO9000: better, faster, stronger","author":"Redmon","year":"2017"},{"key":"10.1016\/j.engappai.2026.114626_b29","series-title":"Yolov3: An incremental improvement","author":"Redmon","year":"2018"},{"key":"10.1016\/j.engappai.2026.114626_b30","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"NIPS"},{"key":"10.1016\/j.engappai.2026.114626_b31","series-title":"RF-DETR","first-page":"1","author":"Robinson","year":"2025"},{"key":"10.1016\/j.engappai.2026.114626_b32","series-title":"ICCV","first-page":"3611","article-title":"Rethinking transformer-based set prediction for object detection","author":"Sun","year":"2021"},{"key":"10.1016\/j.engappai.2026.114626_b33","series-title":"ICCV","first-page":"9627","article-title":"Fcos: Fully convolutional one-stage object detection","author":"Tian","year":"2019"},{"key":"10.1016\/j.engappai.2026.114626_b34","series-title":"YOLOv12: Attention-centric real-time object detectors","first-page":"1","author":"Tian","year":"2025"},{"key":"10.1016\/j.engappai.2026.114626_b35","series-title":"WACV","first-page":"2260","article-title":"Seadronessee: A maritime benchmark for detecting humans in open water","author":"Varga","year":"2022"},{"key":"10.1016\/j.engappai.2026.114626_b36","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"NIPS"},{"key":"10.1016\/j.engappai.2026.114626_b37","series-title":"CVPR","first-page":"7464","article-title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","author":"Wang","year":"2023"},{"key":"10.1016\/j.engappai.2026.114626_b38","doi-asserted-by":"crossref","unstructured":"Wang, H., Wang, Z., Jia, M., Li, A., Feng, T., Zhang, W., Jiao, L., 2019. Spatial attention for multi-scale feature refinement for object detection. In: ICCV Workshops.","DOI":"10.1109\/ICCVW.2019.00014"},{"key":"10.1016\/j.engappai.2026.114626_b39","series-title":"ECCV","first-page":"651","article-title":"Object detection using clustering algorithm adaptive searching regions in aerial images","author":"Wang","year":"2020"},{"key":"10.1016\/j.engappai.2026.114626_b40","first-page":"2567","article-title":"Anchor detr: Query design for transformer-based detector","volume":"vol. 36","author":"Wang","year":"2022"},{"key":"10.1016\/j.engappai.2026.114626_b41","series-title":"ICCV","first-page":"8311","article-title":"Clustered object detection in aerial images","author":"Yang","year":"2019"},{"key":"10.1016\/j.engappai.2026.114626_b42","series-title":"CVPR","first-page":"13668","article-title":"QueryDet: Cascaded sparse query for accelerating high-resolution small object detection","author":"Yang","year":"2022"},{"key":"10.1016\/j.engappai.2026.114626_b43","doi-asserted-by":"crossref","unstructured":"Zhang, J., Huang, J., Chen, X., Zhang, D., 2019. How to fully exploit the abilities of aerial image detectors. In: ICCV Workshops.","DOI":"10.1109\/ICCVW.2019.00007"},{"key":"10.1016\/j.engappai.2026.114626_b44","doi-asserted-by":"crossref","unstructured":"Zhang, X., Izquierdo, E., Chandramouli, K., 2019. Dense and small object detection in uav vision based on cascade network. In: ICCV Workshops.","DOI":"10.1109\/ICCVW.2019.00020"},{"key":"10.1016\/j.engappai.2026.114626_b45","series-title":"ICCV","first-page":"2799","article-title":"ViT-YOLO: Transformer-based YOLO for object detection","author":"Zhang","year":"2021"},{"key":"10.1016\/j.engappai.2026.114626_b46","series-title":"ACM Multimedia","first-page":"19(6)","article-title":"Cluster phys: Facial clues clustering towards efficient remote physiological measurement","author":"Zhu","year":"2024"},{"key":"10.1016\/j.engappai.2026.114626_b47","series-title":"IEEE Transactions on Multimedia","first-page":"19(6)","article-title":"Exploiting efficient sam and temporal coherence for audio-visual segmentation","author":"Zhu","year":"2025"},{"key":"10.1016\/j.engappai.2026.114626_b48","series-title":"PICCV","first-page":"2778","article-title":"TPH-YOLOv5: Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios","author":"Zhu","year":"2021"},{"key":"10.1016\/j.engappai.2026.114626_b49","series-title":"ICLR","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626009073?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626009073?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T23:33:11Z","timestamp":1778283191000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197626009073"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":49,"alternative-id":["S0952197626009073"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114626","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Improved noising training detection Transformer based drone image detector","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114626","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114626"}}