Jason Kuen

I am a PhD student advised by Prof. Yap-Peng Tan at Nanyang Technological University (NTU), Singapore. I also collaborate with Dr. Gang Wang (Alibaba AI Labs) on my research. Prior to this, I was an undergraduate at Multimedia University, with Kian Ming Lim being my thesis supervisor.
My research interests are deep learning (including its domain-agnostic aspects) and its applications in computer vision.


2015 - 2019

PhD (School of EEE)

2010 - 2014

BIT in Artificial Intelligence



July 2018 - Oct 2018

Research Intern

Aug 2017 - Dec 2017

Research Intern

Nov 2014 - Jan 2015

Project Officer

Jun 2012 - Oct 2012

Summer Intern



Scaling Object Detection by Transferring Classification Weights

ICCV 2019 (oral)

Jason Kuen, Federico Perazzi, Zhe Lin, Jianming Zhang, Yap-Peng Tan


Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks

CVPR 2018

Jason Kuen, Xiangfei Kong, Zhe Lin, Gang Wang, Jianxiong Yin, Simon See, Yap-Peng Tan


Motion-Guided Cascaded Refinement Network for Video Object Segmentation

CVPR 2018
TPAMI 2019

Ping Hu, Gang Wang, Xiangfei Kong, Jason Kuen, Yap-Peng Tan


Dual Attention Matching Network for Context-Aware Feature Sequence based Person Re-Identification

CVPR 2018

Jianlou Si, Honggang Zhang, Chun-Guang Li, Jason Kuen, Xiangfei Kong, Alex Kot, Gang Wang


DelugeNets: Deep Networks with Efficient and Flexible Cross-layer Information Inflows

ICCV 2017 Workshop on Compact and Efficient Feature Representation and Learning in Computer Vision (CEFRL), Oral

Jason Kuen, Xiangfei Kong, Gang Wang, Yap-Peng Tan


Recurrent Attentional Networks for Saliency Detection

CVPR 2016

Jason Kuen, Zhenhua Wang, Gang Wang


Recent Advances in Convolutional Neural Networks

Pattern Recognition (PR) 2017

Jiuxiang Gu, Zhenhua Wang, Jason Kuen, Lianyang Ma, Amir Shahroudy, Bing Shuai, Ting Liu, Xingxing Wang, Li Wang, Gang Wang, Jianfei Cai, Tsuhan Chen


Self-taught learning of a deep invariant representation for visual tracking via temporal slowness principle

Pattern Recognition (PR) 2015

Jason Kuen, Kian Ming Lim, Chin Poo Lee



In the first ever formal programming course in my life (which was in my pre-undergraduate year), I single-handedly created WinRAP or Windows Running Applications Protector. It was the very first app for Windows users to "magically" make the desktop applications of choice disappear temporarily (while still running in the background) for privacy and security purposes. Of course, antivirus software had to flag it as malicious after it had become fairly popular.

In the distant past, I was fascinated with graphic design and the related software (e.g., Photoshop, Illustrator). As an amateur hobbyist, I used to design T-shirts, banners, and magazine covers to name a few, for the (educational, extracurricular, and online) communities I belonged to. Here are samples of my mediocre design works.