A5100317577- Image Enhancement Techniques
- AI in cancer detection
- Video Surveillance and Tracking Methods
- Image Retrieval and Classification Techniques
- Advanced Neural Network Applications
- Robotic Path Planning Algorithms
- Advanced Image and Video Retrieval Techniques
- 3D Shape Modeling and Analysis
- Advanced Image Processing Techniques
- Image and Signal Denoising Methods
- Geotechnical Engineering and Analysis
- Advanced Image Fusion Techniques
- Advanced Vision and Imaging
- Topic Modeling
- Carbohydrate Chemistry and Synthesis
- Human Pose and Action Recognition
- Seismology and Earthquake Studies
- Glycosylation and Glycoproteins Research
- Geotechnical Engineering and Underground Structures
- Natural Language Processing Techniques
- Radiomics and Machine Learning in Medical Imaging
- Geophysical Methods and Applications
- Medical Image Segmentation Techniques
- Electric Vehicles and Infrastructure
- Ultrasonics and Acoustic Wave Propagation
Jiangsu University of Technology
2025
Capital University of Physical Education and Sports
2025
Guilin University of Technology
2024-2025
Northeastern University
2019-2024
Peking University
2023-2024
Jilin University
2009-2024
North China Electric Power University
2024
First Hospital of Jilin University
2024
Chinese University of Hong Kong
2023-2024
Zhejiang Energy Research Institute
2024
Forest fire is becoming one of the most significant natural disasters at expense ecology and economy. In this article, we develop an effective SqueezeNet based asymmetric encoder-decoder U-shape architecture, Attention U-Net (ATT Squeeze U-Net), mainly functions as extractor a discriminator forest fire. This model takes attention mechanism to highlight useful features suppress irrelevant contents by embedding Gate (AG) units in skip connection structure. way, salient are emphasized so that...
There are two shortcomings in the application of traditional A* algorithm path planning autonomous driving. One is that vehicle environment description method suitable for not given; other contours and kinematic constraints considered. Therefore, according to characteristics unstructured environment, this paper presents an combining global navigation layer local layer, proposes a motion based on improved driving vehicles environment. In algorithm, profile collision avoided by setting...
In recent years, learning-based single image dehazing networks have been comprehensively developed. However, performance improvement is limited due to domain shift between trained synthetic hazy images and untrained real-world images. To alleviate this issue, paper proposes a targeted training scheme which nearly realizes paired data training. As result, Twofold Multi-scale Generative Adversarial Network (TMS-GAN) consisting of Haze-generation GAN (HgGAN) Haze-removal (HrGAN) designed. HgGAN...
Abstract Background Diabetes mellitus (DM) is a chronic metabolic disease that could produce severe complications threatening life. Its early detection thus quite important for the timely prevention and treatment. Normally, fasting blood glucose (FBG) by physical examination used large-scale screening of DM; however, some people with normal (NFG) actually have suffered from diabetes but are missed examination. This study aimed to investigate whether common indexes can be identify individuals...
We introduce a large-scale 3D shape understanding benchmark using data and annotation from ShapeNet object database. The consists of two tasks: part-level segmentation shapes reconstruction single view images. Ten teams have participated in the challenge best performing outperformed state-of-the-art approaches on both tasks. A few novel deep learning architectures been proposed various representations report techniques used by each team corresponding performances. In addition, we summarize...
Photochemical glycosylation has attracted considerable attention in carbohydrate chemistry. However, to the best of our knowledge, visible-light-promoted via photoactive glycosyl donor not been reported. In study, we report a photosensitizer-free visible-light-mediated approach using 2-glycosyloxy tropone as donor. This reaction proceeds at ambient temperature give wide range O-glycosides or oligosaccharides with yields up 99%. method is further applied stereoselective preparation various...
Trajectory planning is one of the key technologies for autonomous driving. A* algorithm a classical trajectory that has good results in field robot path planning. However, there are still some practical problems to be solved when applied vehicles, such as fails consider vehicle contours, planned not smooth, and it lacks speed In order solve these problems, this paper proposes processing method tracking algorithm. First, configuring safe redundancy space given considering contour, then,...
Event camera is an emerging imaging sensor for capturing dynamics of moving objects as events, which motivates our work in estimating 3D human pose and shape from the event signals. Events, on other hand, have their unique challenges: rather than static body postures, signals are best at local motions. This leads us to propose a two-stage deep learning approach, called EventHPE. The first-stage, FlowNet, trained by unsupervised infer optical flow events. Both events closely related dynamics,...
Objectives The relationship between cathepsins and prostate cancer (PCa) has been reported. However, there is a lack of research on benign diseases (BPDs). This study investigated the potential genetic link BPDs through utilization Mendelian randomization (MR) analysis to determine if causal exists. Methods Publicly accessible summary statistics were obtained from FinnGen Biobank. data comprised 149,363 individuals, with 30,066 cases 119,297 controls for BPH, 123,057 3,760 prostatitis. IEU...
The influence of anisotropy on dissimilar aluminum alloy FSW joints were studied by changing the welding direction and advancing side materials. results show significant differences in both mechanical properties microstructure welded joints. 0°7AS joint has highest tensile strength (414MPa), reaching 87% 2A12 alloys strength. smallest average grain size weld nugget, best recovery recrystallization ability, exhibits pronounced anisotropy. In HAZ, strongest texture types 45°7AS are different....
Safety-critical cyber-physical systems (CPS), such as quadrotor UAVs, are particularly prone to cyber attacks, which can result in significant consequences if not detected promptly and accurately. During outdoor operations, the nonlinear dynamics of UAV systems, combined with non-Gaussian noise, pose challenges effectiveness conventional statistical machine learning methods. To overcome these limitations, we present QUADFormer, an advanced attack detection framework for UAVs leveraging a...
We present the Unit Region Encoding of floorplans, which is a unified and compact geometry-aware encoding representation for various applications, ranging from interior space planning, floorplan metric learning to generation tasks. The floorplans are represented as latent encodings on set boundary-adaptive unit region partition based clustering proposed density map. extracted by trained network (URE-Net) input dense map other available semantic maps. Compared over-segmented rasterized images...
This study presents a sustainable approach to transform waste cooking oil (WCO) into multifunctional 3D-printable photocurable elastomer with integrated self-healing capabilities. A linear monomer, WCO-based methacrylate fatty acid ethyl ester (WMFAEE), was synthesized via sequential strategy of transesterification, epoxidation, and ring-opening esterification. By copolymerizing WMFAEE hydroxypropyl acrylate (HPA), novel developed, which could be amenable molding using an LCD light-curing 3D...
Learning English through videos has long been proven to be an effective learning method. However, Chinese learners have quite different attitudes towards this approach. This paper uses both quantitative and qualitative methods investigate analyze the factors that influence learners’ by watching videos. The research shows encouragement from teachers is most crucial influencing factor. Some suggestions for teachers, educational departments, parents are also put forward in paper.