Recent Publications

Sparsely Aggregated Convolutional Networks.
ECCV, 2018.   PDF Github
Learning to Forecast Videos of Human Activity with Multi-granularity Models and Adaptive Rendering.
Preprint, 2018.   PDF
Colorizing Color Images.
HVEI, 2018.   PDF Code
Attribute Recognition from Adaptive Parts.
BMVC, 2016.   PDF


August 2018 – Present
Cambridge, MA, USA

Visiting Student

HanLab @ MIT

Supervisor: Song Han

January 2018 – July 2018
Beijing, China

Reseasrch Intern

Video Segmentation Group @ Sensetime

Mentor: Jianping Shi

May 2017 – May 2018
Vancouver, Canada

Reseasrch Assistant.

Computational Vision Lab @ SFU

Supervisor: Brian Funt

May 2017 – July 2017
California, USA

Deep Learning Enginneer

Self-driving Group @ TuSimple

Mentor: Panqu Wang

May 2015 – May 2017
Vancouver, Canada

Reseasrch Assistant

Graphic and Vision Lab @ SFU

Supervisor: Ping Tan

Recent & Upcoming Talks

Sparsely Aggregated Convolution Networks
Deep Learning Tutorial for Computer Visioners
Neural Style Transform Explained
Deep Learning Tutorial for Beginners



A tool to counter PyTorch model FLOPs.

A simple and flexible toolbox for MXNet framework.

Seq2seq + attention model for English to Chinese machine translation.

God says, let there be color, then the deep neural network brings the color.

A new method for video stylization that keeps the temporal consistency and reasonable time costs