A5100356545- Advanced Image Fusion Techniques
- Image and Signal Denoising Methods
- Image and Video Quality Assessment
- Remote-Sensing Image Classification
- Advanced Image Processing Techniques
- Cloud Computing and Resource Management
- Blockchain Technology Applications and Security
- IoT and Edge/Fog Computing
- Privacy-Preserving Technologies in Data
- Multi-Criteria Decision Making
- Big Data Technologies and Applications
- Civil and Geotechnical Engineering Research
- Web Data Mining and Analysis
- Ovarian function and disorders
- Photorefractive and Nonlinear Optics
- Photonic and Optical Devices
- Bayesian Modeling and Causal Inference
- Grouting, Rheology, and Soil Mechanics
- Advanced Steganography and Watermarking Techniques
- Photoacoustic and Ultrasonic Imaging
- Geomechanics and Mining Engineering
- Evaluation Methods in Various Fields
- Human Mobility and Location-Based Analysis
- Advanced Optical Imaging Technologies
- Video Surveillance and Tracking Methods
Xidian University
2020-2025
Alibaba Group (China)
2024-2025
Beihang University
2025
Ningxia Medical University
2024
Inspur (China)
2024
Jinan Central Hospital
2019
Shandong University
2019
Shenzhen Institutes of Advanced Technology
2017-2018
Northeastern University
2017
Xi'an University of Science and Technology
2015
Existing free-energy guided No-Reference Image Quality Assessment (NR-IQA) methods continue to face challenges in effectively restoring complexly distorted images. The features guiding the main network for quality assessment lack interpretability, and efficiently leveraging high-level feature information remains a significant challenge. As novel class of state-of-the-art (SOTA) generative model, diffusion model exhibits capability intricate relationships, enhancing image restoration...
Online social networks, as platforms for personal expression, have evolved into complex networks integrating political and dimensions. This evolution has shifted the focus of network governance from addressing hacking activities to mitigating unpredictable behaviors, such malicious manipulation public opinion, doxing ordinary users, cyberbullying. However, sparsity data concealed nature user behavior pose significant challenges existing reconnaissance technologies. In this study, we on...
Quality assessment of medical images is highly related to the quality assurance, image interpretation and decision making. As magnetic resonance (MR) images, signal-to-noise ratio (SNR) routinely used as a indicator, while little knowledge known its consistency regarding different observers. In total, 192, 88, 76 55 brain are acquired using T2*, T1, T2 contrast-enhanced T1 (T1C) weighted MR imaging sequences, respectively. To each protocol, SNR measurement verified between within two...
Existing hyperspectral image (HSI) super-resolution (SR) methods struggle to effectively capture the complex spectral-spatial relationships and low-level details, while diffusion models represent a promising generative model known for their exceptional performance in modeling relations learning high visual features. The direct application of HSI SR is hampered by challenges such as difficulties convergence protracted inference time. In this work, we introduce novel Group-Autoencoder (GAE)...
Existing free-energy guided No-Reference Image Quality Assessment (NR-IQA) methods still suffer from finding a balance between learning feature information at the pixel level of image and capturing high-level efficient utilization obtained remains challenge. As novel class state-of-the-art (SOTA) generative model, diffusion model exhibits capability to intricate relationships, enabling comprehensive understanding images possessing better both low-level visual features. In view these, we...
Manifold causes of image blurring make the no-reference evaluation realistic blurred images very challenging. Previous studies indicate that handcrafted features suffer from poor representation intrinsic characteristics and thus blind sharpness assessment (BISA) is unsatisfactory. This paper explores a shallow convolutional neural network (CNN) to address this problem facilitated by data augmentation. Superior algorithms necessitates considerable expertise efforts handcraft for optimal...
Medical image quality assessment (MIQA) is highly related to content interpretation and disease diagnosis in medical community. However, a few metrics have been developed. On the contrary, massive models designed for natural (NIQA) field of computer vision. Connect both sides MIQA NIQA useful challenging. This study explores signal-to-noise ratio (SNR) as intermediate metric bridge gap between consequently, can be employed or modified applications. A number 411 images from 4 magnetic...
Existing hyperspectral image (HSI) super-resolution (SR) methods struggle to effectively capture the complex spectral-spatial relationships and low-level details, while diffusion models represent a promising generative model known for their exceptional performance in modeling relations learning high visual features. The direct application of HSI SR is hampered by challenges such as difficulties convergence protracted inference time. In this work, we introduce novel Group-Autoencoder (GAE)...
The power consumption flexibility provided by the energy-intensive Internet data centers (IDCs) has been extensively studied as a potential solution for enhancing of systems. In IDCs, computational workloads are further divided into potentially interdependent tasks. To assess it is necessary to consider interdependency However, there no methods deriving task dependency-aware IDC load model that easy embed in operation systems fully utilize IDCs. this end, paper proposes framework derive...
Remote-sensing images typically feature large dimensions and contain repeated texture patterns. To effectively capture finer details encode comprehensive information, feature-extraction networks with larger receptive fields are essential for remote-sensing image super-resolution tasks. However, mainstream methods based on stacked Transformer modules suffer from limited due to fixed window sizes, impairing long-range dependency fine-grained reconstruction. In this paper, we propose a...
In recent years, At home and abroad scholars proposed a great deal of mathematical models on landslide forecast, which through the fitting monitoring data trend analysis to determine landslides time.How results different identify good bad quality forecast model is an important problem decision-makers.The author effect index(including posterior index, efficiency index RMS error) experiment related coefficient index), establishment testing forecast.Using gray GM (1,1) model, three exponential...