{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T09:10:16Z","timestamp":1765012216101,"version":"3.46.0"},"reference-count":56,"publisher":"Wiley","issue":"27-28","license":[{"start":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T00:00:00Z","timestamp":1761696000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52374221"],"award-info":[{"award-number":["52374221"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2022MF288","ZR2023MF097","ZR2024QF107"],"award-info":[{"award-number":["ZR2022MF288","ZR2023MF097","ZR2024QF107"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2022ZD0119501"],"award-info":[{"award-number":["2022ZD0119501"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Concurrency and Computation"],"published-print":{"date-parts":[[2025,12,25]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>In recent years, self\u2010attention mechanisms have demonstrated remarkable performance across various computer vision tasks, gradually emerging as a mainstream approach. However, compared to traditional Convolutional Neural Networks (CNNs), its high quadratic complexity and limited adaptability to 2D structures have constrained its broader application and adoption. To enhance the feature extraction capability of CNNs, this work focuses on augmenting input information and introduces a novel architectural unit called the Global Query Vector (GQ Vector). The proposed unit adopts a co\u2010evolutionary architecture consisting of a parallel branch and the main backbone network, which continuously integrates and refines global semantic information during forward propagation, establishing a cross\u2010layer, persistent context memory mechanism. This design enables progressive accumulation and refinement of contextual information, thereby enhancing the CNN's capacity to model long\u2010range dependencies. Building on this, we propose a novel CNN architecture named a Global Query Convolutional Network (GQConvNet). It can be seamlessly integrated into existing CNN frameworks, further enhancing their performance. For example, on the ImageNet\u20101K dataset, a ResNet\u201050 model augmented with GQ Vector achieves a 1.7% improvement in Top\u20101 accuracy over baseline models. This work offers a fresh perspective on optimizing CNNs, with substantial academic value and practical implications.<\/jats:p>","DOI":"10.1002\/cpe.70384","type":"journal-article","created":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T18:20:11Z","timestamp":1761762011000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dynamic Global Query Fusion: A Plug\u2010and\u2010Play Module for Enhancing Convolutional Networks"],"prefix":"10.1002","volume":"37","author":[{"given":"Faming","family":"Lu","sequence":"first","affiliation":[{"name":"College of Computer Science and Engineering Shandong University of Science and Technology  Qingdao China"}]},{"given":"Kunhao","family":"Jia","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering Shandong University of Science and Technology  Qingdao China"}]},{"given":"Guiyuan","family":"Yuan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering Shandong University of Science and Technology  Qingdao China"}]}],"member":"311","published-online":{"date-parts":[[2025,10,29]]},"reference":[{"key":"e_1_2_8_2_1","first-page":"6232","article-title":"Instancediffusion: Instance\u2010Level Control for Image Generation IEEE","author":"Wang X.","year":"2024","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_2_8_3_1","first-page":"20331","article-title":"Deformable 3D Gaussians for High\u2010Fidelity Monocular Dynamic Scene Reconstruction IEEE","author":"Yang Z.","year":"2024","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_2_8_4_1","first-page":"8693","article-title":"DEADiff: an Efficient Stylization Diffusion Model with Disentangled Representations IEEE","author":"Qi T.","year":"2024","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_2_8_5_1","first-page":"16901","article-title":"Yolo\u2010World: Real\u2010Time Open\u2010Vocabulary Object Detection IEEE","author":"Cheng T.","year":"2024","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_2_8_6_1","first-page":"16965","article-title":"Detrs Beat Yolos on Real\u2010Time Object Detection IEEE","author":"Zhao Y.","year":"2024","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_2_8_7_1","first-page":"15909","article-title":"Repvit: Revisiting Mobile CNN from ViT Perspective IEEE","author":"Wang A.","year":"2024","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"e_1_2_8_9_1","first-page":"16133","article-title":"Convnext v2: Co\u2010Designing and Scaling Convnets with Masked Autoencoders IEEE","author":"Woo S.","year":"2023","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_2_8_10_1","unstructured":"O.Elharrouss Y.Akbari N.Almaadeed andS.Al\u2010Maadeed \u201cBackbones\u2010Review: Feature Extraction Networks for Deep Learning and Deep Reinforcement Learning Approaches. arXiv Preprint arXiv:2206.08016 \u201d2022."},{"key":"e_1_2_8_11_1","first-page":"14408","article-title":"Internimage: Exploring Large\u2010Scale Vision Foundation Models with Deformable Convolutions IEEE","author":"Wang W.","year":"2023","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"volume-title":"International Conference on Learning Representations (ICLR)","year":"2021","author":"Dosovitskiy A.","key":"e_1_2_8_12_1"},{"key":"e_1_2_8_13_1","first-page":"14420","article-title":"Efficientvit: Memory Efficient Vision Transformer with Cascaded Group Attention IEEE","author":"Liu X.","year":"2023","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_2_8_14_1","first-page":"10012","article-title":"Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows IEEE","author":"Liu Z.","year":"2021","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_2_8_15_1","first-page":"12009","article-title":"Swin Transformer v2: Scaling up Capacity and Resolution IEEE","author":"Liu Z.","year":"2022","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_2_8_16_1","first-page":"5785","article-title":"FastViT: a Fast Hybrid Vision Transformer Using Structural Reparameterization","author":"Vasu P. K. A.","year":"2023","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_2_8_18_1","first-page":"1097","article-title":"ImageNet classification with Deep Convolutional Neural Networks","volume":"25","author":"Krizhevsky A.","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_8_19_1","first-page":"730","volume-title":"Computer Science","author":"Simonyan K.","year":"2014"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_2_8_23_1","unstructured":"A. G.Howard M.Zhu B.Chen et al. \u201cMobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv Preprint arXiv:1704.04861 \u201d2017."