I am currently a Ph.D. student in the University of Illinois Urbana-Champaign (UIUC), advised by Alexander Schwing. Previously, I obtained a MPhil degree from The Hong Kong University of Science and Technology (HKUST)1, advised by Yu-Wing Tai and Chi-Keung Tang.
I am recently working on scalable (long-term and open-world) video segmentation and understanding. I am generally interested in artificial intelligence. I believe in AGIs and has high hope for their potential to transform human civilization for the better.
I first experienced programming in secondary school when I was making a competitive map (i.e., mod) for a Blizzard game Warcraft III. It started as an anti-cheat patch for an existing map. I then later started adding new features and eventually reprogrammed the entire map. It was challenging to make the game rich yet balanced. Players tend to optimize their actions in a replayable competitive game, and my task, in retrospect, was to make the optima non-trivial and dynamic (as a function of the actions of other players).
Eighteen different versions were released in the time span from 2011 to 2016.
I joined the HKUST Robotics Team in my first year of undergraduate study. We represented Hong Kong in the asia-pacific Robocon 2017 competition in Tokyo, and took home the Best Design Award.
I developed various low-level libraries (robust communication protocol, PID, drivers for peripheral sensors) and high-level functionalities (path planning, control interfaces), and picked up crucial engineering/problem solving skills during this time.
I was the chairperson for the 8th Robot Design Contest in HKUST. I am incredibly grateful to this amazing team and all the enthusiastic teammates!
CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement
Ho Kei Cheng*, Jihoon Chung*, Yu-Wing Tai, Chi-Keung Tang. Published in CVPR, 2020.
Refines segmentations (4K and beyond) in a class-agnostic manner without using any high-resolution training data through a set of carefully designed cascade operations.
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion
Ho Kei Cheng, Yu-Wing Tai, Chi-Keung Tang. Published in CVPR, 2021.
A more user-friendly and efficient paradigm of iVOS in which interactions and propagations are decoupled, with the user’s intention captured by a novel difference-aware fusion module. Used by: [Sieve], [Trioscope]
Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation
Ho Kei Cheng, Yu-Wing Tai, Chi-Keung Tang. Published in NeurIPS, 2021.
Rethinks mask tracking as an image correspondence problem and uses L2 similarity to encourage diversified voting -- simpler, better, and more efficient.