{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T18:16:22Z","timestamp":1793816182718,"version":"4.6.1"},"reference-count":81,"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\/501100011932","name":"Beijing Institute of Graphic Communication","doi-asserted-by":"publisher","award":["27170024003"],"award-info":[{"award-number":["27170024003"]}],"id":[{"id":"10.13039\/501100011932","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L251065"],"award-info":[{"award-number":["L251065"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003213","name":"Beijing Municipal Education Commission","doi-asserted-by":"publisher","award":["KM202410015001"],"award-info":[{"award-number":["KM202410015001"]}],"id":[{"id":"10.13039\/501100003213","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472040"],"award-info":[{"award-number":["62472040"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006579","name":"Ministry of Industry and Information Technology of the People's Republic of China","doi-asserted-by":"publisher","award":["2024IFS080607-A"],"award-info":[{"award-number":["2024IFS080607-A"]}],"id":[{"id":"10.13039\/501100006579","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012456","name":"National Social Science Fund of China","doi-asserted-by":"publisher","award":["2025"],"award-info":[{"award-number":["2025"]}],"id":[{"id":"10.13039\/501100012456","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.2026.109256","type":"journal-article","created":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T06:34:06Z","timestamp":1781246046000},"page":"109256","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":3,"special_numbering":"C","title":["DFIR-DETR: Frequency-domain iterative refinement and dynamic feature aggregation for small object detection"],"prefix":"10.1016","volume":"204","author":[{"given":"Bo","family":"Gao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6226-8737","authenticated-orcid":false,"given":"Jingcheng","family":"Tong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingsheng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zichen","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109256_bib0001","series-title":"International conference on learning representations (ICLR)","article-title":"Token merging: Your ViT but faster","author":"Bolya","year":"2023"},{"key":"10.1016\/j.neunet.2026.109256_bib0002","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.2026.109256_bib0003","series-title":"European conference on computer vision (ECCV)","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.neunet.2026.109256_bib0004","article-title":"Freq-DETR: Frequency-aware transformer for real-time small object detection in unmanned aerial vehicle imagery","volume":"298","author":"Chen","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.neunet.2026.109256_bib0005","doi-asserted-by":"crossref","unstructured":"Chen, Q., Wang, Y., Yang, T., Zhang, X., Cheng, J., & Sun, J. (2021). You only look one-level feature. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(pp. 13039\u201313048).","DOI":"10.1109\/CVPR46437.2021.01284"},{"issue":"3","key":"10.1016\/j.neunet.2026.109256_bib0006","doi-asserted-by":"crossref","first-page":"817","DOI":"10.3390\/s22030817","article-title":"Online detection of surface defects based on improved YOLOV3","volume":"22","author":"Chen","year":"2022","journal-title":"Sensors"},{"key":"10.1016\/j.neunet.2026.109256_bib0007","first-page":"36","article-title":"DGCST: Dynamic group convolution shuffle transformer for efficient vision backbone","volume":"168","author":"Chen","year":"2023","journal-title":"Pattern Recognition Letters"},{"key":"10.1016\/j.neunet.2026.109256_bib0008","series-title":"Advances in neural information processing systems (neurIPS)","first-page":"4479","article-title":"Fast fourier convolution","volume":"vol. 33","author":"Chi","year":"2020"},{"key":"10.1016\/j.neunet.2026.109256_bib0009","series-title":"Proceedings of the IEEE International conference on computer vision","first-page":"764","article-title":"Deformable convolutional networks","author":"Dai","year":"2017"},{"key":"10.1016\/j.neunet.2026.109256_bib0010","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition","first-page":"10886","article-title":"Diverse branch block: Building a convolution as an inception-like unit","author":"Ding","year":"2021"},{"key":"10.1016\/j.neunet.2026.109256_bib0011","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.131467","article-title":"CBH-YOLO: