A5100634465- Advanced Image and Video Retrieval Techniques
- Medical Image Segmentation Techniques
- Radiomics and Machine Learning in Medical Imaging
- Image Retrieval and Classification Techniques
- Optical measurement and interference techniques
- Image and Signal Denoising Methods
- Video Surveillance and Tracking Methods
- Robotics and Sensor-Based Localization
- Network Traffic and Congestion Control
- Advanced Neural Network Applications
- Advanced MRI Techniques and Applications
- Medical Imaging Techniques and Applications
- Advanced machining processes and optimization
- Multimodal Machine Learning Applications
- Simulation and Modeling Applications
- Industrial Vision Systems and Defect Detection
- Advanced Surface Polishing Techniques
- AI in cancer detection
- Complex Network Analysis Techniques
- Power Systems and Technologies
- Advanced X-ray and CT Imaging
- COVID-19 diagnosis using AI
- Sparse and Compressive Sensing Techniques
- Image Processing Techniques and Applications
- Robotic Path Planning Algorithms
Wannan Medical College
2025
Shanghai Maritime University
2025
Zhijiang College of Zhejiang University of Technology
2022-2024
Zhejiang University of Technology
2011-2024
Tongji University
2011-2024
Beijing Jiaotong University
2018-2024
Harbin Institute of Technology
2022-2024
Northwestern Polytechnical University
2015-2024
Jilin University
2020-2024
State Grid Corporation of China (China)
2024
Thanks to the success of deep learning, cross-modal retrieval has made significant progress recently. However, there still remains a crucial bottleneck: how bridge modality gap further enhance accuracy. In this paper, we propose self-supervised adversarial hashing (SSAH) approach, which lies among early attempts incorporate learning into in fashion. The primary contribution work is that two networks are leveraged maximize semantic correlation and consistency representations between different...
Non-local low-rank tensor approximation has been developed as a state-of-the-art method for hyperspectral image (HSI) restoration, which includes the tasks of denoising, compressed HSI reconstruction and inpainting. Unfortunately, while its restoration performance benefits from more spectral bands, runtime also substantially increases. In this paper, we claim that lies in global subspace, subspaces each full band patch group should lie subspace. This motivates us to propose unified paradigm...
With the goal of effectively identifying common and salient objects in a group relevant images, co-saliency detection has become essential for many applications such as video foreground extraction, surveillance, image retrieval, annotation. In this paper, we propose unified framework by introducing two novel insights: 1) looking deep to transfer higher-level representations using convolutional neural network with additional adaptive layers could better reflect properties co-salient objects,...
In recent years, hashing has attracted more and attention owing to its superior capacity of low storage cost high query efficiency in large-scale cross-modal retrieval. Benefiting from deep leaning, continuously compelling results retrieval community have been achieved. However, existing methods either rely on amounts labeled information or no ability learn an accuracy correlation between different modalities. this paper, we proposed Unsupervised coupled Cycle generative adversarial Hashing...
Deep network based cross-modal retrieval has recently made significant progress. However, bridging modality gap to further enhance the accuracy still remains a crucial bottleneck. In this paper, we propose Graph Convolutional Hashing (GCH) approach, which learns modality-unified binary codes via an affinity graph. An end-to-end deep architecture is constructed with three main components: semantic encoder module, two feature encoding networks, and graph convolutional (GCN). We design as...
Defects in the textile manufacturing process lead to a great waste of resources and further affect quality products. Automated guarantee fabric materials is one most important demanding computer vision tasks smart manufacturing. This survey presents thorough overview algorithms for defect detection. First, this review briefly introduces importance inevitability detection towards era artificial intelligence. Second, methods are categorized into traditional learning-based algorithms,...
Accurate tumor, node, and metastasis (TNM) staging, especially N staging in gastric cancer or the on lymph node diagnosis, is a popular issue clinical medical image analysis which gemstone spectral imaging (GSI) can provide more information to doctors than conventional computed tomography (CT) does. In this paper, we apply machine learning methods GSI of cancer. First, use some feature selection metric reduce data dimension space. We then employ K-nearest neighbor classifier distinguish from...
Antiferromagnetic (AF) skyrmions are topological spin structures with fully compensated, net-zero magnetization. Compared to their ferromagnetic (FM) skyrmion counterparts, reduced stray field and enhanced electrical response can enable linear, high-throughput current-driven motion. However, bubble-like character in conventional bilayer AFs limits stability fluctuations, leading deformation annihilation. Here we present the engineering of a composite AF chiral multilayer, wherein interplay...
Background: There is limited understanding of the effect salt types on progression cardiovascular disease (CVD) and their longevity, due to previous evidence from cross-sectional studies. The purpose this study was evaluate association type with CVD all-cause mortality in American population by using a prospective design. Methods: National Health Nutrition Examination Survey (NHANES) large, complex, public health survey US population. Weighted Cox proportional hazard ratios (HRs) 95%...
Abstract New energy represented by wind and solar is often used in conjunction with storage devices due to its changing characteristics. For the three-phase two-level power conversion system (PCS), a super twisting algorithm (STA) control strategy based on error model proposed this paper. This method can maintain quality of grid current when has large harmonics; it operate different modes meet factor requirements. The high parameter robustness resist drift components. Theoretical analysis...
ABSTRACT A modified finite‐time convergence sliding mode control method is presented in this paper for the power conversion system integrated with LLCL filter applied battery energy storage system. The strategy mainly possesses several merits including restricted time to equilibrium and strong robustness uncertainties of parameters. state error model established first as a preliminary step design. Then, surface approaching rule are determined obtain dedicated law output voltage generated by...
High-strength carbon fiber reinforced polymer (CFRP) composites have become popular materials to be utilized in the aerospace and automotive industries, due their unique superior mechanical properties. An understanding of cutting temperatures is rather important when dealing with high-strength CFRPs, since machining defects are likely occur because high (especially semi-closed drilling process). The friction behavior at flank tool-workpiece interface CFRPs plays a vital role heat generation,...