I am a third-year Ph.D. student at the University of North Carolina at Chapel Hill in the Department of Computer Science and advised by Prof. Alex C. Berg in the Computer Vision Group. From Oct. 2011 to Jun. 2014, I worked as a research assistant at Academia Sinica in Taiwan with Dr. Tyng-Luh Liu. In 2010, I received my B.S. and M.S. in Computer Science from National Tsing Hua University under the supervision of Prof. Ren-Song Tsay. My previously research interests were multi-core simulation and embedded system, but now I am more intereted in and totally committed to computer vision and deep learning.

Google Scholar, Resume


Conference and Workshop Publications

DSSD : Deconvolutional Single Shot Detector [arXiv] [demo]
Cheng-Yang Fu*, Wei Liu*, Ananth Ranga, Ambrish Tyagi, and Alexander C. Berg
arXiv preprint arXiv:1701.06659, *=Equal Contribution
Fast Single Shot Detection and Pose Estimation [arXiv]
Patrick Poirson, Phil Ammirato, Cheng-Yang Fu, Wei Liu, Jana Kosecka, and Alexander C. Berg
3DV 2016
SSD: Single Shot MultiBox Detector [arXiv] [code]
Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C. Berg
ECCV 2016 (oral)
Attacking the One-Out-Of-m Multicore Problem by Combining Hardware Management with Mixed-Criticality Provisioning [pdf] [longer version pdf]
Namhoon Kim, Bryan C. Ward, Micaiah Chisholm, Cheng-Yang Fu, James H. Anderson, and F. Donelson Smith.
RTAS 2016
Outstanding Paper Award and Best Student Paper Award
A High-Parallelism Distributed Scheduling Mechanism for Multi-Core Instruction-Set Simulation [pdf]
Meng-Huan Wu, Peng-Chih Wang, Cheng-Yang Fu, and Ren-Song Tsay
DAC 2011
A Shared-Variable-Based Synchronization Approach to Efficient Cache Coherence Simulation for Multi-Core Systems [pdf]
Cheng-Yang Fu, Meng-Huan Wu, and Ren-Song Tsay
DATA 2011
An Effective Synchronization Approach for Fast and Accurate Multi-core Instruction-set Simulation [pdf]
Meng-Huan Wu, Cheng-Yang Fu, Peng-Chih Wang, and Ren-Song Tsay

Useful Links

Academic Countdown