A5043169810- Industrial Technology and Control Systems
- Advanced Image and Video Retrieval Techniques
- Advanced Sensor and Control Systems
- Handwritten Text Recognition Techniques
- Robotics and Sensor-Based Localization
- Advanced Computational Techniques and Applications
- Advanced Neural Network Applications
- Advanced Vision and Imaging
- Video Analysis and Summarization
- Advanced Algorithms and Applications
- Vehicle License Plate Recognition
- Multimodal Machine Learning Applications
- Power Systems and Renewable Energy
- Image Retrieval and Classification Techniques
- Video Surveillance and Tracking Methods
- Human Pose and Action Recognition
- Microgrid Control and Optimization
- 3D Surveying and Cultural Heritage
- Smart Grid Energy Management
- Embedded Systems and FPGA Design
- Domain Adaptation and Few-Shot Learning
- Service-Oriented Architecture and Web Services
- Neural dynamics and brain function
- Smart Grid and Power Systems
- Hydraulic and Pneumatic Systems
Zhejiang University
2015-2025
Shaoxing University
2025
National Clinical Research
2025
Chinese Academy of Medical Sciences & Peking Union Medical College
2025
State Grid Corporation of China (China)
2021-2024
Peking University
2024
Chengdu Third People's Hospital
2024
Southwest Jiaotong University
2024
State Grid Hebei Electric Power Company
2023
Yangtze University
2007-2023
Reconstruction-based methods play an important role in unsupervised anomaly detection images. Ideally, we expect a perfect reconstruction for normal samples and poor abnormal samples. Since the generalizability of deep neural networks is difficult to control, existing models such as autoencoder do not work well. In this work, interpret image divide-and-assemble procedure. Surprisingly, by varying granularity division on feature maps, are able modulate capability model both That is, finer...
Collecting and annotating images with pixel-wise labels is time-consuming laborious. In contrast, synthetic data can be freely available using a generative model (e.g., DALL-E, Stable Diffusion). this paper, we show that it possible to automatically obtain accurate semantic masks of generated by the Off-the-shelf Diffusion model, which uses only text-image pairs during training. Our approach, termed DiffuMask, exploits potential cross-attention map between text image, natural seamless extend...
cloud computing (cloud computing) is a kind of distributed computing, referring to the network "cloud" will be huge data calculation and processing program into countless small programs, then, through system composed multiple servers process analyze these programs get results return user. This report explores intersection financial information processing, identifying risks challenges faced by institutions in adopting technology. It discusses need for intelligent solutions enhance efficiency...
Abstract In this paper, we present a new automatic diagnosis method for facial acne vulgaris which is based on convolutional neural networks (CNNs). To overcome the shortcomings of previous methods were inability to classify enough types vulgaris. The core our extract features images CNNs and achieve classification by classifier. A binary-classifier skin-and-non-skin used detect skin area seven-classifier task healthy skin. experiments, compare effectiveness CNN VGG16 network pre-trained...
Human pose comparison involves measuring the similarities in body postures between individuals to understand movement patterns and interactions, yet existing methods are often insufficiently robust flexible. In this paper, we propose a RotJoint-based pipeline for similarity estimation that is both fine-grained generalizable, as well robust. Firstly, developed comprehensive benchmark action ambiguity intuitively effectively evaluates robustness of against challenges such shape variations,...
Alzheimer's disease (AD) is a complex neurodegenerative disorder and the most common cause of dementia. By 2050, number AD cases projected to exceed 131 million, placing significant strain on healthcare systems economies worldwide. The pathogenesis multifactorial, involving hypotheses/mechanisms, such as amyloid-β (Aβ) plaques, tau protein hyperphosphorylation, cholinergic neuron damage, oxidative stress, inflammation. Despite extensive research, complexity these potentially entangled...
With the global population aging, promoting healthy aging has become a critical societal objective. Movement disorders, which include age-related motor decline and neurodegenerative diseases such as Parkinson’s disease, significantly impair quality of life impose substantial healthcare burdens. Early detection intervention are crucial, yet current assessment methods primarily rely on subjective questionnaires physical examinations, inefficient, resource-intensive, lack standardization. To...
<title>Abstract</title> A 43-year-old female patient with a history of left breast invasive carcinoma, treated mastectomy and adjuvant therapy, presented for delayed reconstruction after nearly three years stable disease. Following the mastectomy, experienced significant psychological distress due to absence her breast, severely impacting quality life. Routine follow-up examinations revealed no recurrence or metastasis. Preoperative assessments, including CT scans, 3D reconstruction,...
Abstract Background Left ventricular hypertrophy (LVH) is an independent prognostic factor for cardiovascular events and it can be detected by echocardiography in the early stage. In this study, we aim to develop a semi-automatic diagnostic network based on deep learning algorithms detect LVH. Methods We retrospectively collected 1610 transthoracic echocardiograms, included 724 patients [189 hypertensive heart disease (HHD), 218 hypertrophic cardiomyopathy (HCM), 58 cardiac amyloidosis (CA),...
The individual identification of pigs is the basis for precision livestock farming (PLF), which can provide prerequisites personalized feeding, disease monitoring, growth condition monitoring and behavior identification. Pig face recognition has problem that pig samples are difficult to collect images easily affected by environment body dirt. Due this problem, we proposed a method using three-dimension (3D) point clouds pig's back surface. Firstly, cloud segmentation model based on...