profile picture
Ho Kei (Rex) Cheng

I am currently a Ph.D. candidate at the University of Illinois Urbana-Champaign, advised by Alexander Schwing. Before that, I was at The Hong Kong University of Science and Technology, advised by Yu-Wing Tai and Chi Keung Tang. I am recently working on scalable video understanding, including video object segmentation and open-world object tracking. I am delighted to have worked closely with Seoung Wug Oh, Brian Price, and Joon-Young Lee at Adobe Research in 2022.

Looking for student collaborators in video segmentation. Feel free to contact me.

[GitHub] | [Google Scholar] | [CV]


Research (hover over videos to play):
arXiv 2023
Project page / code / arXiv / pdf
Equipped with an object transformer that integrates pixel-level features and object-level features for efficient and robust video object segmentation in challenging scenarios.
ICCV 2023
Project page / code / arXiv / pdf
Open-world video segmentation achieved by combining universal image segmentation with temporal propagation. Easy to extend.
Ho Kei Cheng, Alexander Schwing.
ECCV 2022
Project page / code / arXiv / pdf
We look at video object segmentation from a memory perspective and design a pipeline that models both short-term and long-term dependencies effectively. Used by supervisely and Track-Anything.
Ho Kei Cheng, Yu-Wing Tai, Chi Keung Tang.
NeurIPS 2021
Project page / code / arXiv / pdf
We devise a new, simple, and effective way of modeling correspondences between pixels from different frames. Used by Trioscope and BURST.
Ho Kei Cheng, Yu-Wing Tai, Chi Keung Tang.
CVPR 2021
Project page / code / arXiv / pdf
We decouple the problem of interactive video segmentation into single-frame interaction and temporal propagation, showing that this works better by a large margin. Used by Sieve.
CVPR 2020
Project page / code / arXiv / pdf / pypi
We train an iterative refinement network that generalizes to high-quality/high-resolution (4K+) segmentation with just low-resolution (<500 pixels per side) data.


Misc: