Duc Nguyen
C703 Engineering Hall 3, Yonsei University, Seodaemun-gu, Seoul, Korea, 03722. | +8210-3458-9210 | adnguyen@yonsei.ac.kr
I am trying to teach machine to learn. Currently, I am working towards my PhD in Computer Vision at Yonsei University. I am interested in computer vision, machine learning, deep learning, and statistics.
I am the author of GPU Task Spooler, a simple CLI queuing system for CPU/GPU tasks in Linux.
Education
Yonsei University
PhD, Computer Vision • 2015 — 2023 (expected)
I am working in 3D computer vision which involves processing and reconstruct 3D point clouds and triangle meshes. Previously, I have experienced photo style transfer, video frame interpolation, image classification, and saliency detection.
Hanoi University of Science and Technology
Bachelor, Automatic control • 2010 — 2015
My thesis was titled "Indoor User Localization based on WiFi Fingerprinting using RSSI measurement" which implemented an indoor localization system in C++.
Associations
NAVER LABS Europe
Research Intern • Feb 2020 — July 2020
I worked with Romain Brégier in 3D Vision team. Together, we setup a benchmark for state-of-the-art deep learning point cloud convolutional operators.
IEEE P3333.1 Human Factors for Visual Experiences Working Group
Secretary • Oct 2017 — present
We develop standard documents for Quality of Experiences of various visual contents. I served as the secretary of the P3333.1.3 WG.
International Research Institute MICA: Multimedia, Information, Communication and Applications
Intern • Jan 2014 — Aug 2015
I implemented and integrated an indoor localization method based on Wifi SSI and K-Nearest Neighbor into the existing localization system at MICA, which was a part of my Undergraduate Thesis.
Publications
Single Image 3D Reconstruction: Rethinking Point Cloud Deformation
Duc Nguyen, Seonghwa Choi, Woojae Kim, Jongyoo Kim, Heeseok Oh, Jiwoo Kang, and Sanghoon Lee
IEEE Transactions on Neural Networks and Learning Systems (2022)
GradMask: Gradient-Guided Token Masking for Textual Adversarial Example Detection
Hancheol Moon, Shafiq Joty, and Xu Chi
CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING (SigKDD 2022) (Acked) (2022)
Diverse and Adjustable Versatile Image Enhancer
Woojae Kim, Anh-Duc Nguyen, Jinwoo Kim, Jongyoo Kim, Heeseok Oh, and Sanghoon Lee
IEEE Access (2021)
Statistical Convolution On Unordered Point Set
Anh-Duc Nguyen, Seonghwa Choi, Woojae Kim, Sanghoon Lee, and Weisi Lin
International Conference on Image Processing (2020)
Dynamic Receptive Field Generation for Full-Reference Image Quality Assessment
Woojae Kim, Anh-Duc Nguyen, Sanghoon Lee, and Alan Conrad Bovik
IEEE Transactions on Image Processing (2020)
Modern trends on quality of experience assessment and future work
Woojae Kim, Sewoong Ahn, Anh-Duc Nguyen, Jinwoo Kim, Jaekyung Kim, Heeseok Oh, and Sanghoon Lee
APSIPA Transactions on Signal and Information Processing (2019)
Video Frame Synthesis via Plug-and-Play Deep Locally Temporal Embedding
Anh-Duc Nguyen, Woojae Kim, Jongyoo Kim, Weisi Lin, and Sanghoon Lee
IEEE Access (2019)
GraphX-Convolution for Point Cloud Deformation in 2D-to-3D Conversion
Anh-Duc Nguyen, Seonghwa Choi, Woojae Kim, and Sanghoon Lee
International Conference on Computer Vision (acceptance rate: 25%) (2019)
POINT CLOUD DEFORMATION FOR SINGLE IMAGE 3D RECONSTRUCTION
