I interned at NVIDIA this summer as a performance software engineering intern while pursuing a Master's in Computer Science at UIUC.
Previously, I worked as a C++ backend engineer at Intouch Games.
I succeeded in handling game-related issues independently and had contributed to over two dozen slot games in eight months.
Before this role, I was a Computer Science undergraduate student at National Chiao Tung University. During my collegiate experience, I was lucky to have the opportunity to work with Prof. Wen-Hsiao Peng
as a research student. Additionally, I was a software engineer intern at Logitech in my senior year.
The above experiences made me determine to pursue a software engineering career.
Hence, I’m looking for an opportunity where I can put my abilities to work for a mission I’m passionate about.
UIUC MCS Aug. 21 - Dec. 22
NVIDIA Software Intern May. 22 - Aug. 22
Intouch Games C++ Backend Engineer Sep. 20 - May. 21
Logitech Software Intern Mar. 20 - Jun. 20
NCTU CS Research Student Apr. 19 - Feb. 20
News
[05/2022] Start my internship at NVIDIA TensorRT team!
[08/2021] Start my graduate study at UIUC MCS.
[09/2020] Start my job at Intouch Games Ltd..
[03/2020] Start my internship at Logitech MBG PQA team.
[01/2020] One paper accepted at ISCAS'20.
[04/2019] Start working as a research student at NCTU advised by Prof. Wen-Hsiao Peng.
[09/2017] Start participating in the UI/UX department at NCTU+.
Publications
Semantic Segmentation on Compressed Video Using Block Motion Compensation and Guided Inpainting
Stefanie Tanujaya, Tieh Chu, Jia-Hao Liu, Wen-Hsiao Peng
ISCAS 2020 (Oral Presentation)
This paper addresses the problem of fast semantic segmentation on compressed video.
Unlike most prior works for video segmentation, which perform feature propagation based on optical
flow estimates or sophisticated warping techniques, ours takes advantage of block motion vectors in
the com- pressed bitstream to propagate the segmentation of a keyframe to subsequent non-keyframes.
This approach, however, needs to respect the inter-frame prediction structure, which often suggests
recursive, multi-step prediction with error propagation and accumulation in the temporal dimension.
To tackle the issue, we refine the motion-compensated segmentation using inpainting. Our inpainting
network incorporates guided non-local attention for long-range reference and pixel-adaptive convolution
for ensuring the local coherence of the segmentation. A fusion step then follows to combine both the
motion-compensated and inpainted segmentations. Experimental results show that our method outperforms
the state-of-the-art baselines in terms of segmentation accuracy. Moreover, it introduces the least
amount of network parameters and multiply-add operations for non- keyframe segmentation.
@article{chao18radiotherapy,
title = {Radiotherapy Target Contouring with Convolutional Gated Graph Neural
Network},
author = {Chao, Chun-Hung and Cheng, Yen-Chi and Cheng, Hsien-Tzu and Huang, Chi-Wen and
Ho, Tsung-Ying and Tseng, Chen-Kan
Lu, Le and Sun, Min},
journal = {arXiv preprint arXiv:1904.02912},
year = {2019},
}
Projects
Heart Rate Monitor
A heart rate monitor using NodeMCU that can detect and monitor heart rate in real-time and show results on the dashboard.
| dashboard demo video |
pdf |