A5066091502- Human Pose and Action Recognition
- Video Surveillance and Tracking Methods
- Advanced Vision and Imaging
- Technology Adoption and User Behaviour
- Digital Marketing and Social Media
- Advanced Neural Network Applications
- Cardiovascular Disease and Adiposity
- 3D Shape Modeling and Analysis
- Cardiac Imaging and Diagnostics
- Advanced Image and Video Retrieval Techniques
- Image Enhancement Techniques
- Multimodal Machine Learning Applications
- Industrial Vision Systems and Defect Detection
- Neural dynamics and brain function
- Anomaly Detection Techniques and Applications
- Advanced Fluorescence Microscopy Techniques
- Visual Attention and Saliency Detection
- Customer Service Quality and Loyalty
- Cardiovascular Function and Risk Factors
- Computer Graphics and Visualization Techniques
- Knowledge Management and Sharing
- Spectroscopy and Chemometric Analyses
- Advanced Image Fusion Techniques
- Mineral Processing and Grinding
- Human Motion and Animation
Shanghai Academy of Spaceflight Technology
2023-2024
China Coal Technology and Engineering Group Corp (China)
2024
Case Western Reserve University
2021-2024
Minzu University of China
2019-2024
Nanjing University of Science and Technology
2024
Anhui Jianzhu University
2023-2024
California State University, Northridge
2018-2024
Central South University
2024
Hefei University of Technology
2019-2024
Wuhan Institute of Technology
2023-2024
Few-shot learning is a nascent research topic, motivated by the fact that traditional deep methods require tremendous amounts of data. The scarcity annotated data becomes even more challenging in semantic segmentation since pixellevel annotation task labor-intensive to acquire. To tackle this issue, we propose an Attentionbased Multi-Context Guiding (A-MCG) network, which consists three branches: support branch, query feature fusion branch. A key differentiator A-MCG integration multi-scale...
The rapid advances of transportation infrastructure have led to a dramatic increase in the demand for smart systems capable monitoring traffic and street safety. Fundamental these applications are community-based evaluation platform benchmark object detection multi-object tracking. To this end, we organize AVSS2017 Challenge on Advanced Traffic Monitoring, conjunction with International Workshop Street Surveillance Safety Security (IWT4S), evaluate state-of-the-art tracking algorithms...
Abstract Whole-heart coronary calcium Agatston score is a well-established predictor of major adverse cardiovascular events (MACE), but it does not account for individual calcification features related to the pathophysiology disease (e.g., multiple-vessel disease, spread along vessel, stable calcifications, numbers lesions, and density). We used novel, hand-crafted (calcium-omics); Cox time-to-event modeling; elastic net; up down synthetic sampling methods imbalanced data, assess MACE risk....
Although online social network services (OSNS), e.g., Facebook, Twitter, MySpace, LinkedIn, are enjoying rampant popularity, a subsection of the population (i.e., nonadopters) continues to forgo using them. Our study is one first focus exclusively on what might motivate nonadopters accept widely adopted IT. By considering nonadopters' inertia within context early stages innovation diffusion and incorporating status quo bias theory into well-established technology acceptance model (TAM)...
Neural network models of early sensory processing typically reduce the dimensionality streaming input data. Such networks learn principal subspace, in sense component analysis, by adjusting synaptic weights according to activity-dependent learning rules. When derived from a principled cost function, these rules are nonlocal and hence biologically implausible. At same time, plausible local have been postulated rather than function. Here, bridge this gap, we derive for subspace on data...
Automatic image visual recognition can make full use of largely available images with text descriptions on social media platforms to build large-scale labeled datasets. In this paper, we propose a novel representation, named DG-VRT (Diverse GAN-Visual Representation Text), which extracts features from synthetic generated by diverse conditional Generative Adversarial Network (DCGAN) the text, for recognition. The DCGAN incorporates current state-of-the-art text-to-image GANs and generates...
To exploit the massive amounts of onboard data in vehicular networks while protecting privacy and security, federated learning (FL) is regarded as a promising technology to support enormous applications. Despite that FL has great potential improve architecture intelligent networks, mobility vehicles dynamic nature wireless channels make integration more challenging. In this paper, we propose vehicle mobility- channel dynamic-aware (MADCA-FL) scheme fit enhance performances. This novel...
Underwater target detection is widely used in various applications such as underwater search and rescue, environment monitoring, marine resource surveying. However, the complex environment, including factors light changes background noise, poses a significant challenge to detection. We propose an improved algorithm based on YOLOv8n overcome these problems. Our focuses three aspects. Firstly, we replace original C2f module with Deformable Convnets v2 enhance adaptive ability of region...
The extraction, purification, and utilization of mineral resources have been among the largest anthropogenic sources chromium (Cr) in soil. Determining Cr contamination soil is a key issue prior to its appropriate remediation. Nevertheless, efficient identification large-scale requires continuous research. present study proposes continental-scale method rapidly identify using visible-near infrared spectroscopy (vis-NIR) machine learning (ML). A large dataset containing 18,675 topsoil samples...
The prediction of travel times is challenging because the sparseness real-time traffic data and intrinsic uncertainty on congested urban road networks. We propose a new gradient–boosted regression tree method to accurately predict times. This model accounts for spatiotemporal correlations extracted from historical adjacent target links. can deliver high accuracy by combining simple trees with poor performance. It corrects error found in existing models improved accuracy. Our was verified...
Abstract Epicardial adipose tissue volume (EAT) has been linked to coronary artery disease and the risk of major adverse cardiac events. As manual quantification EAT is time-consuming, requires specialized training, prone human error, we developed a deep learning method (DeepFat) for automatic assessment on non-contrast low-dose CT calcium score images. Our DeepFat intuitively segmented enclosed by pericardial sac axial slices, using two preprocessing steps. First, applied...
Recent studies have used basic epicardial adipose tissue (EAT) assessments (eg, volume and mean Hounsfield unit [HU]) to predict risk of atherosclerosis-related, major adverse cardiovascular events (MACEs). The purpose this study was create novel, hand-crafted EAT features, "fat-omics," capture the pathophysiology improve MACE prediction. We studied a cohort 400 patients with low-dose cardiac computed tomography calcium score examinations. purposefully MACE-enriched (56% event rate) for...