L-ENet: An Ultralightweight SAR Image Detection Network by Yutong Wang, Min Miao, Shiliang Zhu

“…Furthermore, the trihead detection structure is revised to a dual-head structure omni-dimensional adaptive spatial feature fusion, using object detection convolution to allocate weights across different scales for efficient detection. …”
Get full text

CBLN-YOLO: An Improved YOLO11n-Seg Network for Cotton Topping in Fields by Yufei Xie, Liping Chen

“…Firstly, the standard convolution and multihead self-attention (MHSA) mechanisms in YOLO11n-seg are replaced by linear deformable convolution (LDConv) and coordinate attention (CA) mechanisms to reduce the parameter growth rate of the original model and better mine detailed features of the top buds. …”
Get full text

CWMS-GAN: A small-sample bearing fault diagnosis method based on continuous wavelet transform and multi-size kernel attention mechanism. by Shun Yu, Zi Li, Jialin Gu, Runpu Wang, Xiaoyu Liu, Lin Li, Fusen Guo, Yuheng Ren

“…Specifically, this study proposes a continuous wavelet convolution strategy (CWCL) instead of the traditional convolution operation in GAN, which can additionally capture the signal's frequency domain features. …”
Get full text

Towards rigorous dataset quality standards for deep learning tasks in precision agriculture: A case study exploration by A. Carraro, G. Saurio, F. Marinello

“…Deep Learning (DL) through Convolutional Neural Networks (CNNs) has emerged as a critical player in classifying plant diseases from images. …”
Get full text

The shallowest transparent and interpretable deep neural network for image recognition by Gurmail Singh, Stefano Frizzo Stefenon, Kin-Choong Yow

“…This model consists of a transparent prototype layer, followed by an indispensable fully connected layer that connects prototypes and logits, whereas usually, interpretable models are not fully transparent because they use some black-box part as their baseline. This is the difference between Shallow-ProtoPNet and prototypical part network (ProtoPNet), the proposed Shallow-ProtoPNet does not use any black box part as a baseline, whereas ProtoPNet uses convolutional layers of black-box models as the baseline. …”
Get full text

Virtual Reality Video Image Classification Based on Texture Features by Guofang Qin, Guoliang Qin

“…As one of the most widely used methods in deep learning technology, convolutional neural networks have powerful feature extraction capabilities and nonlinear data fitting capabilities. …”
Get full text

A Ship’s Maritime Critical Target Identification Method Based on Lightweight and Triple Attention Mechanisms by Pu Wang, Shenhua Yang, Guoquan Chen, Weijun Wang, Zeyang Huang, Yuanliang Jiang

“…First, the lightweight double convolution kernel feature extraction layer is constructed using group convolution technology to replace the Conv structure of YOLOv9 (You Only Look Once Version 9), effectively reducing the number of parameters in the original model. …”
Get full text

Panel defect detection algorithm based on improved Faster R-CNN by Chen Wanqin, Tang Qingshan, Huang Tao

“…This method adds local adaptive cross-channel convolution without dimensionality reduction in the feature fusion layer to increase the feature mapping of channel crossing，and adds the CBAM attention network after the backbone feature extraction network to capture the long-term feature dependency of the feature map . …”
Get full text

Research on refined UAV inspection method of wind/solar power stations based on YOLOv8 by Jieyi Pu, Qifeng Zhang, Wenbo Zhao, Wei Zhang, Zengren Qin, Yumeng Zhang

“…In the extraction of key points such as the center and tip of wind turbine blades, this paper firstly adopts serpentine convolution to replace the traditional convolution operator in order to adapt the wind turbine blade features, and secondly incorporates the a priori information of the angle constraints between the blades into the loss function. …”
Get full text

A high-precision correction method in non-rigid 3D motion poses reconstruction by Cuihong Fan, Weina Fu, Shuai Liu

“…According to the frame difference and morphological processing, the background of image is separated and denoised. …”
Get full text

