Underground low-light self-supervised image enhancement method based on structure and texture perception by Shan PAN, Ting YU, Wei CHEN, Zijian TIAN, Zhongwen YUE

“…To further exploit local texture features and global structural features in low-light images to improve the performance of the illumination estimation network, we introduce a local-global perception module into the illumination estimation network. …”
Get full text

MixRformer: Dual-Branch Network for Underwater Image Enhancement in Wavelet Domain by Jie Li, Lei Zhao, Heng Li, Xiaojun Xue, Hui Liu

“…To address the problems of insufficient global modeling in existing CNN models, weak local feature extraction of Transformer and high computational complexity, multi-resolution feature decomposition is performed through a discrete wavelet transform (IWT/DWT) in which low-frequency components retain structure and texture, and high-frequency components capture detail features. …”
Get full text

A Computational Approach to Understanding Agglutinative Structures in Urdu by Muhammad Shoaib Tahir, Mahnoor Amjad

“…This study investigates the computational challenges and opportunities presented by the agglutinative structures in Urdu, a language characterized by its complex system of morpheme-based word formation. …”
Get full text

Transition state structure detection with machine learningś by Yitao Si, Yiding Ma, Tao Yu, Yifan Wu, Yingzhe Liu, Weipeng Lai, Zhixiang Zhang, Jinwen Shi, Liejin Guo, Oleg V. Prezhdo, Maochang Liu

“…Abstract Transition structure calculations via quantum chemistry methods have become a staple in modern chemical reaction research. …”
Get full text

GP-GCN: Global features of orthogonal projection and local dependency fused graph convolutional networks for aspect-level sentiment classification by Subo Wei, Guangli Zhu, Zhengyan Sun, Xiaoqing Li, TienHsiung Weng

Get full text

Interesting Concept Mining With Concept Lattice Convolutional Networks by Mohamed Hamza Ibrahim, Rokia Missaoui, Pedro Henrique B. Ruas

“…In this paper, we introduce the Concept Lattice Convolutional Network (<inline-formula> <tex-math notation="LaTeX">$\mathcal {LCN}$ </tex-math></inline-formula>), an efficient semi-supervised learning approach to identify actionable concepts (i.e., interesting conceptual structures) based on a scalable convolutional neural network architecture that operates on concept lattices. …”
Get full text

On the convolutive development of elastic substrate media as nano foundation by D. Indronil, IM Nazmul

“…The validity of the proposed model is verified through comparisons with established theories, demonstrating its precision and broader applicability to complex structural scenarios. The convolution-based formulation also enhances the analysis of advanced loading conditions and nonlinear material responses, making it highly adaptable to real-world engineering applications. …”
Get full text

Target Tracking via Particle Filter and Convolutional Network by Hongxia Chu, Kejun Wang, Xianglei Xing

“…The global representation is generated by combining local features without changing their structures and space arrangements. …”
Get full text

Fuzzy Optimized Attention Network with Multi-Instance Deep Learning (FOAN-MIDL) for Alzheimer’s Disease Diagnosis with Structural Magnetic Resonance Imaging (sMRI) by Afnan M. Alhassan, Nouf I. Altmami

Get full text

Parking space number detection with multi‐branch convolution attention by Yifan Guo, Jianxun Zhang, Yuting Lin, Jie Zhang, Bowen Li

“…Since no scholar has proposed a high‐performance method for such problems, a parking space number detection model based on the multi‐branch convolutional attention is presented. Firstly, using ResNet50 as the backbone network, a multi‐branch convolutional structure is proposed in the backbone network, which aims to process and fuse the feature map through three parallel branches, and enhance the network to represent ability information by convolutional attention, learn global features to selectively strengthen the features containing helpful information, and improve the ability of the model to detect the parking space number area. …”
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

Fault Diagnosis of Rotating Machinery Based on Evolutionary Convolutional Neural Network by Yihao Bai, Weidong Cheng, Weigang Wen, Yang Liu

“…This paper proposes a fault diagnosis method for rotating machinery based on evolutionary convolutional neural network (ECNN). With the time-frequency images as the network input, with the help of the global optimization ability of the genetic algorithm, the structure of the convolutional neural network can evolve autonomously, and the adaptive configuration of the structural hyperparameters for the target task is realized. …”
Get full text

Efficient Semantic Segmentation of Remote Sensing Images Through Global-Local Feature Integration by Fengyi Zhang, Xiuyu Xia

“…To address these challenges, this paper proposes an efficient remote sensing image semantic segmentation model called Multi-GLISS, which integrates global and local features. The model captures global features through consecutive downsampling and Fourier transform while preserving spatial feature learning and boundary information using convolutional residual layers. …”
Get full text

A point cloud segmentation network with hybrid convolution and differential channels by Xiaoyan Zhang, Yantao Bu

“…Specifically, we design a hybrid convolutional feature extraction (HCFE) module for processing 3D semantic information and spatial information independently, using different convolution kernels to obtain the subtle geometric structure differences between points. …”
Get full text

SMS spam detection using BERT and multi-graph convolutional networks by Linjie Shen, Yanbin Wang, Zhao Li, Wenrui Ma

“…This multigraph approach captures diverse features and models both global and local structures using tailored Graph Convolutional Networks. …”
Get full text

TIER: Temporal Convolutional Network Information Extractor With Conditional Random Field by Huiwen Wu, Xiubo Zhang, Tengyuan Zhou, An Hu

“…The dilated convolution structure of TCN is used to expand the Receptive Fields (RFs) to capture long-distance context features, and the global dependency between labels is modeled through the CRF layer to improve the information extraction performance further. …”
Get full text

A Novel Hierarchical Multimodal Recommender With Enhanced Global Collaborative Signals by Peng Yi, Lu Chen, Zhaoxian Li, Cheng Yang

“…Specifically, modality features are first utilized to identify neighboring relationships, and similar users (items) are steadily merged together to form modality-specific hierarchical structures. Then, with the proper graph convolution operation on each hierarchy, the crucial global collaborative signals can be effectively extracted and integrated into the modality-specific user (item) embeddings. …”
Get full text

Global information aware network with global interaction graph attention for infrared small target detection by Ruimin Yang, Yidan Zhang, Guangshuai Gao, Liang Liao, Chunlei Li

“…However, distinguishing small infrared targets from similar backgrounds is challenging due to their lack of structural and textural characteristics. To address these challenges, this study proposes a novel global information‐aware network with global interaction graph attention (GIGA) for infrared small target detection. …”
Get full text

Optimization of the road bump and pothole detection technology using convolutional neural network by Ding Haiping, Tang Qianlong

“…In addition, this work explores the combination of sensor fusion techniques, combining data from many sources such as bridge structural health monitoring systems, cameras, accelerometers, and Global Positioning System. …”
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