ViT-DualAtt: An efficient pornographic image classification method based on Vision Transformer with dual attention by Zengyu Cai, Liusen Xu, Jianwei Zhang, Yuan Feng, Liang Zhu, Fangmei Liu

“…The model adopts a CNN-Transformer hierarchical structure, combining the strengths of Convolutional Neural Networks (CNNs) and Transformers to effectively capture and integrate both local and global features, thereby enhancing feature representation accuracy and diversity. …”
Get full text

MRP-YOLO: An Improved YOLOv8 Algorithm for Steel Surface Defects by Shuxian Zhu, Yajie Zhou

“…It is further proposed that the RepHead detection head approximates the multi-branch structure of the original training by a single convolution operation. …”
Get full text

EEG-based schizophrenia diagnosis using deep learning with multi-scale and adaptive feature selection by Alanoud Al Mazroa, Majdy M. Eltahir, Shouki A. Ebad, Faiz Abdullah Alotaibi, Venkatachalam K, Jaehyuk Cho

“…With the help of atrous convolutions, local and global dependencies within the EEGs can be effectively modeled in this way. …”
Get full text

Dynamic Graph Attention Network for Skeleton-Based Action Recognition by Zhenhua Li, Fanjia Li, Gang Hua

“…To address these challenges, we propose a Dynamic Graph Attention Network (DGAN) that dynamically integrates local structural features and global spatiotemporal dependencies. …”
Get full text

Anterior Cruciate Ligament (ACL) Tear Detection Using Hybrid CNN Transformer by Suthir Sriram, Deependra K. Singh, D. V. Sairam, Nivethitha Vijayaraj, Thangavel Murugan

“…Firstly, MambaConvT utilizes multi-core convolutional networks to achieve higher extraction capability of the ACL tear specific local features from structural MR (Magnetic Resonance) images. …”
Get full text

GKCAE: A graph-attention-based encoder for fine-grained semantic segmentation of high-voltage transmission corridors scenario LiDAR data by Su Zhang, Haibo Liu, Jingguo Rong, Yaping Zhang

“…GKCAE first captures local geometric features using Kernel Point Convolution, and then models inter-class spatial relationships through Graph Edge-Conditioned Convolution to incorporate global contextual information. …”
Get full text

GLAI-Net: Global–Local Awareness Integrated Network for Semantic Change Detection in Remote Sensing Images by Qing Ding, Fengyan Wang, Mingchang Wang, Ying Zhang, Gui Cheng

“…We design a parallel encoding structure and utilize convolutional neural networks and transformer to achieve multi-scale modeling of images and enhance feature expression ability. …”
Get full text

Multiscale Wavelet and Graph Network With Spectral Self-Attention for Hyperspectral Image Classification by Anyembe C. Shibwabo, Zou Bin, Tahir Arshad, Jorge Abraham Rios Suarez

“…Third, DH-GCN constructs a deep graph structure to model spatial topology and overcome oversmoothing. …”
Get full text

Swin-GAT Fusion Dual-Stream Hybrid Network for High-Resolution Remote Sensing Road Extraction by Hongkai Zhang, Hongxuan Yuan, Minghao Shao, Junxin Wang, Suhong Liu

“…By decoupling detailed feature extraction from global context modeling, the proposed framework more faithfully represents complex road structures. …”
Get full text

YOLO-AFR: An Improved YOLOv12-Based Model for Accurate and Real-Time Dangerous Driving Behavior Detection by Tianchen Ge, Bo Ning, Yiwu Xie

“…YOLO-AFR builds upon the YOLOv12 architecture and introduces three key innovations: (1) the redesign of the original A2C2f module by introducing a Feature-Refinement Feedback Network (FRFN), resulting in a new A2C2f-FRFN structure that adaptively refines multiscale features, (2) the integration of self-calibrated convolution (SC-Conv) modules in the backbone to enhance multiscale contextual modeling, and (3) the employment of a SEAM-based detection head to improve global contextual awareness and prediction accuracy. …”
Get full text

