Zhuozhang Li

ORCID: 0000-0003-2427-1182
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Topic Modeling
  • Machine Learning in Healthcare
  • Image and Signal Denoising Methods
  • Image and Object Detection Techniques
  • Image Retrieval and Classification Techniques
  • Video Analysis and Summarization
  • Geophysics and Gravity Measurements
  • Digital Media Forensic Detection
  • Advanced Steganography and Watermarking Techniques
  • Domain Adaptation and Few-Shot Learning
  • Solar and Space Plasma Dynamics
  • Advanced Vision and Imaging
  • Educational and Technological Research
  • Advanced Text Analysis Techniques

Guangdong University of Technology
2020-2021

Domain adaptation on time series data is an important but challenging task. Most of the existing works in this area are based learning domain-invariant representation with help restrictions like MMD. However, such extraction a non-trivial task for data, due to complex dependence among timestamps. In detail, fully dependent series, small change lags or offsets may lead difficulty domain invariant extraction. Fortunately, stability causality inspired us explore structure data. To reduce...

10.1609/aaai.v35i8.16846 article EN Proceedings of the AAAI Conference on Artificial Intelligence 2021-05-18

Polar Harmonic Transform (PHT) is termed to represent a set of transforms those kernels are basic waves and harmonic in nature, which can improve the effect Intelligent Transportation System (ITS) applications. PHTs consist Complex Exponential (PCET), Cosine (PCT) Sine (PST). extract orthogonal rotation invariant features demonstrated superior performance various image processing computer vision For real time systems large multimedia databases, execution efficiency always significant...

10.1109/access.2020.2995392 article EN cc-by IEEE Access 2020-01-01

Domain adaptation on time series data is an important but challenging task. Most of the existing works in this area are based learning domain-invariant representation with help restrictions like MMD. However, such extraction a non-trivial task for data, due to complex dependence among timestamps. In detail, fully dependent series, small change lags or offsets may lead difficulty domain invariant extraction. Fortunately, stability causality inspired us explore structure data. To reduce...

10.48550/arxiv.2012.11797 preprint EN other-oa arXiv (Cornell University) 2020-01-01

Angular radial transform (ART) is a shape descriptor in MPEG-7 for image representation and analysis. For real world applications, execution efficiency always significant challenge. With widespread use of Graphics Processing Unit (GPU) processing tasks, this paper presents GPU based angular (GART). Proposed parallel GART on mathematical properties ART optimization techniques GPU. Optimal parameter selections are also evaluated. In our experiments, with same computation result over 1800 times...

10.1109/wsai49636.2020.9143278 article EN 2020-06-01

Polar Fourier analysis can extract orthogonal and rotation invariant features demonstrate superior performances in many image processing tasks. For real world applications, execution efficiency is always a significant challenge. With widespread use of Graphics Processing Unit (GPU), this research presents GPU accelerated polar analysis. Proposed parallel algorithm based on mathematical properties optimization techniques GPU. Optimal parameter selections for are also evaluated. In our...

10.1109/icip40778.2020.9191179 article EN 2022 IEEE International Conference on Image Processing (ICIP) 2020-09-30
Coming Soon ...