Xiang (Ryan) Li

I am a third-year Ph.D. student at the University of Illinois Urbana-Champaign (UIUC), advised by Prof. James Rehg.

Previously, I obtained my bachelor's degree at the Hong Kong University of Science and Technology (HKUST), where I was advised by Prof. Yu-Wing Tai and Prof. Chi-Keung Tang.

Email  /  Google Scholar  /  Github  /  LinkedIn

We present a weakly-supervised Video State-Changing Object Segmentation (VSCOS) benchmark, revealing challenges in current VOS models for state-changing objects and introducing three solutions for improved state-changing object segmentation.

We introduce YouTubePD, the first public multimodal benchmark for Parkinson's Disease (PD) analysis, crowdsourced from existing YouTube videos featuring over 200 subjects. The benchmark provides diverse expert annotations and suggests three tasks, with experimental evaluations indicating the potential and limits of deep learning models for real-world clinical applications.

We introduce a two-stage model and training strategies for one-shot object detection by integrating the metric learning with an anchor-free Faster R-CNN-style detection pipeline.

A few-shot segmentation dataset containing 1000 varied and balanced object categories with pixelwise annotation of ground-truth segmentation.

This website's template is from Jon Barron.