A steel surface defect detection algorithm based on cross-stage Mamba enhancement and hierarchical semantic graph fusion","volume":"656","author":"Gao","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.109256_bib0012","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition","first-page":"7036","article-title":"NAS-FPN: Learning scalable feature pyramid architecture for object detection","author":"Ghiasi","year":"2019"},{"key":"10.1016\/j.neunet.2026.109256_bib0013","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition workshops","first-page":"4156","article-title":"CGAFusion: Context-guided adaptive fusion network for rgb-t semantic segmentation","author":"Guo","year":"2023"},{"key":"10.1016\/j.neunet.2026.109256_bib0014","article-title":"Strip: Spatial transformer for efficient image processing","volume":"135","author":"Guo","year":"2023","journal-title":"Pattern Recognition"},{"issue":"8","key":"10.1016\/j.neunet.2026.109256_bib0015","first-page":"4456","article-title":"DBBC3: Dynamic branching bottleneck for efficient neural networks","volume":"34","author":"Han","year":"2023","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.109256_bib0016","series-title":"Proceedings of the AAAI Conference on artificial intelligence","first-page":"860","article-title":"Mfm: Multi-frequency multiscale feature fusion for object detection","volume":"vol. 37","author":"Hu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109256_bib0017","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition","first-page":"3368","article-title":"MSN: Multi-scale network for object detection","author":"Huang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109256_bib0018","unstructured":"Jocher, G., Chaurasia, A., & Qiu, J. (2023). Ultralytics YOLOv8. https:\/\/github.com\/ultralytics\/ultralytics."},{"key":"10.1016\/j.neunet.2026.109256_bib0019","doi-asserted-by":"crossref","first-page":"292","DOI":"10.1007\/s00530-025-01864-9","article-title":"TCF-DETR: Multi-scale token-channel fusion transformer for enhanced small object detection","volume":"31","author":"Lei","year":"2025","journal-title":"Multimedia Systems"},{"key":"10.1016\/j.neunet.2026.109256_bib0020","unstructured":"Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., Nie, W. et al. (2023a). YOLOv6 v3.0: A full-scale reloading. arXiv preprint arXiv: 2301.05586."},{"key":"10.1016\/j.neunet.2026.109256_bib0021","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition (CVPR)","first-page":"13619","article-title":"DN-DETR: Accelerate detr training by introducing query denoising","author":"Li","year":"2022"},{"key":"10.1016\/j.neunet.2026.109256_bib0022","article-title":"FC-DETR: High-precision end-to-end surface defect detector based on foreground supervision and cascade refined hybrid matching","volume":"266","author":"Li","year":"2025","journal-title":"Expert Systems with Applications"},{"issue":"3","key":"10.1016\/j.neunet.2026.109256_bib0023","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1007\/s11554-024-01436-6","article-title":"Slim-neck by GSConv: A lightweight-design for real-time detector architectures","volume":"21","author":"Li","year":"2024","journal-title":"Journal of Real-Time Image Processing"},{"issue":"7","key":"10.1016\/j.neunet.2026.109256_bib0024","first-page":"261","article-title":"Lightweight object detection algorithm for UAV aerial imagery","volume":"12","author":"Li","year":"2023","journal-title":"ISPRS International Journal of Geo-Information"},{"key":"10.1016\/j.neunet.2026.109256_bib0025","series-title":"Advances in neural information processing systems","first-page":"21002","article-title":"Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection","volume":"vol. 33","author":"Li","year":"2020"},{"key":"10.1016\/j.neunet.2026.109256_bib0026","first-page":"103","article-title":"FSA: Feature separation and aggregation network for semantic segmentation","volume":"523","author":"Li","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.109256_bib0027","first-page":"2918","article-title":"Hsfpn: Hierarchical semantic fusion pyramid network for multi-scale object detection","volume":"32","author":"Li","year":"2023","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.109256_bib0028","series-title":"Proceedings of the IEEE Conference on computer vision and pattern recognition","first-page":"936","article-title":"Feature