},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"e_1_2_8_26_1","first-page":"6105","volume-title":"Proceedings of the 36th International Conference on Machine Learning (ICML)","author":"Tan M.","year":"2019"},{"key":"e_1_2_8_27_1","first-page":"10096","volume-title":"Proceedings of the 38th International Conference on Machine Learning (ICML)","author":"Tan M.","year":"2021"},{"key":"e_1_2_8_28_1","first-page":"5998","article-title":"Attention is All You Need","volume":"30","author":"Vaswani A.","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_2_8_29_1","unstructured":"H.Touvron M.Cord M.Douze F.Massa A.Sablayrolles andH.J\u00e9gou \u201cTraining Data\u2010Efficient Image Transformers & Distillation through Attention \u201d inInternational Conference on Machine Learning (ICML)(2021) 10347\u201310357."},{"key":"e_1_2_8_30_1","first-page":"12077","article-title":"Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows","volume":"34","author":"Liu Z.","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"e_1_2_8_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"e_1_2_8_34_1","article-title":"Attention is All You Need","volume":"30","author":"Vaswani A.","year":"2017","journal-title":"Advances In Neural Information Processing Systems"},{"volume-title":"North American Chapter of the Association for Computational Linguistics (NAACL)","year":"2019","author":"Devlin J.","key":"e_1_2_8_35_1"},{"key":"e_1_2_8_36_1","first-page":"1877","article-title":"Language Models are Few\u2010Shot Learners","volume":"33","author":"Brown T.","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_8_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.304"},{"key":"e_1_2_8_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1"},{"key":"e_1_2_8_39_1","first-page":"10353","article-title":"HorNet: Efficient High\u2010Order Spatial Interactions with Recursive Gated Convolutions","volume":"35","author":"Rao Y.","year":"2022","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_2_8_40_1","unstructured":"Y.Li C. Y.Wu H.Fan et al. \u201cConv2Former: A Simple Transformer\u2010Style ConvNet for Visual Recognition. arXiv Preprint arXiv:2211.11943 \u201d2022."},{"key":"e_1_2_8_41_1","first-page":"11963","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Ding X.","year":"2022"},{"key":"e_1_2_8_42_1","unstructured":"S.Liu T.Chen X.Chen et al. \u201cMore Convnets in the 2020s: Scaling up Kernels beyond 51\u2009\u00d7\u200951 Using Sparsity. arXiv Preprint arXiv:2207.03620 \u201d2022."},{"key":"e_1_2_8_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0364-2"},{"key":"e_1_2_8_44_1","first-page":"5672","article-title":"Inceptionnext: When Inception Meets ConvNeXt","author":"Yu W.","year":"2024","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_2_8_45_1","doi-asserted-by":"crossref","unstructured":"H.Chen X.Chu Y.Ren X.Zhao andK.Huang \u201cPeLK: Parameter\u2010efficient Large Kernel ConvNets with Peripheral Convolution \u201d2024 5557\u20135567.","DOI":"10.1109\/CVPR52733.2024.00531"},{"key":"e_1_2_8_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_2_8_47_1","article-title":"Dual Path Networks","volume":"30","author":"Chen Y.","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_8_48_1","article-title":"Pelee: a Real\u2010Time Object Detection System on Mobile Devices","volume":"31","author":"Wang R. J.","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_8_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00103"},{"key":"e_1_2_8_50_1","first-page":"395","volume-title":"DenseNets Reloaded: Paradigm Shift beyond Resnets and ViTs","author":"Kim D.","year":"2024"},{"key":"e_1_2_8_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_2_8_52_1","first-page":"618","volume-title":"Grad\u2010CAM: Visual Explanations from Deep Networks via Gradient\u2010Based Localization","author":"Selvaraju R. R.","year":"2017"},{"key":"e_1_2_8_53_1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"e_1_2_8_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00060"},{"key":"e_1_2_8_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"e_1_2_8_56_1","first-page":"2736","article-title":"Resnest: Split\u2010Attention Networks IEEE","author":"Zhang H.","year":"2022","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_2_8_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"}],"container-title":["Concurrency and Computation: Practice and Experience"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cpe.70384","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T09:08:08Z","timestamp":1765012088000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/cpe.70384"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,29]]},"references-count":56,"journal-issue":{"issue":"27-28","published-print":{"date-parts":[[2025,12,25]]}},"alternative-id":["10.1002\/cpe.70384"],"URL":"https:\/\/doi.org\/10.1002\/cpe.70384","archive":["Portico"],"relation":{},"ISSN":["1532-0626","1532-0634"],"issn-type":[{"type":"print","value":"1532-0626"},{"type":"electronic","value":"1532-0634"}],"subject":[],"published":{"date-parts":[[2025,10,29]]},"assertion":[{"value":"2025-08-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-12","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70384"}}