National Chung Cheng University

Multimedia Lab., Department of Electrical Engineering

Wen-Nung Lie
https://wnlie.ccu.edu.tw/

Research Field

Smart Computing (Information)

Introduction

Wen-Nung Lie (M’96) received the B.S., M.S., and PhD. Degrees in electrical engineering from National Tsing Hua University, Hsinchu, Taiwan, in 1984, 1986, and 1990, respectively. From September 1990 to June 1996, he served as an assistant scientist in Chung Shan Institute of Science and Technology (CSIST), Taiwan, where he was devoted to the development of infrared imaging system and target tracker for military applications. In August 1996, he joined the Department of Electrical Engineering, National Chung Cheng University, Chia-Yi, Taiwan, where he is currently a Professor and was the Vice Dean of the College of Engineering. From July 2000 to January 2001, he was a Visiting Scholar in the University of Washington, Seattle. His research interests include image/video compression, networked video transmission, audio/video watermarking, multimedia content analysis, machine learning, standard-compliant multimedia encryption, infrared image processing, 3-D TV related, 2-D to 3-D image/video conversion, industrial inspection, and deep learning for computer vision applications.

This lab is to do researches on computer vision based on the modern deep learning (machine learning) techniques. In our research, you will learn deep learning techniques such as CNN, RNN, LSTM, AE, VAE, etc. The possible applications and topics include: (1) 3D human skeleton extraction, skeleton-based action recognition, action prediction for elderly monitoring, (2) depth estimation from mono- binocular images, (3) 3D object (vehicle, pedestrian, cyclist) detection and positioning from fusion of RGB/LiDAR sensor data, (4) mapless robot navigation based on deep reinforce learning (DRL), (5) object (head/vehicle/human/object)  pose estimation from single RGB image, (5) deep learning-based adverse drug reaction (ADR) prediction for clinic medicine use, (6) elderly caring application of AI-generated content (AIGC), such as (text/audio/image) -to-(image/video). The intern student is expected to have some preliminary knowledge on NN (neural network) or deep learning and skilled in Python programming. He/She will learn how to apply state-of-the-art deep learning techniques to solve the indicated problems. For more detail about my topics, please visit my Youtube video at: https://youtu.be/tIwenpyFRhw


Research Topics

Computer vision applications based on deep learning techniques


Honor

World's Top 2% Scientist, 2020, 2021


Educational Background

BS, MS, and PhD from Department of Electrical Engineering, National Tsing-Hua University (NTHU), Taiwan in 1984, 1986, and 1990, respectively.


1 Vacancy

Job Description

This research is to estimate the 3D human skeleton or 3D human mesh model from a single RGB image based on deep learning approach.

Preferred Intern Education Level

Final-year undergraduate student or post-graduate student.

Skill sets or Qualities

Python language, Deep neural network knowledge.

1 Vacancy

Job Description

This research is to recognize human actions from skeleton-based sequence.

Preferred Intern Education Level

Final-year undergraduate or first-year post-graduate student

Skill sets or Qualities

Python language programming and deep neural network techniques

1 Vacancy

Job Description

This research is to predict ADR (Adverse Drug Reaction) from EMRs or EHRs time series data. This is a research in medicine field.

Preferred Intern Education Level

year-3 above undergraduate students

Skill sets or Qualities

Python language programming and deep neural network techniques

1 Vacancy

Job Description

This research is to estimate grasp pose (7 DoF) for robotic arm for cluttered objects.

Preferred Intern Education Level

year-3 or above undergraduate students

Skill sets or Qualities

Python language programming and deep neural network techniques