Charig Yang

I am a fourth (final) year PhD student at the Visual Geometry Group (VGG) at University of Oxford, advised by Andrew Zisserman and Weidi Xie. I am also interning at Meta from June to December 2024, working on multimodal LLMs, and am expected to graduate by April 2025.

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

My PhD research focuses on exploring new applications of computer vision using `time' as self-supervision. I am particularly interested in (i) new applications previously unachievable in computer vision, (ii) simple and elegant solutions (to existing/new problems).

Shuffling and ordering sequences reveals changes that are monotonic over time

SAM + Optical Flow works amazingly well in two ways: (i) flow as input to SAM (ii) flow as prompt to guide SAM's RGB input

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

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

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

2022-23: A2 (second-year) Electronic and Information Engineering, B14 (third-year) Information Engineering Systems, C18 (fourth-year) Computer Vision and Robotics
2021-22: B14 (third-year) Information Engineering Systems
2020-21: P2 (first-year) Electronic and Information Engineering, A1 (second-year) Mathematics, C19 (fourth-year) Machine Learning

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

Template gratefully stolen from here.