Seonghwa Choi, Anh-Duc Nguyen, Jinwoo Kim, Sewoong Ahn, and Sanghoon Lee
International Conference on Image Processing (2019)
DISTRIBUTION PADDING IN CONVOLUTIONAL NEURAL NETWORKS
Anh-Duc Nguyen, Seonghwa Choi, Woojae Kim, Sewoong Ahn, Jinwoo Kim, and Sanghoon Lee
International Conference on Image Processing (top 10%) (2019)
A Simple Way of Multimodal and Arbitrary Style Transfer
Anh-Duc Nguyen, Seonghwa Choi, Woojae Kim, and Sanghoon Lee
IEEE International Conference on Acoustics, Speech, and Signal Processing (2019)
Multiple Level Feature-Based Universal Blind Image Quality Assessment Model
Jongyoo Kim, Anh-Duc Nguyen, Sewoong Ahn, Chong Luo, and Sanghoon Lee
International Conference on Image Processing (2018)
Video Frame Interpolation by Plug-and-Play Deep Locally Linear Embedding
Anh-Duc Nguyen, Woojae Kim, Jongyoo Kim, and Sanghoon Lee
Preprint (2018)
IEEE 3333.1.2-2017 - IEEE Standard for the Perceptual Quality Assessment of Three-Dimensional (3D) and Ultra-High-Definition (UHD) Contents
Approved standard document by the IEEE Standardization Board (2018)
Deep Visual Saliency on Stereoscopic Images
Anh-Duc Nguyen, Jongyoo Kim, Heeseok Oh, Weisi Lin, and Sanghoon Lee
IEEE Transactions on Image Processing (IF: 6.790) (2018)
Skills
Below is the list of programming languages that I enjoy and have used in certain non-trivial projects. Those that I am at hello-world level or feel painful when using will not make it here.
Python
- OOP, Multi Threading, Multi Processing, Queuing, Function Decorators, etc...
Deep Learning Python Library
- Theano, Pytorch, Tensorflow, Matconvnet, Chainer, etc...
- I am an (inactive) member of Kornia org.
- I was a contributor of Tensorflow/models and Theano.
C/C++
- OOP, STL, Multi Threading, etc...
- I am the author of GPU Task Spooler and its plugin, Messenger.
Makefile/CMake
- Build tools for GPU Task Spooler.
CUDA
- Pytorch custom Ops, Ray casting, etc...
Bash
- For writing Linux batch job scripts.
Dockerfile
- Making virtual environment for Deep Learning experiments.
Matlab
- For scientific purpose.
Web Development (HTML/CSS/JavaScript/jQuery/Liquid)
- Basic understandings to serve my undergraduate thesis.
Database Administration (MySQL/PHP)
- Basic understandings to serve my undergraduate thesis.
Latex/Beamer
- For writing papers and making presentation slides.
Awards
BK21 Outstanding Student Fellow 2019
Yonsei University • 2019
Brain Korea 21 (BK21) Scholarship
Yonsei University • 2015 — 2020
Funding my PhD program at Yonsei University.
Outstanding International Scholarship
Yonsei University • 2015 — 2018
Tuition fee support for my 3-year coursework period.
MICA Student Research Award 2014-2015
MICA Institute • 2015
Second prize.
Outstanding Student Scholarship
Hanoi University of Science and Technology • 2010 — 2015
Awarded for 4 out of 10 semesters.
Activities
Invited talk
Naver Paper Day • Oct 26, 2019
International Conference on computer vision 2019 (ICCV 2019)
Student volunteer • Oct 27, 2019 — Nov 2, 2019
Hobbies
- Football. And football.
- Books, including novels, science, philosophy, and... football.
- Movies.
- I shoot on 35mm film.
Social Links
- Github: https://github.com/justanhduc
- Facebook: https://m.facebook.com/Mr.DucAnhNguyen
- LinkedIn: https://www.linkedin.com/in/justanhduc/
- Instagram: https://www.instagram.com/_adnguyen/
- Website: http://adnlearningblog.wordpress.com/