{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T00:10:17Z","timestamp":1789085417339,"version":"build-2803163510"},"reference-count":91,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["6247070792"],"award-info":[{"award-number":["6247070792"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472106"],"award-info":[{"award-number":["62472106"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.neunet.2026.109281","type":"journal-article","created":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T15:39:19Z","timestamp":1781969959000},"page":"109281","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["ES-DETR: Real-time detection transformer with encover and soft-dropout"],"prefix":"10.1016","volume":"204","author":[{"given":"Yiqing","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zefeng","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6479-5154","authenticated-orcid":false,"given":"Zhuowei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuhui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiantian","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lianglun","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"2","key":"10.1016\/j.neunet.2026.109281_bib0001","doi-asserted-by":"crossref","first-page":"46","DOI":"10.3390\/jimaging9020046","article-title":"Data augmentation in classification and segmentation: A survey and new strategies","volume":"9","author":"Alomar","year":"2023","journal-title":"Journal of Imaging"},{"key":"10.1016\/j.neunet.2026.109281_bib0002","series-title":"Computer vision: A reference guide","first-page":"875","article-title":"Object detection","author":"Amit","year":"2021"},{"issue":"14","key":"10.1016\/j.neunet.2026.109281_bib0003","doi-asserted-by":"crossref","first-page":"21353","DOI":"10.1007\/s11042-022-13801-3","article-title":"A survey: Object detection methods from CNN to transformer","volume":"82","author":"Arkin","year":"2023","journal-title":"Multimedia Tools and Applications"},{"key":"10.1016\/j.neunet.2026.109281_bib0004","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.108070","article-title":"Fault detection system for paper cup machine based on real-time image processing","volume":"133","author":"Ayd\u0131n","year":"2024","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10.1016\/j.neunet.2026.109281_bib0005","unstructured":"Bochkovskiy, A., Wang, C.-Y., & Liao, H.-Y. M. (2020). YOLOV4: Optimal speed and accuracy of object detection. arXiv: 2004.10934."},{"key":"10.1016\/j.neunet.2026.109281_bib0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.108998","article-title":"A full data augmentation pipeline for small object detection based on generative adversarial networks","volume":"133","author":"Bosquet","year":"2023","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.109281_bib0007","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"6154","article-title":"Cascade R-CNN: Delving into high quality object detection","author":"Cai","year":"2018"},{"key":"10.1016\/j.neunet.2026.109281_bib0008","series-title":"European conference on computer vision","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.neunet.2026.109281_bib0009","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"1692","article-title":"Masked image training for generalizable deep image denoising","author":"Chen","year":"2023"},{"key":"10.1016\/j.neunet.2026.109281_bib0010","unstructured":"Chen, P., Liu, S., Zhao, H., Wang, X., & Jia, J. (2024a). Gridmask data augmentation. arxiv: 2001.04086."},{"issue":"7","key":"10.1016\/j.neunet.2026.109281_bib0011","doi-asserted-by":"crossref","first-page":"7791","DOI":"10.1109\/TITS.2022.3227245","article-title":"An adaptive hybrid attention based convolutional neural net for intelligent transportation object recognition","volume":"24","author":"Chen","year":"2022","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"24","key":"10.1016\/j.neunet.2026.109281_bib0012","doi-asserted-by":"crossref","first-page":"65603","DOI":"10.1007\/s11042-023-17949-4","article-title":"A review of object detection: Datasets, performance evaluation, architecture, applications and current trends","volume":"83","author":"Chen","year":"2024","journal-title":"Multimedia Tools and