A Pretrained Spatio-Temporal Hypergraph Transformer for Multi-Stock Trend Forecasting by Yuchen Wu, Liang Xie, Hongyang Wan, Haijiao Xu

“…This framework enhances the model’s cold-start capability, making it more adaptable to newly listed stocks with insufficient training data. …”
Get full text

PSHNet: Hybrid Supervision and Feature Enhancement for Accurate Infrared Small-Target Detection by Weicong Chen, Chenghong Zhang, Yuan Liu

“…This paper proposes PSHNet, a hybrid deep-learning framework that combines dense spatial heatmap supervision with geometry-aware regression for accurate infrared small-target detection. …”
Get full text

Anomalous Diffusion Models Involving Regularized General Fractional Derivatives with Sonin Kernels by Maryam Alkandari, Dimitri Loutchko, Yuri Luchko

“…First, we show that this master equation can be embedded into the framework of continuous time random walks, and we derive an explicit formula for the waiting time probability density function of the continuous time random walk model in form of a convolution series generated by the Sonin kernel associated with the kernel of the regularized general fractional derivative. …”
Get full text

Improved Asynchronous Federated Learning for Data Injection Pollution by Aiyou Li, Huoyou Li, Yanfang Liu, Guoli Ji

“…In view of the problems of data pollution, incomplete feature extraction, and poor multi-network parameter sharing and transmission under the federated learning framework of deep learning, this article proposes an improved asynchronous federated learning algorithm of multi-model fusion based on data injection pollution. …”
Get full text

YOLOv8n-SMMP: A Lightweight YOLO Forest Fire Detection Model by Nianzu Zhou, Demin Gao, Zhengli Zhu

“…To address these challenges, this paper proposes an enhanced forest fire detection model, YOLOv8n-SMMP (SlimNeck–MCA–MPDIoU–Pruned), based on the YOLO framework. Key innovations include the following: introducing the SlimNeck solution to streamline the neck network by replacing conventional convolutions with Group Shuffling Convolution (GSConv) and substituting the Cross-convolution with 2 filters (C2f) module with the lightweight VoV-based Group Shuffling Cross-Stage Partial Network (VoV-GSCSP) feature extraction module; integrating the Multi-dimensional Collaborative Attention (MCA) mechanism between the neck and head networks to enhance focus on fire-related regions; adopting the Minimum Point Distance Intersection over Union (MPDIoU) loss function to optimize bounding box regression during training; and implementing selective channel pruning tailored to the modified network architecture. …”
Get full text

Lightweight Stereo Matching for Real-Time Applications With 2D Cost Volume Aggregation by Thai la, Linh Tao, Dai Watanabe

“…Despite the significant advancements in learning-based stereo matching algorithms, a significant challenge remains: the high computational cost and memory demands of 3D convolutions, which hinder real-time deployment on resource-constrained platforms like edge devices. …”
Get full text

SS-EMERGE - self-supervised enhancement for multidimension emotion recognition using GNNs for EEG by Chirag Ahuja, Divyashikha Sethia

“…Therefore, this study introduces a hybrid SSL framework: Self-Supervised Enhancement for Multidimension Emotion Recognition using Graph Neural Networks (SS-EMERGE). …”
Get full text

Real-Time Far-Field BCSDF Filtering by Junjie Wei, Ying Song

“…This paper presents a real-time BCSDF filtering framework that achieves high-fidelity rendering without precomputation. …”
Get full text

Urban Traffic Flow Forecasting Based on Graph Structure Learning by Guangyu Huo, Yong Zhang, Yimei Lv, Hao Ren, Baocai Yin

“…At the same time, the temporal convolution network captures the temporal correlation between a single time series. …”
Get full text

Distributed Photovoltaic Short-Term Power Prediction Based on Personalized Federated Multi-Task Learning by Wenxiang Luo, Yang Shen, Zewen Li, Fangming Deng

“…The federal learning framework is used to enhance the privacy of photovoltaic data and improve the model’s performance in a distributed environment. …”
Get full text

An Efficient Aerial Image Detection with Variable Receptive Fields by Wenbin Liu, Liangren Shi, Guocheng An

