A5101605461- Visual Attention and Saliency Detection
- Laser-induced spectroscopy and plasma
- Indoor and Outdoor Localization Technologies
- Advanced Neural Network Applications
- Advanced Image and Video Retrieval Techniques
- Advanced SAR Imaging Techniques
- Advanced Battery Materials and Technologies
- Analytical chemistry methods development
- Remote Sensing and LiDAR Applications
- Ideological and Political Education
- Video Surveillance and Tracking Methods
- Radar Systems and Signal Processing
- Microwave Imaging and Scattering Analysis
- Direction-of-Arrival Estimation Techniques
- Adaptive Control of Nonlinear Systems
- Ion-surface interactions and analysis
- Image and Video Quality Assessment
- Advancements in Battery Materials
- Automated Road and Building Extraction
- Advanced materials and composites
- Surface Roughness and Optical Measurements
- Adaptive Dynamic Programming Control
- Adversarial Robustness in Machine Learning
- Advanced Battery Technologies Research
- Synthetic Aperture Radar (SAR) Applications and Techniques
Lanzhou University
2023-2025
Dalian University of Technology
2019-2025
University of Electronic Science and Technology of China
2024-2025
Harbin Institute of Technology
2022-2024
Lanzhou University of Technology
2024
Beijing University of Posts and Telecommunications
2024
Northeast Electric Power University
2024
Wuhan National Laboratory for Optoelectronics
2022-2023
Huazhong University of Science and Technology
2003-2023
Shanghai University of Engineering Science
2023
Location and appearance are the key cues for video object segmentation. Many sources such as RGB, depth, optical flow static saliency can provide useful information about objects. However, existing approaches only utilize RGB or flow. In this paper, we propose a novel multi-source fusion network zero-shot With help of interoceptive spatial attention module (ISAM), importance each source is highlighted. Furthermore, design feature purification (FPM) to filter inter-source incompatible...
The completeness of road extraction is very important for application. However, existing deep learning (DP) methods often generate fragmented results. prime reason that DP-based use square kernel convolution, which challenging to learn long range contextual relationships roads. produce fractures in the local interference area. Besides, quality results will be subjected resolution remote sensing (RS) image. Generally, an algorithm worse fragmentation when used data differs from training set....
In general, the existence of surface defects in hot rolled strip steel will seriously affect quality and appearance industrial products. order to improve classification efficiency accuracy defect recognition. Firstly, a lightweight high-precision deep learning neural network, parallel attention convolutional is proposed this paper. fusion model combined with multi-scale module focus important feature information capture context without losing information. Secondly, verify model, Parameters,...
W-particle-reinforced Al alloys were prepared on a 7075 aluminum alloy surface via laser melt injection to improve their wear resistance, and the microstructure, microhardness, resistance of W/Al layers studied. Scanning electron microscopy (SEM) results confirmed that melting layer about 1.5 mm thickness contained W particles, Al4W was formed alloys. Due reinforcement particles good bonding matrix, showed excellent compared
Device-free localization (DFL) is a technique of locating targets via wireless sensor networks (WSNs) without carrying any electronic devices. This article introduces device-free vehicle system that can determine the position and 2-D size dynamic in monitoring region ultra wide band (UWB) networks. Specifically, our involves an obstructed recognition model for detecting state links, state-input radio tomography imaging (SI-RTI) algorithm reconstructing high-resolution image, contour...
In recent years, radio tomography image (RTI) becomes a hot topic in device-free localization, which needs target taking no electronic device indoor environment. However, the state-of-the-art does not efficiently solve problems of localization accuracy introduced by multipath interference, and cannot work well to locate multi-person. Due ultra wide band (UWB) owns good resolution, high robustness, stability. this paper, we introduce UWB sensor networks into RTI system track moving order...
A novel composite cathode for lithium ion batteries, Li3V2(PO4)3‖Li2NaV2(PO4)3/C, was synthesized by a sol-gel method. Cetyltrimethylammonium bromide (CTAB) used as surfactant while polyvinylidene difluoride (PVDF) the carbon source. X-ray diffraction (XRD) and Raman results showed that components of this are monoclinic Li3V2(PO4)3, rhombohedral Li2NaV2(PO4)3 an amorphous carbon-coating. Four potential plateaus occur at charge/discharge curves longest plateau is observed 3.8/3.7 V....
<title>Abstract</title> In order to study the signal stability of reheated double pulse laser-induced breakdown spectroscopy (LIBS). Utilizing single Gaussian and Vortex pulse, distance between lens sample is changed exam focus position effect by measuring plasma emission spectrum. The maximum intensity achieved when focal point behind target. Vortex-Gaussian LIBS schemes, variation spectral with inter-pulse delay time are also investigated. change has a great correlation energy presents...