A5101752928- Advanced Vision and Imaging
- Metaheuristic Optimization Algorithms Research
- Video Coding and Compression Technologies
- Video Analysis and Summarization
- Advanced Image and Video Retrieval Techniques
- Advanced Multi-Objective Optimization Algorithms
- Evolutionary Algorithms and Applications
- Advanced Image Processing Techniques
- Robotic Path Planning Algorithms
- Space Satellite Systems and Control
- Image and Video Quality Assessment
- Face recognition and analysis
- Face and Expression Recognition
- Brain Tumor Detection and Classification
- Transportation and Mobility Innovations
- Image Retrieval and Classification Techniques
- Neural Networks and Applications
- Advanced Data Compression Techniques
- Robotics and Sensor-Based Localization
- 3D Surveying and Cultural Heritage
- Recommender Systems and Techniques
- Network Security and Intrusion Detection
- IoT-based Smart Home Systems
- Teleoperation and Haptic Systems
- IoT and Edge/Fog Computing
Hokkaido University
2024-2025
Central China Normal University
2021-2025
Zhejiang University
2024
Chengdu University of Information Technology
2008-2024
Beihang University
2022-2024
Beijing Institute of Technology
2023-2024
Chengdu Third People's Hospital
2022-2024
Southwest Jiaotong University
2024
Heilongjiang University
2024
The University of Queensland
2023
The high redundancy among keyframes is a critical issue for the prior summarizing methods in dealing with user-created videos. To address issue, we present Graph Attention Networks (GAT) adjusted Bi-directional Long Short-term Memory (Bi-LSTM) model unsupervised video summarization. First, GAT adopted to transform an image's visual features into higher-level by Contextual Features based Transformation (CFT) mechanism. Specifically, novel Salient-Area-Size-based spatial attention presented...
Abstract Background It is well known that muscle disuse atrophy associated with mitochondrial dysfunction, which implicated in reduced nicotinamide adenine dinucleotide (NAD + ) levels. Nicotinamide phosphoribosyltransferase (NAMPT), a rate‐limiting enzyme NAD biosynthesis, may serve as novel strategy to treat by reversing dysfunction. Methods To investigate the effects of NAMPT on prevention skeletal muscles predominantly composed slow‐twitch (type I) or fast‐twitch II) fibres, rabbit...
With the increasing volume of video data, how to analyze and browse in a fast effective way has become an urgent problem applications. This letter proposes novel synopsis method compressed domain for browsing captured by static cameras. Synopsis is abstraction, which displays moving objects from different periods simultaneously on primary background contents original video. To overcome low efficiency traditional video, our presents new graph cut algorithm extract tubes meanwhile gives...
This research utilizes time series models to forecast electricity generation from renewable energy sources and consumption. The configuration of optimal parameters for these typically requires optimization algorithms, but conventional algorithms may struggle with fixed search patterns limited robustness. To address this, we propose an auto-evolution hyper-heuristic algorithm named AE-GAPB. AE-GAPB integrates a genetic (GA) at the high-level component employs particle swarm (PSO) bat (BA)...
Light Field Angular Super-Resolution (LFASR) addresses the issue where (LF) images can not simultaneously achieve both high spatial and angular resolution due to limited of optical sensors. Since Spatial-Angular Correlation (SAC) features are closely related structure LF images, its accurate complete extraction is crucial for quality reconstructed by LFASR method based on Deep Neural Networks (DNNs). In low-angular SAC must be extracted from a number pixels that at great distance each other...
User simulators can rapidly generate a large volume of timely user behavior data, providing testing platform for reinforcement learning-based recommender systems, thus accelerating their iteration and optimization. However, prevalent generally suffer from significant limitations, including the opacity preference modeling incapability evaluating simulation accuracy. In this paper, we introduce an LLM-powered simulator to simulate engagement with items in explicit manner, thereby enhancing...
As a substantial amount of research has accumulated on the harmful consequences workplace aggression for target employees, we believe it is now particular importance to examine moderators that alleviate or amplify these effects. We ask following questions: For whom more less detrimental? Moreover, what can employees and organization do mitigate effects aggression? propose address questions with an integrative review empirical targets. In this review, identify illustrate five broad...
Abstract Traditional engine fault diagnosis methods usually need to extract the features manually before classifying them by pattern recognition method, which makes it difficult solve end-to-end problem. In recent years, deep learning has been applied in different fields, bringing considerable convenience technological change, and its application automotive field also many applications, such as image recognition, language processing, assisted driving. this paper, a one-dimensional...
N-methyl-D-aspartate receptor (NMDAR) is one of the main excitatory neurotransmitter glutamate in brain, which key determinant excitatory/inhibitory balance neural network. GluN2A/GRIN2A subunits NMDAR and plays an important role epilepsy. Approximately 78% patients with GluN2A/Grin2a mutations have epilepsy, underlying mechanism this association not well characterized.We constructed a mouse model hyperthermic seizure, conducted vitro vivo electrophysiological behavioral studies to clarify...