pyramid networks for object detection","author":"Lin","year":"2017"},{"key":"10.1016\/j.neunet.2026.109256_bib0029","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.2026.109256_bib0030","article-title":"WDFS-DETR: A transformer-based framework with multi-scale attention for small object detection in UAV engineering tasks","volume":"27","author":"Liu","year":"2025","journal-title":"Results in Engineering"},{"key":"10.1016\/j.neunet.2026.109256_bib0031","series-title":"Proceedings of the IEEE Conference on computer vision and pattern recognition","first-page":"8759","article-title":"Path aggregation network for instance segmentation","author":"Liu","year":"2018"},{"key":"10.1016\/j.neunet.2026.109256_bib0032","series-title":"European conference on computer vision","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"Liu","year":"2016"},{"key":"10.1016\/j.neunet.2026.109256_bib0033","first-page":"29","article-title":"MAFFN: Multi-scale attention feature fusion network for semantic segmentation","volume":"520","author":"Liu","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.109256_bib0034","doi-asserted-by":"crossref","unstructured":"Liu, Y., Tian, Y., Zhao, Y., Yu, H., Xie, L., Wang, Y., Shen, Q., & Liu, Y. (2024). VMamba: Visual state space model. arXiv preprint arXiv: 2401.13260.","DOI":"10.52202\/079017-3273"},{"issue":"8","key":"10.1016\/j.neunet.2026.109256_bib0035","first-page":"4163","article-title":"Dtab: Dual-token attention block for efficient vision transformers","volume":"33","author":"Liu","year":"2023","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.109256_bib0036","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition","first-page":"11043","article-title":"Litv2: Efficient self-attention for vision transformers with learnable interaction tokens","author":"Liu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109256_bib0037","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition","first-page":"7363","article-title":"Grid r-CNN","author":"Lu","year":"2019"},{"key":"10.1016\/j.neunet.2026.109256_bib0038","series-title":"Proceedings of the IEEE\/CVF International conference on computer vision","first-page":"7598","article-title":"FDT: Fast and effective dynamic token for vision transformer","author":"Mao","year":"2023"},{"key":"10.1016\/j.neunet.2026.109256_bib0039","unstructured":"Qin, Z., Zhang, P., Wu, F., & Li, X. (2020). FCANet: Frequency channel attention networks. arXiv preprint arXiv: 2012.11879."},{"key":"10.1016\/j.neunet.2026.109256_bib0040","series-title":"Proceedings of the IEEE\/CVF International conference on computer vision (ICCV)","first-page":"783","article-title":"FCANet: Frequency channel attention networks","author":"Qin","year":"2021"},{"key":"10.1016\/j.neunet.2026.109256_bib0041","series-title":"Advances in neural information processing systems","first-page":"980","article-title":"Global filter networks for image classification","volume":"vol. 35","author":"Rao","year":"2022"},{"key":"10.1016\/j.neunet.2026.109256_bib0042","series-title":"Advances in neural information processing systems (neurIPS)","first-page":"980","article-title":"Global filter networks for image classification","volume":"vol. 34","author":"Rao","year":"2021"},{"key":"10.1016\/j.neunet.2026.109256_bib0043","series-title":"Proceedings of the IEEE Conference on computer vision and pattern recognition","first-page":"779","article-title":"You only look once: Unified, real-time object detection","author":"Redmon","year":"2016"},{"key":"10.1016\/j.neunet.2026.109256_bib0044","unstructured":"Redmon, J., & Farhadi, A. (2018). YOLOv3: An incremental improvement. arXiv preprint arXiv: 1804.02767."},{"issue":"6","key":"10.1016\/j.neunet.2026.109256_bib0045","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":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"6","key":"10.1016\/j.neunet.2026.109256_bib0046","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":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109256_bib0047","unstructured":"Roh, B., Shin, J., Shin, W., & Kim, S. (2022). Sparse DETR: Efficient end-to-end object detection with learnable sparsity. arXiv preprint arXiv: 2111.14330."