Generalized weighted Besov spaces on the Bessel hypergroup by Miloud Assal, Hacen Ben Abdallah

“…In this paper we study generalized weighted Besov type spaces on the Bessel-Kingman hypergroup. We give different characterizations of these spaces in terms of generalized convolution with a kind of smooth functions and by means of generalized translation operators. …”
Get full text

TARNet: An Efficient and Lightweight Trajectory-Based Air-Writing Recognition Model Using a CNN and LSTM Network by Md. Shahinur Alam, Ki-Chul Kwon, Shariar Md Imtiaz, Md Biddut Hossain, Bong-Gyun Kang, Nam Kim

“…This research proposes a unified, lightweight, and general-purpose deep learning algorithm for a trajectory-based air-writing recognition network (TARNet). We combine a convolutional neural network (CNN) with a long short-term memory (LSTM) network. …”
Get full text

Intrusion Detection System to Advance Internet of Things Infrastructure-Based Deep Learning Algorithms by Hasan Alkahtani, Theyazn H. H. Aldhyani

“…These data are sent to the cloud, which is a huge network of super servers that provides different services to different smart infrastructures, such as smart homes and smart buildings. …”
Get full text

LCCDMamba: Visual State Space Model for Land Cover Change Detection of VHR Remote Sensing Images by Junqing Huang, Xiaochen Yuan, Chan-Tong Lam, Yapeng Wang, Min Xia

“…The proposed MISF comprises multi-scale feature aggregation (MSFA), which utilizes strip convolution to aggregate multiscale local change information of bitemporal land cover features, and residual with SS2D (RSS) which employs residual structure with SS2D to capture global feature differences of bitemporal land cover features. …”
Get full text

An improved multiscale fusion dense network with efficient multiscale attention mechanism for apple leaf disease identification by Hui LIU, Dandan DAI

“…Incept_EMA_DenseNet consists of three crucial parts: the inception module, which substituted the convolution layer with multiscale fusion methods in the shallow feature extraction layer; the EMA mechanism, which is used for obtaining appropriate weights of different dense blocks; and the improved DenseNet based on DenseNet_121. …”
Get full text

The Solvability and Explicit Solutions of Singular Integral–Differential Equations with Reflection by A. S. Nagdy, KH. M. Hashem, H. E. H. Ebrahim

“…For such problems, we propose a novel method different from classical one, by which the explicit solutions and the conditions of solvability are obtained.…”
Get full text

Impact of Wall Impedance Phase Angle on Indoor Sound Field and Reverberation Parameters Derived from Room Impulse Response by Mirosław Meissner, Tomasz G. Zieliński

“…In this paper, the issue was investigated theoretically using the convolution integral and a modal representation of the room impulse response for complex-valued boundary conditions. …”
Get full text

Application analysis of computer vision and image recognition based on improved VGG16 network by Xuanzhang Zhu, Yafei Li

“…The research improves the deep convolutional neural network model through wavelet analysis algorithm. …”
Get full text

ST-YOLOv8: Small-Target Ship Detection in SAR Images Targeting Specific Marine Environments by Fei Gao, Yang Tian, Yongliang Wu, Yunxia Zhang

“…The C2f module in the backbone’s transition sections is replaced by the Conv_Online Reparameterized Convolution (C_OREPA) module, reducing convolutional complexity and improving efficiency. …”
Get full text

Evaluation of Shelf Life Prediction for Broccoli Based on Multispectral Imaging and Multi-Feature Data Fusion by Xiaoshuo Cui, Xiaoxue Sun, Shuxin Xuan, Jinyu Liu, Dongfang Zhang, Jun Zhang, Xiaofei Fan, Xuesong Suo

“…Multi-feature data fusion of spectral image information and physical and chemical parameters were combined with different machine learning methods to predict and evaluate the shelf life of broccoli.…”
Get full text