Enhancing leaf disease classification using GAT-GCN hybrid model by Shyam Sundhar, Riya Sharma, Priyansh Maheshwari, Suvidha Rupesh Kumar, T. Sunil Kumar

“…Agriculture plays a critical role in the global economy, providing livelihoods and ensuring food security for billions. …”
Get full text

VE-GCN: A Geography-Aware Approach for Polyline Simplification in Cartographic Generalization by Siqiong Chen, Anna Hu, Yongyang Xu, Haitao Wang, Zhong Xie

“…To enhance the graph convolutional structure for capturing crucial geographic element features and simultaneously learning vertex and edge features within map polylines, this study introduces a joint vertex–edge feature graph convolutional network (VE-GCN). …”
Get full text

Improving unsupervised pedestrian re‐identification with enhanced feature representation and robust clustering by Jiang Luo, Lingjun Liu

Get full text

CNN–Transformer gated fusion network for medical image super-resolution by Juanjuan Qin, Jian Xiong, Zhantu Liang

“…The network consists of two branches, one is the global branch based on residual Transformer network, and the other is the local branch based on dynamic convolutional neural network. …”
Get full text

Directed Knowledge Graph Embedding Using a Hybrid Architecture of Spatial and Spectral GNNs by Guoqiang Hou, Qiwen Yu, Fan Chen, Guang Chen

“…To address this limitation, a directed spectral graph transformer (DSGT), a hybrid architecture model, is constructed by integrating the graph transformer and directed spectral graph convolution networks. The graph transformer leverages multi-head attention mechanisms to capture the global connectivity of the feature graph from different perspectives in the spatial domain, which bridges the gap between frequency responses and, further, naturally couples the graph transformer and directed graph convolutional neural networks (GCNs). …”
Get full text

SGRD: A Ship Group Relationship Description Method Based on Scene Graph Generation With a Global-Local Context Fusion Network by Qianwen Rui, Yanan You, Jingyi Cao, Kaiwen Zhu, Yuanyuan Qiao

“…The proposed network integrates global feature fusion through a transformer-based self-attention mechanism and enhances local feature fusion using a graph convolutional network focused on object-specific graph structures. …”
Get full text

Enhancement of Underwater Images through Parallel Fusion of Transformer and CNN by Xiangyong Liu, Zhixin Chen, Zhiqiang Xu, Ziwei Zheng, Fengshuang Ma, Yunjie Wang

“…Subsequently, to extract global features, both temporal and frequency domain features are incorporated to construct the convolutional neural network. …”
Get full text

Time-Series Forecasting Method Based on Hierarchical Spatio-Temporal Attention Mechanism by Zhiguo Xiao, Junli Liu, Xinyao Cao, Ke Wang, Dongni Li, Qian Liu

“…Breaking through traditional structural designs, the model employs a Squeeze-and-Excitation Network (SENet) to reconstruct the convolutional layers of the Temporal Convolutional Network (TCN), strengthening the feature expression of key time steps through dynamic channel weight allocation to address the redundancy issue of traditional causal convolutions in local pattern capture. …”
Get full text

Bird Species Detection Net: Bird Species Detection Based on the Extraction of Local Details and Global Information Using a Dual-Feature Mixer by Chaoyang Li, Zhipeng He, Kai Lu, Chaoyang Fang

“…The dual-branch feature mixer extracts features from dichotomous feature segments using global attention and deep convolution, expanding the network’s receptive field and achieving a strong inductive bias, allowing the network to distinguish between similar local details. …”
Get full text

Deep Time Series Intelligent Framework for Power Data Asset Evaluation by Lihong Ge, Xin Li, Li Wang, Jian Wei, Bo Huang

“…In the evaluation of the complex and rich Solar-Power dataset and Electricity dataset, TSENet achieved significant performance improvements over other state-of-the-art baseline methods.Through the synergistic design of deep convolutional structures and an efficient memory mechanism, it effectively addresses issues such as inadequate modeling of long-term dependencies, insufficient extraction of short-term features, and high prediction volatility, thereby significantly enhancing both the accuracy and robustness of forecasting in power asset evaluation tasks.…”
Get full text