},{"key":"10.1016\/j.neunet.2026.109256_bib0048","doi-asserted-by":"crossref","first-page":"858","DOI":"10.1016\/j.apsusc.2013.09.002","article-title":"A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects","volume":"285","author":"Song","year":"2013","journal-title":"Applied Surface Science"},{"key":"10.1016\/j.neunet.2026.109256_bib0049","first-page":"1","article-title":"Elgca: Efficient local-global context aggregation for remote sensing change detection","volume":"21","author":"Song","year":"2024","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"key":"10.1016\/j.neunet.2026.109256_bib0050","unstructured":"Sun, P., Zhang, R., Jiang, Y., Kong, T., Xu, C., Zhan, W., Tomizuka, M., Yuan, L., Wang, P., & Luo, P. (2023). PSFM: Progressive semantic feature module for object detection. arXiv preprint arXiv: 2302.02923."},{"key":"10.1016\/j.neunet.2026.109256_bib0051","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition","first-page":"10781","article-title":"Efficientdet: Scalable and efficient object detection","author":"Tan","year":"2020"},{"key":"10.1016\/j.neunet.2026.109256_bib0052","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition (CVPR)","first-page":"10935","article-title":"An image patch is a wave: Phase-aware vision MLP","author":"Tang","year":"2022"},{"key":"10.1016\/j.neunet.2026.109256_bib0053","series-title":"Proceedings of the IEEE\/CVF International conference on computer vision","first-page":"9627","article-title":"FCOS: Fully convolutional one-stage object detection","author":"Tian","year":"2019"},{"key":"10.1016\/j.neunet.2026.109256_bib0054","series-title":"Proceedings of the IEEE\/CVF International conference on computer vision","first-page":"2589","article-title":"Camixer: Convolution and attention mixing for efficient image processing","author":"Tu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109256_bib0055","unstructured":"Ultralytics, (2021). YOLOv5: A state-of-the-art real-time object detection system. https:\/\/github.com\/ultralytics\/yolov5."},{"key":"10.1016\/j.neunet.2026.109256_bib0056","unstructured":"Ultralytics, (2024). YOLOv11: An improved real-time object detection model. https:\/\/docs.ultralytics.com."},{"key":"10.1016\/j.neunet.2026.109256_bib0057","doi-asserted-by":"crossref","unstructured":"Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., & Ding, G. (2024). YOLOv10: Real-time end-to-end object detection. arXiv preprint arXiv: 2405.14458.","DOI":"10.52202\/079017-3429"},{"key":"10.1016\/j.neunet.2026.109256_bib0058","doi-asserted-by":"crossref","unstructured":"Wang, C., He, W., Nie, Y., Guo, J., Liu, C., Han, K., & Wang, Y. (2023a). Gold-YOLO: Efficient object detector via gather-and-distribute mechanism. arXiv preprint arXiv: 2309.11331.","DOI":"10.52202\/075280-2224"},{"key":"10.1016\/j.neunet.2026.109256_bib0059","doi-asserted-by":"crossref","unstructured":"Wang, C. Y., & Liao, H. Y. (2024). YOLOv9: Learning what you want to learn using programmable gradient information. arXiv preprint arXiv: 2402.13616.","DOI":"10.1007\/978-3-031-72751-1_1"},{"issue":"7","key":"10.1016\/j.neunet.2026.109256_bib0060","doi-asserted-by":"crossref","first-page":"2190","DOI":"10.3390\/s25072190","article-title":"SF-DETR: A scale-frequency detection transformer for drone-view object detection","volume":"25","author":"Wang","year":"2025","journal-title":"Sensors"},{"issue":"22","key":"10.1016\/j.neunet.2026.109256_bib0061","doi-asserted-by":"crossref","first-page":"6890","DOI":"10.3390\/s25226890","article-title":"Multi-scale deformable transformer with iterative query refinement for hot-rolled steel surface defect detection","volume":"25","author":"Wang","year":"2025","journal-title":"Sensors"},{"key":"10.1016\/j.neunet.2026.109256_bib0062","article-title":"MSGA: Multi-scale grouped attention mechanism for object detection","volume":"140","author":"Wang","year":"2023","journal-title":"Pattern Recognition"},{"issue":"1","key":"10.1016\/j.neunet.2026.109256_bib0063","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s41095-023-0336-6","article-title":"Attention mechanisms in computer vision: A survey","volume":"10","author":"Wang","year":"2024","journal-title":"Computational Visual Media"},{"key":"10.1016\/j.neunet.2026.109256_bib0064","article-title":"HDRAB: High-dynamic range attention block for efficient image super-resolution","volume":"139","author":"Wang","year":"2023","journal-title":"Pattern Recognition"},{"issue":"12","key":"10.1016\/j.neunet.2026.109256_bib0065","doi-asserted-by":"crossref","first-page":"822","DOI":"10.3390\/drones9120822","article-title":"AUP-DETR: A foundational UAV object detection framework for enabling the low-altitude economy","volume":"9","author":"Xu","year":"2025","journal-title":"Drones"},{"key":"10.1016\/j.neunet.2026.109256_bib0066","series-title":"Proceedings of the IEEE\/CVF International conference on computer vision","first-page":"3868","article-title":"CTrans: Cross-transformer network for multi-scale feature fusion","author":"Yan","year":"2023"},{"key":"10.1016\/j.neunet.2026.109256_bib0067","unstructured":"Yang, C., Huang, Z., & Wang, N. (2022a). ASF: Adaptive spatial fusion for efficient multi-scale feature learning. arXiv preprint arXiv: 2202.03149."