Charig Yang

I am a second-year PhD student at the Visual Geometry Group (VGG) at University of Oxford, advised by Andrew Zisserman and Weidi Xie. I am also part of Autonomous Intelligent Machines and Systems at University of Oxford, and am generously funded by EPSRC and AIMS.

I did my undergraduate in Engineering Science, also at Oxford. During which, I spent lovely summers at Japan Railways, Metaswitch, True, CP Group, and Oxford’s Engineering Department.

Prior to which, I was born and raised in the suburbs of Bangkok, Thailand.

Email  /  CV  /  Twitter  /  Github  /  Google Scholar

profile photo
Research

I work to make computers understand visual information (a field known as computer vision). I am particularly interested in building a system that is able to learn without manual supervision (self-supervised learning), especially in videos (as opposed to images).


It's About Time: Analog Clock Reading in the Wild
Charig Yang, Weidi Xie, Andrew Zisserman
Arxiv, 2021
project page / arXiv

We show that neural networks can read analog clocks in unconstrained environments without manual supervision.


Self-supervised Video Object Segmentation by Motion Grouping
Charig Yang, Hala Lamdouar, Erika Lu, Andrew Zisserman, Weidi Xie
Short: CVPR Workshop on Robust Video Scene Understanding, 2021 (Best Paper Award) Full: ICCV, 2021
project page / arXiv

We use transformers to group independently moving parts into layers, resulting in self-supervised segmentation.


Betrayed by Motion: Camouflaged Object Discovery via Motion Segmentation
Hala Lamdouar, Charig Yang, Weidi Xie, Andrew Zisserman
ACCV, 2020
project page / arXiv

We consider the task of camouflaged animal discovery and present a large-scale video camouflage dataset.

Teaching

2021-22: B14 (third-year) Information Engineering Systems (at Engineering Science Department)
2020-21: P2 (first-year) Electronic and Information Engineering, A1 (second-year) Mathematics, C19 (fourth-year) Machine Learning (at Exeter and St Peter's Colleges)

You can find my summary notes for all P and A modules, and some B modules here.


Template gratefully stolen from here.