Improving Cerebrovascular Imaging with Deep Learning: Semantic Segmentation for Time-of-Flight Magnetic Resonance Angiography Maximum Intensity Projection Image Enhancement by Tomonari Yamada, Takaaki Yoshimura, Shota Ichikawa, Hiroyuki Sugimori

Get full text

Anomaly traffic detection method based on data augmentation and feature mining by AN Yishuai, FU Yu, YU Yihan, LIU Taotao

“…Finally, a multi-layer graph convolutional network with a hierarchical attention mechanism was designed, in which local and global features were hierarchically extracted and fused through a multi-level neighborhood aggregation strategy, significantly enhancing the model’s capability to identify key features. …”
Get full text

HTCNN-Attn: a fine-grained hierarchical multi-label deep learning model for disaster emergency information intelligent extraction from social media by Shanshan Li, Qingjie Liu, Xiaoling Sun

“…It integrates a three-level tree-structured labeling architecture, Transformer-based global feature extraction, convolutional neural network (CNN) layers for local pattern capture, and a hierarchical attention mechanism. …”
Get full text

TMAR: 3-D Transformer Network via Masked Autoencoder Regularization for Hyperspectral Sharpening by Zeinab Dehghan, Jingxiang Yang, Mehran Yazdi, Abdolraheem Khader, Liang Xiao

“…In this study, we focus on leveraging the power of CNN and transformer models and propose a multistage deep transformer-based super-resolution network that is regularized via an asymmetric autoencoder structure. In addition, we utilize a 3-D convolution layer in the light transformer structure because it allows for more flexible computation of correlations between HSI layers and better capturing of dependencies within spectral–spatial features. …”
Get full text

A security data detection and management method in digital library network based on deep learning by Diyin Zhu, Yihang Wei, Jiali Cai, Jingwen Wang, Zhongshan Chen

“…The method combines the structures of temporal convolutional network (TCN) and bidirectional gated recurrent unit (BiGRU) to extract spatial and temporal features from digital library network security data. …”
Get full text

UNestFormer: Enhancing Decoders and Skip Connections With Nested Transformers for Medical Image Segmentation by Adnan Md Tayeb, Tae-Hyong Kim

“…Precise identification of organs and lesions in medical images is essential for accurate disease diagnosis and analysis of organ structures. Deep convolutional neural network (CNN)-based U-shaped networks are among the most popular and promising approaches for this task. …”
Get full text

Antenna Optimization Design Based on Deep Gaussian Process Model by Xin-Yu Zhang, Yu-Bo Tian, Xie Zheng

“…In order to solve this problem, this study constructs a deep GP (DGP) model by using the structural form of convolutional neural network (CNN) and combining it with GP. …”
Get full text

A Drug-Target Interaction Prediction Method Based on Attention Perception and Modality Fusion by PENG Yang, ZHU Xiaofei, HU Dongdong

“…[Methods] For drug branches, Graph Transformer and Graph Convolutional Neural Network were used to jointly characterize the global structures and biochemical information of drug molecules. …”
Get full text

Generation driven understanding of localized 3D scenes with 3D diffusion model by Hao Sun, Junping Qin, Zheng Liu, Xinglong Jia, Kai Yan, Lei Wang, Zhiqiang Liu, Shaofei Gong

“…However, the existing diffusion models primarily focus on the global structure and are constrained by predefined dataset categories, which are unable to accurately resolve the detailed structure of complex 3D scenes. …”
Get full text

HDF-Net: Hierarchical Dual-Branch Feature Extraction Fusion Network for Infrared and Visible Image Fusion by Yanghang Zhu, Mingsheng Huang, Yaohua Zhu, Jingyu Jiang, Yong Zhang

“…Remarkably, we propose a pin-wheel-convolutional transformer (PCT) module that integrates local convolutional processing with directional attention to improve low-frequency feature extraction, thereby enabling more robust global–local context modeling. …”
Get full text

InGSA: integrating generalized self-attention in CNN for Alzheimer's disease classification by Faisal Binzagr, Anas W. Abulfaraj