},{"key":"10.1016\/j.neunet.2026.109256_bib0068","series-title":"Advances in neural information processing systems (neurIPS)","first-page":"4203","article-title":"Focal modulation networks","volume":"vol. 35","author":"Yang","year":"2022"},{"key":"10.1016\/j.neunet.2026.109256_bib0069","series-title":"Proceedings of the IEEE\/CVF International conference on computer vision workshops","first-page":"1477","article-title":"Rab: Residual attention block for efficient image super-resolution","author":"Yang","year":"2021"},{"key":"10.1016\/j.neunet.2026.109256_bib0070","unstructured":"Yao, Z., Ai, J., Li, B., & Zhang, C. (2021). Efficient DETR: Improving end-to-end object detector with dense prior. arXiv preprint arXiv: 2104.01318."},{"key":"10.1016\/j.neunet.2026.109256_bib0071","unstructured":"Yu, W., & Wang, X. (2024). MambaOut: Do we really need mamba for vision?arXiv preprint arXiv: 2405.07992."},{"issue":"22","key":"10.1016\/j.neunet.2026.109256_bib0072","doi-asserted-by":"crossref","first-page":"4265","DOI":"10.3390\/rs16224265","article-title":"Small object detection in UAV remote sensing images based on intra-group multi-scale fusion attention and adaptive weighted feature fusion mechanism","volume":"16","author":"Yuan","year":"2024","journal-title":"Remote Sensing"},{"key":"10.1016\/j.neunet.2026.109256_bib0073","series-title":"International conference on learning representations (ICLR)","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2023"},{"issue":"19","key":"10.1016\/j.neunet.2026.109256_bib0074","article-title":"Improved small object detection algorithm CRL-YOLOv5","volume":"24","author":"Zhang","year":"2024","journal-title":"Sensors"},{"issue":"7","key":"10.1016\/j.neunet.2026.109256_bib0075","first-page":"8784","article-title":"Glsa: Global-local self-attention for multi-scale feature learning","volume":"45","author":"Zhang","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109256_bib0076","article-title":"SDI: Spatial detail injection network for multi-scale semantic segmentation","volume":"138","author":"Zhao","year":"2023","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2026.109256_bib0077","series-title":"Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition (CVPR)","first-page":"16965","article-title":"Detrs beat yolos on real-time object detection","author":"Zhao","year":"2024"},{"key":"10.1016\/j.neunet.2026.109256_bib0078","series-title":"Objects as points","author":"Zhou","year":"2019"},{"key":"10.1016\/j.neunet.2026.109256_bib0079","unstructured":"Zhu, J., Li, J., Chen, J., & Chen, Q. (2024). Efficientvim: Efficient vision mamba with bidirectional state space models for semantic segmentation. arXiv preprint arXiv: 2402.02509."},{"issue":"11","key":"10.1016\/j.neunet.2026.109256_bib0080","doi-asserted-by":"crossref","first-page":"7380","DOI":"10.1109\/TPAMI.2021.3119563","article-title":"Detection and tracking meet drones challenge","volume":"44","author":"Zhu","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109256_bib0081","series-title":"International conference on learning representations (ICLR)","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2021"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026007161?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026007161?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T23:40:03Z","timestamp":1789083603000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026007161"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":81,"alternative-id":["S0893608026007161"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109256","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":"DFIR-DETR: Frequency-domain iterative refinement and dynamic feature aggregation for small object detection","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109256","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":"109256"}}