A5032080339- Remote-Sensing Image Classification
- Nanoplatforms for cancer theranostics
- Remote Sensing and Land Use
- Nanoparticle-Based Drug Delivery
- Advanced Nanomaterials in Catalysis
- Photodynamic Therapy Research Studies
- Remote Sensing in Agriculture
- AI in cancer detection
- Advanced Image Fusion Techniques
- Image Retrieval and Classification Techniques
- Geotechnical Engineering and Soil Mechanics
- Immunotherapy and Immune Responses
- Infrared Target Detection Methodologies
- Geotechnical Engineering and Underground Structures
- Infrastructure Maintenance and Monitoring
- Luminescence and Fluorescent Materials
- Image Enhancement Techniques
- Video Surveillance and Tracking Methods
- Asphalt Pavement Performance Evaluation
- Geotechnical Engineering and Soil Stabilization
- Digital Imaging for Blood Diseases
- Extracellular vesicles in disease
- Skin Protection and Aging
- Handwritten Text Recognition Techniques
- Automated Road and Building Extraction
Wuhan University
2024-2025
Guangdong University of Technology
2022-2025
Wuhan University of Technology
2024-2025
Hubei University of Technology
2022-2024
University of California, San Diego
2024
Jacobs (United States)
2024
Zhejiang University
2023
Nanjing University of Chinese Medicine
2023
University of Electronic Science and Technology of China
2021
China National Chemical Engineering (China)
2015
Building Change Detection (BCD) based on high-resolution Remote Sensing Images (RSI) simplifies urban surface monitoring. Nevertheless, the mainstream detection methods utilizing traditional convolution and attention mechanisms are often prone to errors due loss of edge detail information underutilization global context information. To address these issues, this paper presents a large model, namely ADMNet, which is built adaptive deformable designed handles various types building change...
Building change detection (BCD) is essential for urban dynamic measurement. Deep learning has demonstrated significant potential in image processing, providing powerful feature extraction capabilities BCD tasks. However, existing methods do not adequately mine multiscale information and ignore the importance of alignment, leading to an inadequate representation internal structure. Therefore, we propose a hybrid attention-aware Transformer network (HATNet) designed effectively extract...
Semantic change detection (SCD) has gradually emerged as a prominent research focus in remote sensing image processing due to its critical role earth observation applications. In view of powerful semantic-driven feature extraction capability, the Segment Anything Model (SAM) demonstrated suitability across various visual scenes. However, it suffers from significant performance degradation when confronted with images, especially those containing ground objects that possess inter-class...
Cropland resources are essential for the provision of food production, which is one most fundamental needs human life. Change detection (CD) technology enables dynamic monitoring high-resolution cropland resource images acquired through remote sensing satellite sensors. However, current CD methods not capable extracting meaningful change information from dense and continuously distributed cropland. In addition, common feature fusion processing often results in redundancy loss key features....
Bone is one of the prone metastatic sites patients with advanced breast cancer. The "vicious cycle" between osteoclasts and cancer cells plays an essential role in osteolytic bone metastasis from In order to inhibit cancer, NIR-II photoresponsive bone-targeting nanosystems (CuP@PPy-ZOL NPs) are designed synthesized. CuP@PPy-ZOL NPs can trigger photothermal-enhanced Fenton response photodynamic effect enhance photothermal treatment (PTT) thus achieve synergistic anti-tumor effect. Meanwhile,...
Reactive lymphocytes are an important type of leukocytes, which morphologically transformed from lymphocytes. The increase in these cells is usually a sign certain virus infections, so their detection plays role the fight against diseases. Manual reactive undoubtedly time-consuming and labor-intensive, requiring high level professional knowledge. Therefore, it highly necessary to conduct research into computer-assisted diagnosis. With development deep learning technology field computer...
Breast cancer is one of the most prevalent diseases for women worldwide. Early and accurate ultrasound image segmentation plays a crucial role in reducing mortality. Although deep learning methods have demonstrated remarkable potential, they still struggle with challenges images, including blurred boundaries speckle noise. To generate segmentation, this paper proposes Edge-Aware Multi-Scale Group-Mix Attention Network (EMGANet), which generates by integrating edge features. The Group Mix...
Metal ions are of widespread interest owing to their brilliant biomedical functions. However, a simple and universal nanoplatform designed for assembling range functional metal has not been explored. In this study, concept polyethylene glycol (PEG)-mediated transport is proposed. 31 types PEG-metal hybrid nanoparticles (P-MNPs) successfully synthesized through anionic ring-opening polymerization (ROP), "thiol-ene" click reaction, subsequent incorporation with multiple ions. Compared other...
Suspended waterproof curtains combined with pumping wells are the primary method for controlling groundwater levels in foundation pits within soft soil areas. However, there is still a lack of systematic approach to predict drawdown pit caused by influence these suspended curtains. In order investigate variation level excavation during dewatering processes, finite difference employed analyze seepage characteristics Basing on concept equivalent well, this study examines coupled effects...
Significant challenges exist in the registration of multimodal images (MMIs) due to nonlinear radiation differences, variations lighting, and interference from image noise. These issues often lead unreliable similarity measurements low accuracy point matching during registration. To address these challenges, this letter introduces a novel MMI method based on adjacent self-similarity 3-D convolution (ASTC). The proposed consists three main steps: feature extraction, where key points are...
Building change detection (BCD) using high-resolution remote sensing images aims to identify areas during different time periods, which is a significant research focus in urbanization. Deep learning methods are capable of yielding impressive BCD results by correctly extracting features. However, due the heterogeneous appearance and large individual differences buildings, mainstream cannot further extract reconstruct hierarchical rich feature information. To overcome this problem, we propose...
Road crack detection is one of the important issues in field traffic safety and urban planning. Currently, road damage varies type scale, often has different sizes depths, making task more challenging. To address this problem, we propose a Cross-Attention-guided Feature Alignment Network (CAFANet) for extracting integrating multi-scale features damage. Firstly, use dual-branch visual encoder model with same structure but patch (one large small patch) to extract multi-level features. We...
Bone tumor patients often encounter challenges associated with cancer cell residues and bone defects postoperation. To address this, there is an urgent need to develop a material that can enable treatment promote repair. Metal–organic frameworks (MOFs) have attracted the interest of many researchers due their special porous structure, which has great potential in regenerative medicine drug delivery. However, few studies explore MOFs dual antitumor regeneration properties. In this study, we...
Currently, p-y models have been broadly adopted for estimating the lateral bearing capacity of large-diameter monopiles in offshore engineering. However, existing curves cannot reflect effect pile diameter D on response under local scouring conditions. In order to extend model a pile, well-calibrated three-dimensional pile-soil performed by ABAQUS is used study ultimate soil resistance P and initial stiffness k Lin’s model. Based numerical simulation results, two diameter-related parameters...
Road damage detection is essential to the maintenance and management of roads. The morphological road contains a large number multi-scale features, which means that existing algorithms are unable effectively distinguish fuse multiple features. In this paper, we propose dense multiscale feature learning Transformer embedding cross-shaped attention for (DMTC) network, can segment information in images improve effectiveness detection. Our DMTC makes three contributions. Firstly, adopt mechanism...
Maize is one of the world’s major food crops, and its yields are closely related to sustenance people. However, cultivation hampered by various diseases. Meanwhile, maize diseases characterized spots varying irregular shapes, which makes identifying them with current methods challenging. Therefore, we propose an adversarial training collaborating multi-path context feature aggregation network for disease density prediction. Specifically, our multi-scale patch-embedding module uses...