Applications"},{"key":"10.1016\/j.neunet.2026.109281_bib0013","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"2988","article-title":"Dynamic DETR: End-to-end object detection with dynamic attention","author":"Dai","year":"2021"},{"issue":"6","key":"10.1016\/j.neunet.2026.109281_bib0014","doi-asserted-by":"crossref","first-page":"9243","DOI":"10.1007\/s11042-022-13644-y","article-title":"Object detection using YOLO: Challenges, architectural successors, datasets and applications","volume":"82","author":"Diwan","year":"2023","journal-title":"Multimedia Tools and Applications"},{"key":"10.1016\/j.neunet.2026.109281_bib0015","unstructured":"Dosovitskiy, A. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv: 2010.11929."},{"key":"10.1016\/j.neunet.2026.109281_bib0016","unstructured":"Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A.. The PASCAL visual object classes challenge 2012 (VOC2012) results. http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2012\/workshop\/index.html."},{"key":"10.1016\/j.neunet.2026.109281_bib0017","series-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision","first-page":"1257","article-title":"Data augmentation for object detection via controllable diffusion models","author":"Fang","year":"2024"},{"key":"10.1016\/j.neunet.2026.109281_bib0018","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"3621","article-title":"Fast convergence of DETR with spatially modulated co-attention","author":"Gao","year":"2021"},{"key":"10.1016\/j.neunet.2026.109281_bib0019","first-page":"1","article-title":"Attention-free global multiscale fusion network for remote sensing object detection","volume":"62","author":"Gao","year":"2024","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.neunet.2026.109281_bib0020","unstructured":"Ge, Z. (2021). YOLOX: exceeding YOLO series in 2021. arXiv: 2107.08430."},{"key":"10.1016\/j.neunet.2026.109281_bib0021","first-page":"10750","article-title":"DropBlock: A regularization method for convolutional networks","volume":"31","author":"Ghiasi","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109281_bib0022","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"1440","article-title":"Fast R-CNN","author":"Girshick","year":"2015"},{"key":"10.1016\/j.neunet.2026.109281_bib0023","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"580","article-title":"Rich feature hierarchies for accurate object detection and semantic segmentation","author":"Girshick","year":"2014"},{"key":"10.1016\/j.neunet.2026.109281_bib0024","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"1055","article-title":"KeepAugment: A simple information-preserving data augmentation approach","author":"Gong","year":"2021"},{"issue":"2","key":"10.1016\/j.neunet.2026.109281_bib0025","doi-asserted-by":"crossref","first-page":"327","DOI":"10.3390\/rs16020327","article-title":"Remote sensing object detection in the deep learning era-a review","volume":"16","author":"Gui","year":"2024","journal-title":"Remote Sensing"},{"issue":"1","key":"10.1016\/j.neunet.2026.109281_bib0026","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","article-title":"A survey on vision transformer","volume":"45","author":"Han","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109281_bib0027","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106506","article-title":"Language-aware multiple datasets detection pretraining for DETRs","volume":"179","author":"Hao","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109281_bib0028","series-title":"European conference on computer vision","first-page":"354","article-title":"CoLA: Conditional dropout and language-driven robust dual-modal salient object detection","author":"Hao","year":"2024"},{"issue":"0","key":"10.1016\/j.neunet.2026.109281_bib0029","article-title":"Lite real-time detection transformer for multi-scale algae recognition","volume":"0","author":"He","year":"2026","journal-title":"International Journal of Image and Graphics"},{"key":"10.1016\/j.neunet.2026.109281_bib0030","unstructured":"Ho, J., Kalchbrenner, N., Weissenborn, D., & Salimans, T. (2019). Axial attention in multidimensional transformers. arXiv: 1912.12180."