A5032515095- Ubiquitin and proteasome pathways
- Visual Attention and Saliency Detection
- RNA modifications and cancer
- Video Surveillance and Tracking Methods
- Real-time simulation and control systems
- Advanced Vision and Imaging
- Robotics and Sensor-Based Localization
- Innovative Microfluidic and Catalytic Techniques Innovation
- Machine Learning in Materials Science
- Traffic Prediction and Management Techniques
- Cancer-related gene regulation
- Elasticity and Material Modeling
- Image Processing Techniques and Applications
- Advanced Image Fusion Techniques
- Human Mobility and Location-Based Analysis
- Electric and Hybrid Vehicle Technologies
- Remote-Sensing Image Classification
- Asymmetric Hydrogenation and Catalysis
- Advanced Neural Network Applications
- Traffic and Road Safety
- Ferroptosis and cancer prognosis
- Cancer, Lipids, and Metabolism
- Olfactory and Sensory Function Studies
- Vehicle Dynamics and Control Systems
- Advanced Image and Video Retrieval Techniques
Hubei University of Medicine
2023-2024
Chongqing Medical University
2024
Taihe Hospital
2024
Shandong University
2024
Tongji University
2023
Dalian University of Technology
2021
Accident anticipation attempts to predict whether an accident may occur in advance, which is greatly significant for improving the safety of intelligent vehicles. Most existing approaches integrate features accident-relevant agents with spatial information anticipation. However, these ignore actual spatio-temporal state missing agents, they are occluded or left, relevant occurrence. To address this issue, we propose a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML"...
Multi-agent collaborative perception (MCP) has recently attracted much attention. It includes three key processes: communication for sharing, collaboration integration, and reconstruction different downstream tasks. Existing methods pursue designing the process alone, ignoring their intrinsic interactions resulting in suboptimal performance. In contrast, we aim to propose a Unified Collaborative framework named UMC, optimizing communication, collaboration, processes with Multi-resolution...
Elastography is a non-invasive medical imaging technique to map the spatial variation of elastic properties soft tissues. The quality reconstruction results in elastography highly sensitive noise induced by measurements and processing. To address this issue, we propose deep learning (DL) model based on conditional Generative Adversarial Networks (cGANs) improve nonhomogeneous shear modulus reconstruction. train model, generated synthetic displacement field with finite element simulation...
Collaborative perception is dedicated to tackling the constraints of single-agent perception, such as occlusions, based on multiple agents' multi-view sensor inputs. However, most existing works assume an ideal condition that all cameras are continuously available. In reality, may be highly noisy, obscured or even failed during collaboration. this work, we introduce a new robust camera-insensitivity problem: how overcome issues caused by camera perspectives, while stabilizing high...
Hyperspectral image (HSI) and light detection ranging (LiDAR) data joint classification has been applied in the field of ground category recognition. However, existing methods still perform poorly extracting high-dimensional features elevation information, resulting insufficient accuracy. To address this challenge, we propose a novel efficient Calibration-Enhanced Multi-Awareness Network (CEMA-Net), which exploits spectral–spatial–elevation depth to realize accurate identification land cover...
Multi-agent collaborative perception (MCP) has recently attracted much attention. It includes three key processes: communication for sharing, collaboration integration, and reconstruction different downstream tasks. Existing methods pursue designing the process alone, ignoring their intrinsic interactions resulting in suboptimal performance. In contrast, we aim to propose a Unified Collaborative framework named UMC, optimizing communication, collaboration, processes with Multi-resolution...
Path following is a crucial technique for ensuring the safe and efficient operation of automatic electric vehicles. Four-wheel steering (4WS) technology known to enhance accuracy flexibility such In this paper, we propose new constrained model predictive control (MPC) based method path-following, specifically 4WS To simplify vehicle kinematics model, use assumption pure rolling it single-track model. We employ high-precision linearization transformation convert nonlinear models linear...
Stereo depth estimation plays a crucial role in enabling robots, autonomous driving and other applications. As an ill-posed problem, both deep learning based traditional methods have been extensively studied recent years. Traditional mainly focus on feature matching between multiple images to estimate depth, but often result blank pixels with zero disparity also require significant computation time. In this paper, we propose new stereo algorithm the dynamic programming method known as...
Abstract Background PPM1F has been shown to play diverse biological functions in the progression of multiple tumors. controls T788/T789 phosphorylation switch ITGB1 and regulates integrin activity. However, impacts on ovarian cancer (OV) remain unclear. whether there is such a regulatory relationship between not studied. Therefore, purpose this study elucidate function mechanism cancer. Methods The expression level survival curve were analyzed by databases. Gain loss applied explore Tumor...