Tsung-Shan (Kevin) Yang

Tsung-Shan (Kevin) Yang

PhD Candidate at University of Southern California

Download CV Contact Me

About Me

Tsung-Shan (Kevin) Yang is currently a Ph.D. candidate, advised by Professor C.-C. Jay Kuo, in Electrical Engineering at the University of Southern California. He received his Bachelor’s Degree in Chemistry and Electrical Engineering from National Taiwan University (NTU) in 2019 and his Master’s Degree in Electrical Engineering from NTU in 2021.

His research interests include image understanding and machine learning.

His research can be refered to google scholar

Education

Ph.D. Candidate from University of Southern California, CA, USA
Aug 2022 - Present
Master of Science from National Taiwan University, Taipei, Taiwan
Sep 2019 - Jun 2021
Major in data science
Master thesis: "Omnidirectional Image Encoding"
GPA: 4.04/4.30
Bachelor of Science from National Taiwan University, Taipei, Taiwan
Sep 2014 - Jun 2019
Double major in Chemistry and Electrical Engineering
GPA: 3.81/4.30
Dean's List for 2 semesters (2014 Fall, 2015 Spring)

Publication

Multimodal Alignment / Image Understanding / Green Learning

GMA: Green Multi-Modal Alignment for Image-Text Retrieval (APSIPA ASC' 24)

Explainable alignment for features from two separately trained models in different modalities (image and text).

Human-Object Interaction Detection / Image Understanding / Green Learning

GHOI: A Green Human-Object-Interaction Detector (IEEE MIPR' 24)

A lightweight and human sensible human-object interaction detector.

Point Cloud / Quality Assessment / Green Learning

BPQA: A Blind Point Cloud Quality Assessment Method (IEEE ICIP' 23)

A point cloud quality assessment with statistical feature extraction and interpretable learning scheme.

Omnidirectional Video / Saliency Detection / Center Bias

Viewing Bias Matters in 360 Videos Visual Saliency Prediction (IEEE Access' 23)

Statistically analyze the human-bias in saliency maps and generalize the spherical kernel to time series data.

Omnidirectional Image / Encoding / Deep Learning

Omnidirectional Image Encoding (Master Thesis)

Propose an encoding based on great circle distance to revise the convolution output of omnidirectional images.

Dehazing / Real World Image / Deep Learning

NTIRE 2020 Challenge on NonHomogeneous Dehazing (IEEE CVPR' 20)

Propose an attention refinement block of the deep learning model.

Few Shot Learning / Clustering / Deep Learning

Few Shot Learning With Difficult Setting (CVGIP' 18)

Analyze the different approaches of few shot learning.

IC design / Machine Learning

IR Drop Prediction of ECO-Revised Circuits Using Machine Learning (IEEE VTS' 18)

Reduce 30X simulation time through deep learning.

Work Experience

T.A. of Introduction to Computer Programming at University of Southern California
2024 Fall
Design C++ projects and lead the lab sections.
Introduction to the basic c++ syntax and algorithms.
T.A. of Systems for Machine Learning at University of Southern California
2024 Spring
Impelement LLM finutuing and inferencing.
Design deep learning projects and assignments.
T.A. of Machine Learning at National Taiwan University
2019 Fall, 2020 Fall
Design assignment about theoretical analysis and deep learning projects.
Maintain the course website.
T.A. of Data Structure at National Taiwan University
2020 Spring
Design assignment about theoretical analysis and data structure implementation.
T.A. of General Chemistry at National Taiwan University
2018 Fall
Lead group discussion and provide hints of assignments.
Provide 2 hour TA class each week for over 300 students.

Contact

tsungsha AT usc.edu