},{"issue":"7","key":"10.1016\/j.neunet.2026.109281_bib0031","doi-asserted-by":"crossref","first-page":"10067","DOI":"10.1109\/TITS.2025.3547325","article-title":"DAEAR-DETR: DETR with dual-attention and ECHO accumulative residual for bus passenger detection","volume":"26","author":"Hou","year":"2025","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.1016\/j.neunet.2026.109281_bib0032","unstructured":"Jocher, G. (2020). Ultralytics YOLOV5. 10.5281\/zenodo.3908559."},{"key":"10.1016\/j.neunet.2026.109281_bib0033","unstructured":"Jocher, G., Chaurasia, A., & Qiu, J. (2023). Ultralytics YOLOV8. https:\/\/github.com\/ultralytics\/ultralytics."},{"key":"10.1016\/j.neunet.2026.109281_bib0034","unstructured":"Jocher, G., & Qiu, J. (2026). Ultralytics YOLO26. https:\/\/github.com\/ultralytics\/ultralytics."},{"key":"10.1016\/j.neunet.2026.109281_bib0035","series-title":"2021 IEEE international midwest symposium on circuits and systems (MWSCAS)","first-page":"537","article-title":"Data augmentation for object detection: A review","author":"Kaur","year":"2021"},{"key":"10.1016\/j.neunet.2026.109281_bib0036","doi-asserted-by":"crossref","DOI":"10.1016\/j.dsp.2022.103812","article-title":"A comprehensive review of object detection with deep learning","volume":"132","author":"Kaur","year":"2023","journal-title":"Digital Signal Processing"},{"key":"10.1016\/j.neunet.2026.109281_bib0037","unstructured":"Khanam, R., & Hussain, M. (2024). YOLOV11: An overview of the key architectural enhancements. arXiv: 2410.17725."},{"key":"10.1016\/j.neunet.2026.109281_bib0038","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/j.cogr.2024.07.002","article-title":"Unmanned aerial vehicles advances in object detection and communication security review","volume":"4","author":"Laghari","year":"2024","journal-title":"Cognitive Robotics"},{"key":"10.1016\/j.neunet.2026.109281_bib0039","unstructured":"Lei, M., Li, S., Wu, Y., Hu, H., Zhou, Y., Zheng, X., Ding, G., Du, S., Wu, Z., & Gao, Y. (2025). YOLOV13: Real-time object detection with hypergraph-enhanced adaptive visual perception. arXiv: 2506.17733."},{"key":"10.1016\/j.neunet.2026.109281_bib0040","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"18558","article-title":"Lite DETR: An interleaved multi-scale encoder for efficient DETR","author":"Li","year":"2023"},{"key":"10.1016\/j.neunet.2026.109281_bib0041","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"13619","article-title":"DN-DETR: Accelerate detr training by introducing query denoising","author":"Li","year":"2022"},{"issue":"4","key":"10.1016\/j.neunet.2026.109281_bib0042","doi-asserted-by":"crossref","first-page":"7193","DOI":"10.3934\/mbe.2023311","article-title":"Dynamic mosaic algorithm for data augmentation","volume":"20","author":"Li","year":"2023","journal-title":"Mathematical Biosciences and Engineering"},{"key":"10.1016\/j.neunet.2026.109281_bib0043","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.107021","article-title":"Transformer for object detection: Review and benchmark","volume":"126","author":"Li","year":"2023","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10.1016\/j.neunet.2026.109281_bib0044","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.121778","article-title":"MEANet: An effective and lightweight solution for salient object detection in optical remote sensing images","volume":"238","author":"Liang","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.neunet.2026.109281_bib0045","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"key":"10.1016\/j.neunet.2026.109281_bib0046","unstructured":"Liu, S., Li, F., Zhang, H., Yang, X., Qi, X., Su, H., Zhu, J., & Zhang, L. (2022a). DAB-DETR: Dynamic anchor boxes are better queries for DETR. arXiv: 2201.12329."