A5032443390- Infrared Target Detection Methodologies
- Advanced Neural Network Applications
- Advanced Measurement and Detection Methods
- Domain Adaptation and Few-Shot Learning
- Video Surveillance and Tracking Methods
- Spectroscopy and Chemometric Analyses
- Spectroscopy Techniques in Biomedical and Chemical Research
- Calibration and Measurement Techniques
- Privacy-Preserving Technologies in Data
- Machine Learning and Data Classification
- Remote-Sensing Image Classification
- DNA and Biological Computing
- Industrial Vision Systems and Defect Detection
- Multimodal Machine Learning Applications
- AI in cancer detection
- Fire Detection and Safety Systems
- Insect-Plant Interactions and Control
- Phytoplasmas and Hemiptera pathogens
- Thermography and Photoacoustic Techniques
- Human Pose and Action Recognition
- Machine Learning and Algorithms
- Brain Tumor Detection and Classification
- Advanced Chemical Sensor Technologies
- Optical Polarization and Ellipsometry
- Dementia and Cognitive Impairment Research
Gannan Normal University
2025
Institute of Information Engineering
2023-2024
Chinese Academy of Sciences
2023-2024
Nanjing University of Aeronautics and Astronautics
2024
Hangzhou Dianzi University
2024
Northeastern University
2024
University of Chinese Academy of Sciences
2023
Tianjin Research Institute of Water Transport Engineering
2022
Nanjing University of Science and Technology
2012
Shanghai Normal University
2007
Detecting infrared small targets under cluttered background is mainly challenged by dim textures, low contrast and varying shapes. This paper proposes an approach to facilitate target detection learning contrast-enhanced shape-biased representations. The cascades a contrast-shape encoder shape-reconstructable decoder learn discriminative representations that can effectively identify objects. applies stem of central difference convolutions few large-kernel extract shape-preserving features...
In the context of rising global prevalence obesity, traditional intervention measures have proven insufficient to meet demands personalized and sustainable health management, necessitating exploration innovative solutions through technologies. This study explores how advanced digital technologies, including Internet Things (IoT) Artificial Intelligence (AI), can manage weight enhance full-lifecycle in individuals with obesity under simulated high-altitude hypoxic conditions (HC). The...
Typically, infrared small target detection aims to accurately localize objects from complex backgrounds where the object textures are often dim and shapes varying. A feasible solution is learning discriminative representations with deep convolutional neural networks (CNNs). However, learned by traditional CNNs suffer low shape bias. In this work, we propose a unified framework learn shape-biased for facilitating explicitly incorporating information into model learning. The cascades...
Abstract A rapid spectroscopic approach for whole‐organism fingerprinting of Fourier transform infrared (FT‐IR) spectroscopy was used to analyse 16 isolates from five closely related species Fusarium : F. graminearum , moniliforme nivale semitectum and oxysporum . Principal components analysis hierarchical cluster were study the clusters in data. On visual inspection both methods, spectra not differentiated into separate corresponding these unsupervised methods failed identify fungal...
Federated learning provides a privacy-preserving manner to collaboratively train models on data distributed over multiple local clients via the coordination of global server. In this paper, we focus label distribution skew in federated learning, where due different user behavior client, distributions between are significantly different. When faced with such cases, most existing methods will lead suboptimal optimization inadequate utilization information clients. Inspired by this, propose...
Federated learning provides a privacy-preserving manner to collaboratively train models on data distributed over multiple local clients via the coordination of global server. In this paper, we focus label distribution skew in federated learning, where due different user behavior client, distributions between are significantly different. When faced with such cases, most existing methods will lead suboptimal optimization inadequate utilization information clients. Inspired by this, propose...
This work explores the utility of multimodal imaging techniques such as Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET) in early detection Alzheimer’s disease (AD), well importance machine learning, notably convolutional neural networks (CNNs). In order to enhance diagnostic performance brain scans, study employed a range models, Visual Geometry Group 16 (VGG16), EfficientNetB7, hybrid Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) architecture,...
A multi-modal information fusion algorithm with LiDAR point cloud and camera images for ship target detection is proposed. It can effectively solve the limitations of single sensor environment perception has higher precision robustness.
There exists three variables in the radiative transfer equation based on dynamic energy conservation, including polar angle, azimuth angle and normalized penetrate depth. In order to solute this with double integral first step is introduce proper method isolate azimuthal dependency from angle. paper, we propose a novel phase matrix expansion Zernike polynomials, which represents probability of scattering events. The results show that it can provide new improved strategy for solution...