“…Furthermore, several GSA heads are used to exploit other dependency structures of global features as well. Our evaluation of InGSA on a two benchmark dataset, using various pre-trained networks, demonstrates the GSA's superior performance.…”
Get full text

DECTNet: A detail enhanced CNN-Transformer network for single-image deraining by Liping Wang, Guangwei Gao

“…While CNNs are highly effective at extracting local information, they struggle to capture global context. Conversely, Transformers excel at capturing global information but often face challenges in preserving spatial and structural details. …”
Get full text

GAT-Enhanced YOLOv8_L with Dilated Encoder for Multi-Scale Space Object Detection by Haifeng Zhang, Han Ai, Donglin Xue, Zeyu He, Haoran Zhu, Delian Liu, Jianzhong Cao, Chao Mei

“…The local features extracted by convolutional neural networks are mapped to graph-structured data, and the nodal attention mechanism of GAT is used to capture the global topological association of space objects, which makes up for the deficiency of the convolutional operation in weight allocation and realizes GAT integration. …”
Get full text

An industrial carbon block instance segmentation algorithm based on improved YOLOv8 by Runjie Shi, Zhengbao Li, Zewei Wu, Wenxin Zhang, Yihang Xu, Gan Luo, Pingchuan Ma, Zheng Zhang

“…YOLOv8-HDSA adds a convolutional self-attention mechanism with residual structure to the head, preserving important local information of carbon blocks and improving the ability to extract fine-grained edge details and global features of carbon blocks. …”
Get full text

FingerDTA: A Fingerprint-Embedding Framework for Drug-Target Binding Affinity Prediction by Xuekai Zhu, Juan Liu, Jian Zhang, Zhihui Yang, Feng Yang, Xiaolei Zhang

“…Owing to the structural limitations of CNN, features extracted from this method are local patterns that lack global information. …”
Get full text

Data-Enabled Intelligence in Complex Industrial Systems Cross-Model Transformer Method for Medical Image Synthesis by Zebin Hu, Hao Liu, Zhendong Li, Zekuan Yu

“…Recently, generative adversarial network (GAN) models are applied to many medical image synthesis tasks and show prior performance, since they enable to capture structural details clearly. However, GAN still builds the main framework based on convolutional neural network (CNN) that exhibits a strong locality bias and spatial invariance through the use of shared weights across all positions. …”
Get full text

SwinCNet leveraging Swin Transformer V2 and CNN for precise color correction and detail enhancement in underwater image restoration by Chun Yang, Liwei Shao, Yi Deng, Jiahang Wang, Hexiang Zhai

“…Current methods face difficulties in effectively balancing local detail preservation with global information integration. This study proposes SwinCNet, an innovative deep learning architecture that incorporates an enhanced Swin Transformer V2 following primary convolutional layers to achieve synergistic processing of local details and global dependencies. …”
Get full text

Two-Branch Filtering Generative Network Based on Transformer for Image Inpainting by Feihan Cao, Qifeng Zhu, Yasheng Chang, Min Sun

“…This module utilizes predictive filtering constructed from convolutions to leverage local interactions, while simultaneously employing a transformer architecture with kernels from the predictive network to capture global correlations. …”
Get full text

DTC-m6Am: A Framework for Recognizing N6,2′-O-dimethyladenosine Sites in Unbalanced Classification Patterns Based on DenseNet and Attention Mechanisms by Hui Huang, Fenglin Zhou, Jianhua Jia, Huachun Zhang

“…The model then combines densely connected convolutional networks (DenseNet) and temporal convolutional network (TCN). …”
Get full text

GIVTED-Net: GhostNet-Mobile Involution ViT Encoder-Decoder Network for Lightweight Medical Image Segmentation by Resha Dwika Hefni Al-Fahsi, Ahmad Naghim Fauzaini Prawirosoenoto, Hanung Adi Nugroho, Igi Ardiyanto

“…Nevertheless, conventional CNN layers, such as convolution and pooling, demonstrate a spatial inductive bias that constrains their ability to instantly capture global context information. …”
Get full text