A5101914224- Advanced Image Processing Techniques
- Imbalanced Data Classification Techniques
- Image and Video Quality Assessment
- Image and Signal Denoising Methods
- Anomaly Detection Techniques and Applications
- Advanced Image Fusion Techniques
- Image Processing Techniques and Applications
- Educational Technology and Assessment
- ECG Monitoring and Analysis
- Artificial Intelligence in Healthcare
- Gait Recognition and Analysis
- Face and Expression Recognition
- Online Learning and Analytics
- EEG and Brain-Computer Interfaces
- Human Pose and Action Recognition
- Innovative Teaching and Learning Methods
- Learning Styles and Cognitive Differences
Harbin Institute of Technology
2018-2024
Ocean University of China
2017-2018
Electrocardiogram (ECG) signal is critical to the classification of cardiac arrhythmia using some machine learning methods. In practice, ECG datasets are usually with multiple missing values due faults or distortion. Unfortunately, many established algorithms for require a fully complete matrix as input. Thus it necessary impute data increase effectiveness few values. this paper, we compare main methods estimating in electrocardiogram data, e.g., “Zero method”, “Mean “PCA‐based and...
This paper reviews the NTIRE 2024 Challenge on Shortform UGC Video Quality Assessment (S-UGC VQA), where various excellent solutions are submitted and evaluated collected dataset KVQ from popular short-form video platform, i.e., Kuaishou/Kwai Platform. The database is divided into three parts, including 2926 videos for training, 420 validation, 854 testing. purpose to build new benchmarks advance development of S-UGC VQA. competition had 200 participants 13 teams valid final testing phase....
Academic performance is one of the indicators to evaluate achievement college students, which plays an important role in individual development. However, it worth mentioning that personality traits and thinking styles have influence on academic performance. To further study correlation among traits, performance, we carry out a series experiments using certain C programming language course as example. Firstly, eliminate overlap by principal component analysis (PCA). Then, three groups...
For flexible non-blind image denoising, existing deep networks usually take both noisy and noise level map as the input to handle various levels with a single model. However, in this kind of solution, variance (i.e., level) is only deployed modulate first layer convolution feature channel-wise shifting, which limited balancing removal detail preservation. In paper, we present novel enoising network (CFMNet) by equipping an U-Net backbone multi-layer conditional modulation (CFM) modules....
Collaborative learning has been widely used in educational contexts. Considering that group formation is one of the key processes collaborative learning, aim this paper to propose a method obtain inter-homogeneous and intra-heterogeneous groups. In method, problem translated into combinatorial optimization problem, an improved genetic algorithm approach also proposed cope with problem. To evaluate we carry out computational experiments based on eight datasets different levels complexity. The...
With the advancement of new curriculum reform, educators put more attentions on quality physical education (PE). However, traditional way to evaluate PE class is not efficient and often time-wasting. In this paper, we attempt realize automatic evaluation by activity recognition. Recently, recognition methods are widely applied in various fields, e.g., surveillance, content-based video indexing. This paper utilizes an method performance students from their activities recorded videos order...
Full-Reference Image Quality Assessment (FR-IQA) metrics such as PSNR, SSIM, and LPIPS have been widely adopted for evaluating image restoration (IR) methods. However, pristine-quality images are usually not available, making inferior No-Reference (NR-IQA) seem to be the only solutions in practical applications. Fortunately, when methods, paired degraded generally available. Thus, this paper takes a step forward develop Degraded-Reference IQA (DR-IQA) model while respecting its...