Tieh (Daisy) Chu
email: tiehchu2@illinois.edu     phone: +1(217)979-8969

| LinkedIn |

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.

sym

UIUC
MCS
Aug. 21 - Dec. 22

sym

NVIDIA
Software Intern
May. 22 - Aug. 22

sym

Intouch Games
C++ Backend Engineer
Sep. 20 - May. 21

sym

Logitech
Software Intern
Mar. 20 - Jun. 20

sym

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
sym

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)

| abstract | video | pdf |

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
sym

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 |

sym

Contextual Attention Inpainting Network with Non-local Blocks
Combined contextual attention module and non-local blocks to address image semantic segmentation problem.
| pdf |

sym

League of Legends -- The Consistency between Emotion Management and Rank
Collected data and employed 4 machine learning models to explore relationships between players' emotion management and their performances in League of Legends
| video |

sym

UAV Autopilot-- Face Detection and Obstacle Avoidance
Designed a system for drones that can utilize computer vision to perform autonomous navigation and landing from one point to another while avoiding human faces on a track.
| demo video (only includes marker detection) |

  Honor and Awards
  • Tau Beta Pi Engineering Honor Society Outstanding Graduate Awards, UIUC
  • SS Radhakrishnan Scholarship, UIUC
  • Tau Beta Pi Engineering Honor Society Member, UIUC
  • IEEE Eta Kappa Nu Honor Society Member, Taiwan
  • 1st Place, Taiwan Intelligent Transportation Creative Idea Competition (ITCIC)
  • Yang Li Lau Tai Scholarship
  • Teacher Association Scholarship, New Taipei City Educational Association
  • Outstanding Academic Achievement Award, NCTU
  • Rotary Club of Yung Ho Fellowship
  • Outstanding Academic Achievement Award in Digital Circuit Design, NCTU

Template: this