Ship detection in Synthetic Aperture Radar (SAR) images remains challenging due to coherent speckle noise, complex inshore clutter, and large variations in target scale, especially for tiny ships. To address these issues, this paper proposes a lightweight SAR ship detection network based on YOLOv11n. The proposed model introduces a high-resolution P2 detection branch to preserve fine spatial details that may be weakened during repeated downsampling. To improve multi-scale feature representation, a Four-Head Adaptive Spatial Feature Fusion (FASFF) structure is adopted to adaptively combine features from P2, P3, P4, and P5. In addition, the Squeeze-and-Excitation (SE) attention module is inser... More >

Ship detection in Synthetic Aperture Radar (SAR) imagery is crucial for maritime surveillance. However, it faces significant challenges, including small target sizes, complex sea clutter interference, and stringent requirements for computational efficiency in on-board processing. While detection frameworks like YOLOv12 have achieved a favorable balance between speed and accuracy by integrating attention mechanisms with convolutional neural networks (CNNs), their generic architectures are not optimized for the unique physical characteristics of SAR imagery and the scattering properties of ship targets. To develop a more suitable lightweight and high-precision model for SAR ship detection, thi... More >

Image segmentation is an important task in computer vision and plays a critical role in many fields. Fuzzy Active Contour Model (FACM) has been widely applied in image segmentation because it can handle complex shape changes. However, it is difficult for current FACMs to obtain ideal performance when segmenting noisy images. Therefore, this paper proposes a Total Variation Diffusion-Guided Fuzzy Active Contour Model (TVDGFACM), which formulates noisy image segmentation as a hierarchical fusion process. Specifically, this model introduces total variation and adaptively fuses anisotropic and isotropic diffusion mechanisms to suppress noise interference while preserving image edges. Moreover, T... More >

In complex dynamic environments, infrared and visible video sequences exhibit highly variable and unpredictable feature distributions. Existing fusion algorithms with fixed architectures cannot adaptively respond to these dynamic feature changes, resulting in blurred fusion outcomes and the loss of critical detail information. To address this limitation, we propose a salient feature-driven mimic fusion algorithm that continuously monitors feature variations and dynamically reconfigures the fusion architecture to maintain optimized fusion performance. First, we extract amplitude and frequency attributes from infrared and visible video features and perform weighted fusion to calculate single-m... More >

Russian handwritten text recognition presents significant challenges due to the complex morphology of the Cyrillic alphabet, prevalent cursive writing, and substantial writer variability. To address the limitations of existing methods in dynamic contextual modeling and language-specific feature adaptation, this paper proposes an end-to-end framework named AMRC-NET. This framework integrates a multi-path architecture with linguistic feature awareness through three core modules: a Context Enhancement Module for long-range dependency modeling, a Russian Alphabet Morphology Optimization Module for script-specific pattern capture, and a Multi-Path Adaptive Fusion Mechanism for dynamic output inte... More >

In this paper, we consider the state estimation problem in a cyber-physical system (CPS) against intermittent denial-of-service (DoS) attacks, which are usually difficult to defend due to their concealment and unpredictability. To address this issue, this paper proposes a dynamic observation scheduling method based on Fisher information to achieve efficient and resilient state estimation. Specifically, a sliding window mechanism is first employed to predict the successful transmission probability for each time window. Subsequently, the method constructs a scheduling sequence by aligning these predicted probabilities with the Fisher information of the observation's components. This strategy e... More >

Genomic information is increasingly leveraged for the precise prediction of crop traits, with the adoption of advanced genomic prediction techniques resulting in substantial improvements in both crop yield and quality. However, traditional genomic prediction methods exhibit notable limitations in capturing long-range dependencies and fully utilizing prior information from chromosome structure. In this work, two novel Transformer models fusing chromosome conformation and genomic information have been proposed. One is the chromosomal self-attention fusion model, which captures cross-chromosomal interactions more precisely by introducing chromosomal conformation information into the self-attent... More >

Background: Practical implementation of radiomics research faces significant data accessibility challenges due to privacy and ethical restrictions on multicenter data aggregation. Federated Learning (FL) provides a secure distributed framework that preserves data privacy through cryptographic techniques. Its adoption in radiomics is an emerging trend, enabling collaborative training without sharing sensitive imaging data. However, the inherently Non-IID data distribution across clients in FL often leads to class imbalance, which can substantially degrade global model performance. Purpose: To develop a privacy-preserving, multicenter collaborative CT-radiomics model for evaluating neoadjuvant... More >