more

About

關於我

潘品齊

Pin-Chi Pan

國立台灣大學 電信工程研究所

Graduate Institute of Communication Engineering
National Taiwan University

Education

  • B.S., Department of Electrical Engineering,
    National Chung Cheng University, Taiwan (2019/9 - 2023/6)
  • M.S., Graduate Institute of Communication Engineering,
    National Taiwan University, Taiwan (2023/9 - Present)

Work Experience

  • Office of Information Technology - Web Developer
    (2021/9 - 2022/9)
  • College Admissions Committee - Web Developer
    (2022/3 - 2022/9)
  • Institute of Information Science, Academia Sinica - Summer Intern
    (2022/7 - 2022/8)
  • Institute of Information Science, Academia Sinica - Research Assistant
    (2022/9 - Present)

Independent Study Project

  • LogoGANs: Generating and Compositing Multimodal Logo based on Generative Adversarial Networks
  • Screen-Based Gaze Tracking Model
  • Global-Local Awareness Network for Image Super-Resolution
Web Development
  • Codeigniter
  • PHP
  • HTML, CSS, Javascript
  • JQuery
  • MySQL, SQLite
Research Interests
  • Deeplearning
  • Computer Vision
  • Image Generation
  • Image Restoration
  • Image Processing
Programming Language
  • C / C++
  • Python
  • MATLAB
Development Environment / IDE
  • Visual Studio Code
  • PyCharm
  • Google Colab
  • Linux
  • Github/Git
Personality Trait
  • Positive
  • Excellent Communication Skills
  • Quick Learner
  • Reliable
  • Detail-Oriented

Research

專題研究

Global-Local Awareness Network for Image Super-Resolution

While self-attention excels at modeling global information, it is less effective at capturing high frequencies (e.g., edges etc.) that deliver local information primarily, which is crucial for SISR. To tackle this, we propose a global-local awareness network (GLA-Net) to effectively capture global and local information to learn comprehensive features with low- and high-frequency information.


LogoGANs: Generating and Compositing Multimodal Logo based on Generative Adversarial Networks

Designing a logo entails a protracted and intricate process for any designer. This research endeavors to introduce a novel architecture of generative adversarial network aimed at producing multimodal logos. Our focus lies in enhancing the model performance of compositional generative adversarial networks by integrating them with spatial transformation networks.


Screen-Based Eye Tracking

In this research, we propose an appearance-based method for predicting head pose and eye gaze. Furthermore, we leverage decision trees in machine learning to accurately predict the user's viewing area on the screen. This study addresses the challenge of gaze prediction errors arising from variations in head posture, particularly when employing non-wearable devices for gaze prediction.


Side Project

專案開發

Implementation

模型實作

Participate

參與活動