},{"key":"10.1016\/j.neunet.2026.109281_bib0047","series-title":"Computer vision\u2013ECCV 2016: 14th European conference, Amsterdam, The Netherlands, october 11\u201314, 2016, proceedings, Part I 14","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"Liu","year":"2016"},{"issue":"6","key":"10.1016\/j.neunet.2026.109281_bib0048","doi-asserted-by":"crossref","first-page":"7478","DOI":"10.1109\/TNNLS.2022.3227717","article-title":"A survey of visual transformers","volume":"35","author":"Liu","year":"2023","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.109281_bib0049","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"12009","article-title":"Swin transformer V2: Scaling up capacity and resolution","author":"Liu","year":"2022"},{"issue":"5","key":"10.1016\/j.neunet.2026.109281_bib0050","doi-asserted-by":"crossref","first-page":"2486","DOI":"10.1109\/TGRS.2016.2645610","article-title":"Accurate object localization in remote sensing images based on convolutional neural networks","volume":"55","author":"Long","year":"2017","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.neunet.2026.109281_bib0051","unstructured":"Lv, W., Zhao, Y., Chang, Q., Huang, K., Wang, G., & Liu, Y. (2024). RT-DETRV2: Improved baseline with bag-of-freebies for real-time detection transformer. arXiv: 2407.17140."},{"key":"10.1016\/j.neunet.2026.109281_bib0052","series-title":"Artificial intelligence, machine learning, and data science technologies","first-page":"93","article-title":"Implication of image pre-processing in object detection using machine learning techniques","author":"Mago","year":"2021"},{"issue":"2","key":"10.1016\/j.neunet.2026.109281_bib0053","doi-asserted-by":"crossref","first-page":"15","DOI":"10.3390\/technologies12020015","article-title":"A review of machine learning and deep learning for object detection, semantic segmentation, and human action recognition in machine and robotic vision","volume":"12","author":"Manakitsa","year":"2024","journal-title":"Technologies"},{"key":"10.1016\/j.neunet.2026.109281_bib0054","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"3651","article-title":"Conditional detr for fast training convergence","author":"Meng","year":"2021"},{"issue":"3","key":"10.1016\/j.neunet.2026.109281_bib0055","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3758090","article-title":"Transformers in small object detection: A benchmark and survey of state-of-the-art","volume":"58","author":"Miri Rekavandi","year":"2025","journal-title":"ACM Computing Surveys"},{"issue":"20","key":"10.1016\/j.neunet.2026.109281_bib0056","doi-asserted-by":"crossref","first-page":"59143","DOI":"10.1007\/s11042-023-17751-2","article-title":"Exploring the efficacy and comparative analysis of one-stage object detectors for computer vision: A review","volume":"83","author":"Mustapha","year":"2024","journal-title":"Multimedia Tools and Applications"},{"key":"10.1016\/j.neunet.2026.109281_bib0057","doi-asserted-by":"crossref","DOI":"10.1016\/j.compag.2024.109104","article-title":"Outlier classification for microbiological open set recognition","volume":"224","author":"Pan","year":"2024","journal-title":"Computers and Electronics in Agriculture"},{"key":"10.1016\/j.neunet.2026.109281_bib0058","unstructured":"Peng, Y., Li, H., Wu, P., Zhang, Y., Sun, X., & Wu, F. (2024). D-FINE: Redefine regression task in DETRs as fine-grained distribution refinement. arXiv: 2410.13842."},{"key":"10.1016\/j.neunet.2026.109281_bib0059","unstructured":"Pereira, G. A., & Hussain, M. (2024). A review of transformer-based models for computer vision tasks: Capturing global context and spatial relationships. arXiv: 2408.15178."},{"key":"10.1016\/j.neunet.2026.109281_bib0060","doi-asserted-by":"crossref","DOI":"10.1016\/j.ibmed.2021.100037","article-title":"A novel data augmentation approach for mask detection using deep transfer learning","volume":"5","author":"Prusty","year":"2021","journal-title":"Intelligence-Based Medicine"},{"issue":"3","key":"10.1016\/j.neunet.2026.109281_bib0061","doi-asserted-by":"crossref","first-page":"2851","DOI":"10.1109\/TITS.2025.3530678","article-title":"A guide to image-and video-based small object detection using deep learning: Case study of maritime surveillance","volume":"26","author":"Rekavandi","year":"2025","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"6","key":"10.1016\/j.neunet.2026.109281_bib0062","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2016","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"3","key":"10.1016\/j.neunet.2026.109281_bib0063","doi-asserted-by":"crossref","first-page":"821","DOI":"10.3390\/s24030821","article-title":"The impact of noise and brightness on object detection