Multiscale Feature Fusion for Salient Object Detection of Strip Steel Surface Defects by Li Zhang, Xirui Li, Yange Sun, Yan Feng, Huaping Guo

“…For the first step, MFF uses ResNet (convolutions with downsampling operations) instead of sampling techniques to generate multiscale features because convolution excels at extracting local regional features (e.g., edge and contour information). …”
Get full text

HEAT: Incorporating hierarchical enhanced attention transformation into urban road detection by Ting Han, Chuanmu Li, Siyu Chen, Zongyue Wang, Jinhe Su, Yundong Wu, Guorong Cai

Get full text

Multi-scale conv-attention U-Net for medical image segmentation by Peng Pan, Chengxue Zhang, Jingbo Sun, Lina Guo

“…Abstract U-Net-based network structures are widely used in medical image segmentation. …”
Get full text

Honeycomb lung segmentation network based on P2T with CNN two-branch parallelism by Zhichao Li, Gang Li, Ling Zhang, Guijuan Cheng, Shan Wu

“…Aiming at the problem that honeycomb lung lesions are difficult to accurately segment due to diverse morphology and complex distribution, a network with parallel two-branch structure is proposed. In the encoder, the Pyramid Pooling Transformer (P2T) backbone is used as the Transformer branch to obtain the global features of the lesions, the convolutional branch is used to extract the lesions’ local feature information, and the feature fusion module is designed to effectively fuse the features in the dual branches; subsequently, in the decoder, the channel prior convolutional attention is used to enhance the localization ability of the model to the lesion region. …”
Get full text

CCTNet: CNN and Cross-Shaped Transformer Hybrid Network for Remote Sensing Image Semantic Segmentation by Honglin Wu, Zhaobin Zeng, Peng Huang, Xinyu Yu, Min Zhang

“…This model follows an encoder–decoder structure. It employs ResNet18 as an encoder to extract hierarchical feature information, and constructs a transformer decoder based on efficient cross-shaped self-attention to fully model local and global feature information and achieve lightweighting of the network. …”
Get full text

Complex Network Analytics for Structural–Functional Decoding of Neural Networks by Jiarui Zhang, Dongxiao Zhang, Hu Lou, Yueer Li, Taijiao Du, Yinjun Gao

Get full text

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

Two-stream spatio-temporal GCN-transformer networks for skeleton-based action recognition by Dong Chen, Mingdong Chen, Peisong Wu, Mengtao Wu, Tao Zhang, Chuanqi Li

“…This study proposes a novel architecture addressing this limitation by implementing a parallel configuration of GCNs and the Transformer model (SA-TDGFormer). This parallel structure integrates the advantages of both the GCN model and the Transformer model, facilitating the extraction of both local and global spatio-temporal features, leading to more accurate motion information encoding and improved recognition performance. …”
Get full text

A Rotation Target Detection Network Based on Multi-Kernel Interaction and Hierarchical Expansion by Qi Wang, Guanghu Xu, Donglin Jing

Get full text

Image Inpainting Algorithm Based on Structure-Guided Generative Adversarial Network by Li Zhao, Tongyang Zhu, Chuang Wang, Feng Tian, Hongge Yao

“…The proposed methodology advances a two-stage restoration paradigm: (1) Structural Prior Extraction, where adaptive edge detection algorithms identify residual contours in corrupted regions, and a transformer-enhanced network reconstructs globally consistent structural maps through contextual feature propagation; (2) Structure-Constrained Texture Synthesis, wherein a multi-scale generator with hybrid dilated convolutions and channel attention mechanisms iteratively refines high-fidelity textures under explicit structural guidance. …”
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

PoseAlign network for hybrid structure in 2D human pose estimation by Jin Zhang, Yabo Yin, Wenzhong Yang, Doudou Ren, Danny Chen

“…We introduce a novel 2D HPE method called the PoseAlign Network for Hybrid Structure (PAN-HS). PAN-HS leverages the conceptually simple yet effective depth-wise convolution to design two feature extraction blocks: the Spatial Align Block and the Channel Align Block. …”
Get full text

Infant cry classification using an efficient graph structure and attention-based model by Qiao X., Jiao S., Li H.

“…Additionally, in order to better classify the efficient graph structure, a local-to-global convolutional neural network (AlgNet) based on convolutional neural networks and attention mechanisms is proposed. …”
Get full text

MSA-Net: multiple self-attention mechanism for 3D lung nodule classification in CT images by Jiating Pan, Lishi Liang, Peng Sun, Yongbo Liang, Jianming Zhu, Zhencheng Chen

Get full text

Classification of Structural and Functional Development Stage of Cardiomyocytes Using Machine Learning Techniques by V. R. Bondarev, K. O. Ivanko, N. G. Ivanushkina

“…A pre-processed and augmented dataset is used for training of the convolutional neural network having an architecture with hierarchical structure and residual block usage. …”
Get full text

A Parallel Image Denoising Network Based on Nonparametric Attention and Multiscale Feature Fusion by Jing Mao, Lianming Sun, Jie Chen, Shunyuan Yu

“…The lower branch network used multiple dilation convolution residual blocks with different dilation rates to increase the receptive field and extend more contextual information to obtain the global features of the noise in the image. …”
Get full text

A Feature-Driven Inception Dilated Network for Infrared Image Super-Resolution Reconstruction by Jiaxin Huang, Huicong Wang, Yuhan Li, Shijian Liu

“…Therefore, an Inception Dilated Super-Resolution (IDSR) network with multiple branches is proposed. A dilated convolutional branch captures high-frequency information to reconstruct edge details, while a non-local operation branch captures long-range dependencies between any two positions to maintain the global structure. …”
Get full text

MT-SCnet: multi-scale token divided and spatial-channel fusion transformer network for microscopic hyperspectral image segmentation by Xueying Cao, Hongmin Gao, Haoyan Zhang, Shuyu Fei, Peipei Xu, Peipei Xu, Zhijian Wang

“…IntroductionHybrid architectures based on convolutional neural networks and Transformers, effectively captures both the local details and the overall structural context of lesion tissues and cells, achieving highly competitive segmentation results in microscopic hyperspectral image (MHSI) segmentation tasks. …”
Get full text