Yuhuang Hu
Zürich, Switzerland
H +41 76 519 95 11
B yuhuang.hu@ini.uzh.ch
2017-present Ph.D. Student, Institute of Neuroinformatics, UZH/ETH Zürich, Zürich, Switzerland.
2016–2017 MScNSC, Institute of Neuroinformatics, UZH/ETH Zürich, Zürich, Switzerland.
2011–2015 BCompSc
, Department of Artificial Intelligence, Faculty of Comp Sci & Info Tech, University
of Malaya, Kuala Lumpur, Malaysia.
{ Algorithm design and implementation, Data analysis.
{ Professional in Deep Learning, Computer Vision.
{ Professional in Self-supervised Learning, Event-based Learning and Processing.
{ Familiar with Natural Language Processing, Acoustic Processing.
{ Professional in Python programming and development.
{ Proficient at PyTorch, Tensorflow, and modern Deep Learning tools.
{ Familiar with C/C++, Java, Matlab programming.
{ Familiar with modern VCS and CI/CD.
{ Quick learning and problem-solving under time constraints.
{ Critical thinking and eective communication.
Languages { Chinese: Native. English: Fluent.
¯ https://www.linkedin.com/in/duguyue100
Project Highlights
2021 v2e: From Video Frames to Realistic DVS Events (Best Paper Award Finalist).
This project introduces the
toolbox that generates realistic synthetic DVS events from
intensity frames.
2020 DDD20: End-to-End Event Camera Driving Dataset.
51h of DAVIS camera and vehicle control data collected from 4000 km of highway and urban
driving. We report the first study of fusing brightness change events and intensity frame data
using a deep learning approach to predict the instantaneous steering wheel angle.
2019 Learning to Exploit Multiple Vision Modalities by Using Grafted Networks.
This project proposes a self-supervised learning method, Network Grafting Algorithm (NGA).
NGA allows new vision sensors such as event camera and thermal camera to capitalize on
previously pretrained powerful deep models.
2018 Incremental Learning meets Reduced Precision Networks.
An empirical study of how reduced precision training methods impact the iCARL incremental
learning algorithm. The incremental network accuracy on image datasets shows that weights
can be quantized to 1 bit without severe drop in accuracy.
2017 Understanding Iterative Estimation in Gated Neural Networks (Master Thesis).
This thesis shows how we can overcome the vanishing gradient problem in a plain recurrent
network by analyzing the gating mechanisms in Gated Neural Networks.
2016 Max-Pooling Operations in Deep Spiking Neural Networks.
This project proposes three implementations of the max-pooling operation that result in a low
performance loss during spiking neural network conversion.
Mar. 2018-
May. 2019
Teaching Assistant, D-ITET, ETH Zürich, Zürich, Switzerland.
Teaching assistant of Projects & Seminars module for bachelor students. Focused on Deep
Learning and Computer Vision using Raspberry Pi. (Spring semesters 2018, 2019)
Oct. 2016-
Sep. 2017
Technical Assistant, iniLabs GmbH, Zürich, Switzerland.
Part-time technical assistant on: Neuromorphic devices, maintenance, etc.
Oct. 2012-
Jul. 2015
Research Assistant, Advanced Robotic Lab, University of Malaya.
A Generalized Quantum-Inspired Decision Making Model, Deep Learning, Robotics.
Sep. 2012-
Dec. 2014
Teaching Assistant, Faculty of Comp Sci & Info Tech, University of Malaya.
TA for Programming I (WXES1116) and Data Structure (WXES1117).
Sep. 2014 Google Summer of Code 2014 (Sponsored by Google and OpenCog Organization).
Dec. 2013 My Robot, Cover story of Life & Times, New Straits Times (December 16).
Aug. 2013
Silver medal of HuroCup Marathon category in 18th FIRA RoboWorld Cup & Congress
2013, Kuala Lumpur, Malaysia.
Feb. 2013 Dean’s List for Semester I Session 2012/2013 (Faculty of CS & IT, University of Malaya).
Selected Publications
Main contributions
[1] Y. Hu
, S-C. Liu, and T. Delbruck. “v2e: From Video Frames to Realistic DVS Events”
in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops
(CVPRW), Virtual, 2021.
[2] Y. Hu
, T. Delbruck, S-C. Liu, “Learning to Exploit Multiple Vision Modalities by Using
Grafted Networks” in The 16th European Conference on Computer Vision (ECCV), Online,
[3] Y. Hu
, J. Binas, D. Neil, S-C. Liu, T. Delbruck, “DDD20 End-to-End Event Camera
Driving Dataset: Fusing Frames and Events with Deep Learning for Improved Steering
Prediction” in The 23rd IEEE International Conference on Intelligent Transportation Systems
(ITSC), Virtual, 2020.
[4] Y. Hu
, T. Delbruck, S-C. Liu “Incremental Learning Meets Reduced Precision Networks”
in 2019 IEEE International Symposium on Circuits and Systems (ISCAS), Sapporo, Japan,
[5] Y. Hu
, A.E.G. Huber, J. Anumula, S-C. Liu, “Overcoming the vanishing gradient
problem in plain recurrent networks”, arXiv:abs/1801.06105, 2018.
[6] Y. Hu
, H. Liu, M. Pfeier, T. Delbruck, “DVS Benchmark Datasets for Object Tracking,
Action Recognition and Object Recognition”, Frontiers in Neuroscience, 10:405, 2016.
I-A. Lungu, A. Aimar,
Y. Hu
, T. Delbruck, and S-C. Liu, “Siamese Networks for
Few-shot Learning on Edge Embedded Devices”, IEEE Journal on Emerging and
Selected Topics in Circuits and Systems, 10(4):488–497, 2020.
Y. Gao, N.I. Nikolov,
Y. Hu
, R.H.R. Hahnloser, “Character-Level Translation with
Self-attention” in 2020 Annual Conference of the Association for Computational Linguistics
(ACL), Online, 2020.
S. Wang,
Y. Hu
, J. Burgués, S. Macro, S-C. Liu, “Prediction of Gas Concentration
Using Gated Recurrent Neural Networks” in 2020 2nd IEEE International Conference on
Artificial Intelligence Circuits and Systems (AICAS), Genoa, Italy, 2020.
N.I. Nikolov,
Y. Hu
, MX. Tan, R.H.R. Hahnloser, “Character-level Chinese-English
Translation through ASCII Encoding” in The Third Conference on Machine Translation
(WMT18), Brussels, Belgium, 2018.
B. Rueckauer, I-A. Lungu,
Y. Hu
, M. Pfeier, S-C. Liu, “Conversion of Continuous-
Valued Deep Networks to Ecient Event-Driven Networks for Image Classification”,
Frontiers in Neuroscience, 11:682, 2017.