methods","volume":"24","author":"Rodr\u00edguez-Rodr\u00edguez","year":"2024","journal-title":"Sensors"},{"issue":"14","key":"10.1016\/j.neunet.2026.109281_bib0064","doi-asserted-by":"crossref","first-page":"3106","DOI":"10.3390\/electronics12143106","article-title":"A review on dropout regularization approaches for deep neural networks within the scholarly domain","volume":"12","author":"Salehin","year":"2023","journal-title":"Electronics"},{"key":"10.1016\/j.neunet.2026.109281_bib0065","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2020.104129","article-title":"The impact of pre-and post-image processing techniques on deep learning frameworks: A comprehensive review for digital pathology image analysis","volume":"128","author":"Salvi","year":"2021","journal-title":"Computers in Biology and Medicine"},{"issue":"8","key":"10.1016\/j.neunet.2026.109281_bib0066","doi-asserted-by":"crossref","first-page":"1543","DOI":"10.3390\/electronics13081543","article-title":"TL-YOLO: Foreign-object detection on power transmission line based on improved YOLOV8","volume":"13","author":"Shao","year":"2024","journal-title":"Electronics"},{"issue":"11","key":"10.1016\/j.neunet.2026.109281_bib0067","doi-asserted-by":"crossref","first-page":"8135","DOI":"10.1109\/TNNLS.2022.3152527","article-title":"Learning from noisy labels with deep neural networks: A survey","volume":"34","author":"Song","year":"2022","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.109281_bib0068","doi-asserted-by":"crossref","unstructured":"Tian, Y., Ye, Q., & Doermann, D. (2025). YOLOV12: Attention-centric real-time object detectors. arXiv: 2502.12524.","DOI":"10.52202\/085713-2627"},{"key":"10.1016\/j.neunet.2026.109281_bib0069","doi-asserted-by":"crossref","first-page":"34899","DOI":"10.52202\/068431-2529","article-title":"Fully convolutional one-stage 3D object detection on lidar range images","volume":"35","author":"Tian","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"2","key":"10.1016\/j.neunet.2026.109281_bib0070","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1007\/s10044-024-01258-z","article-title":"Saliency information and mosaic based data augmentation method for densely occluded object recognition","volume":"27","author":"Tong","year":"2024","journal-title":"Pattern Analysis and Applications"},{"key":"10.1016\/j.neunet.2026.109281_bib0071","first-page":"6000","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109281_bib0072","doi-asserted-by":"crossref","first-page":"107984","DOI":"10.52202\/079017-3429","article-title":"YOLOV10: Real-time end-to-end object detection","volume":"37","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109281_bib0073","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","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.neunet.2026.109281_bib0074","series-title":"European conference on computer vision","first-page":"1","article-title":"YOLOV9: Learning what you want to learn using programmable gradient information","author":"Wang","year":"2025"},{"key":"10.1016\/j.neunet.2026.109281_bib0075","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"2567","article-title":"Anchor DETR: Query design for transformer-based detector","volume":"Vol. 36","author":"Wang","year":"2022"},{"key":"10.1016\/j.neunet.2026.109281_bib0076","doi-asserted-by":"crossref","first-page":"3343","DOI":"10.1109\/TMM.2025.3535316","article-title":"All-in-one weather-degraded image restoration via adaptive degradation-aware self-prompting model","volume":"27","author":"Wen","year":"2025","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2026.109281_bib0077","first-page":"1","article-title":"Encoder-free multiaxis physics-aware fusion network for remote sensing image dehazing","volume":"61","author":"Wen","year":"2023","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.neunet.2026.109281_bib0078","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109347","article-title":"A comprehensive survey of image augmentation techniques for deep learning","volume":"137","author":"Xu","year":"2023","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.109281_bib0079","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.110003","article-title":"Monte Carlo dropblock for modeling uncertainty in object detection","volume":"146","author":"Yelleni","year":"2024","journal-title":"Pattern