“…This article presents VRF-DETR, a lightweight real-time object detection framework for aerial remote sensing images, aimed at addressing the challenge of insufficient receptive fields for easily confused categories due to differences in height and perspective. …”
Get full text

CKAN-YOLOv8: A Lightweight Multi-Task Network for Underwater Target Detection and Segmentation in Side-Scan Sonar by Yao Xiao, Hualong Yang, Dongchen Dai, Hongjian Wang, Ziqi Shan, Hao Wu

“…This paper proposes CKAN-YOLOv8, a lightweight multi-task network integrating Kolmogorov–Arnold Networks Convolution (KANConv) into YOLOv8. The core innovation replaces conventional convolutions with KANConv blocks using learnable B-spline activations, dynamically adapting to noise and multi-scale targets while ensuring parameter efficiency. …”
Get full text

Dual knowledge‐guided two‐stage model for precise small organ segmentation in abdominal CT images by Tao Liu, Xukun Zhang, Zhongwei Yang, Minghao Han, Haopeng Kuang, Shuwei Ma, Le Wang, Xiaoying Wang, Lihua Zhang

“…This article introduces a novel knowledge‐guided cascaded framework that utilizes two types of knowledge—image intrinsic (anatomy) and clinical expertise (radiology)—to improve the segmentation accuracy of small abdominal organs. …”
Get full text

Chinese Tone Recognition Based on 3D Dynamic Muscle Information by JianRong Wang, Li Wan, Ju Zhang, Qiang Fang, Fan Yang, Jing Hu

“…In this paper, we mainly studied the vowel tonal transformation in Chinese pronunciation and designed a lightweight skipping convolution network framework (SCNet). And, the experimental results showed that the SCNet was sensitive to the more detailed description of the pitch change than that of the traditional model and achieved a better tone recognition effect and outstanding antiinterference performance. …”
Get full text

KEDM: Knowledge-Embedded Diffusion Model for Infrared Image Destriping by Lingxiao Li, Xin Wang, Dan Huang, Yunan He, Zhuqiang Zhong, Qingling Xia

“…This approach effectively integrates the spatial distribution characteristics of stripe noise with an innovative, data-driven diffusion network model, creating a hybrid knowledge and data-driven framework for stripe correction. The core components of KEDM are the latent diffusion model (LDM) architecture and the directional wavelet convolution module (DWCM). …”
Get full text

A Lightweight Dual-Branch Complex-Valued Neural Network for Automatic Modulation Classification of Communication Signals by Zhaojing Xu, Youchen Fan, Shengliang Fang, You Fu, Liu Yi

“…Spatial and channel reconstruction convolution (SCConv) is extended to complex domain and combined with complex-valued depthwise separable convolution block (CBlock) and complex-valued average pooling to eliminate feature redundancy and extract higher order features. …”
Get full text

Fault Detection of a Wheelset Bearing Based on Appropriately Sparse Impulse Extraction by Jianming Ding, Fenglin Li, Jianhui Lin, Bingrong Miao, Lu Liu

“…Convolution sparse representation (CSR) is a novel compressive sensing technique proposed in 2016 and provides an excellent framework for extracting the impulses induced by bearing faults and the unevenness of wheel tread. …”
Get full text

Evaluation of a Deep Learning Model for Automatic Detection of Schizophrenia Using EEG Signals by Swetha Padmavathi Polisetty, Radhamani Ellapparaj, Karthikeyan M P

“…After data preprocessing to reduce noise and artifacts from EEGs, an 11-layer deep learning model consisting of convolution and LSTM layers with LeakyReLU activation function and different kernel sizes was implemented to automatically extract and classify features. …”
Get full text

A high-performance tensor computing unit for deep learning acceleration by Qiang Zhou, Tieli Sun, Taoran Shen, York Xue

“…Then, the tuner-configuration generator pruned the search space and the distributed tuner framework selected the best data-flow pattern and corresponding parameters. …”
Get full text

HSF-YOLO: A Multi-Scale and Gradient-Aware Network for Small Object Detection in Remote Sensing Images by Fujun Wang, Xing Wang

“…To address these issues, this paper proposes a novel detection framework named HSF-YOLO, which is designed to jointly enhance feature encoding, attention interaction, and localization precision within the YOLOv8 backbone. …”
Get full text