Recognition"},{"issue":"17","key":"10.1016\/j.neunet.2026.109281_bib0080","doi-asserted-by":"crossref","first-page":"3169","DOI":"10.3390\/rs16173169","article-title":"MCG-RTDETR: Multi-convolution and context-guided network with cascaded group attention for object detection in unmanned aerial vehicle imagery","volume":"16","author":"Yu","year":"2024","journal-title":"Remote Sensing"},{"issue":"1","key":"10.1016\/j.neunet.2026.109281_bib0081","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1109\/TCC.2024.3361858","article-title":"Edge-cloud collaborative UAV object detection: Edge-embedded lightweight algorithm design and task offloading using fuzzy neural network","volume":"12","author":"Yuan","year":"2024","journal-title":"IEEE Transactions on Cloud Computing"},{"key":"10.1016\/j.neunet.2026.109281_bib0082","doi-asserted-by":"crossref","DOI":"10.1016\/j.dsp.2022.103514","article-title":"A survey of modern deep learning based object detection models","volume":"126","author":"Zaidi","year":"2022","journal-title":"Digital Signal Processing"},{"key":"10.1016\/j.neunet.2026.109281_bib0083","first-page":"1","article-title":"A small-sized object detection oriented multi-scale feature fusion approach with application to defect detection","volume":"71","author":"Zeng","year":"2022","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"10.1016\/j.neunet.2026.109281_bib0084","unstructured":"Zhang, H., Li, F., Liu, S., Zhang, L., Su, H., Zhu, J., Ni, L. M., & Shum, H.-Y. (2022). DINO: DETR with improved denoising anchor boxes for end-to-end object detection. arXiv: 2203.03605."},{"key":"10.1016\/j.neunet.2026.109281_bib0085","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.122669","article-title":"DsP-YOLO: An anchor-free network with DsPAN for small object detection of multiscale defects","volume":"241","author":"Zhang","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.neunet.2026.109281_bib0086","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.107513","article-title":"Deep learning-based object detection in maritime unmanned aerial vehicle imagery: Review and experimental comparisons","volume":"128","author":"Zhao","year":"2024","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10.1016\/j.neunet.2026.109281_bib0087","doi-asserted-by":"crossref","first-page":"33384","DOI":"10.1109\/ACCESS.2024.3355199","article-title":"Leveraging Monte Carlo dropout for uncertainty quantification in real-time object detection of autonomous vehicles","volume":"12","author":"Zhao","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.neunet.2026.109281_bib0088","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107547","article-title":"A pipeline for enabling nearshore infrared video super-resolution to learn more high-frequency foreground information","volume":"189","author":"Zhao","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109281_bib0089","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"16965","article-title":"DETRs beat YOLOs on real-time object detection","author":"Zhao","year":"2024"},{"key":"10.1016\/j.neunet.2026.109281_bib0090","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., & Dai, J. (2020). Deformable DETR: Deformable transformers for end-to-end object detection. arXiv: 2010.04159."},{"issue":"3","key":"10.1016\/j.neunet.2026.109281_bib0091","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/JPROC.2023.3238524","article-title":"Object detection in 20 years: A survey","volume":"111","author":"Zou","year":"2023","journal-title":"Proceedings of the IEEE"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026007410?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026007410?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T23:45:14Z","timestamp":1789083914000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026007410"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":91,"alternative-id":["S0893608026007410"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109281","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"ES-DETR: Real-time detection transformer with encover and soft-dropout","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109281","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"109281"}}