Yuang Shi (施宇昂)

I'm a second year Ph.D. Candidate at National University of Singapore advised by Prof. Wei Tsang Ooi, where I work on Networking and Multimedia Systems.

I received my M.Comp Degree in 2022 from National University of Singapore, where I did research on human activity recognition in-the-wild. I received my B. Eng. Degree in 2021 from Sichuan University in China, where I worked on Medical Image Processing.

I'm a super cat lover.

Email  /  Google Scholar  /  Github

• [04/2024] - Invited talk at Université de Toulouse, Toulouse INP-ENSEEIHT, IRIT, France.
• [03/2024] - Three paper accepted to MMVE 2024.
• [01/2024] - One paper accepted to MMSys 2024.
• [12/2023] - Invited talk at National Tsing Hua University, Taiwan.
• [12/2023] - Passed my PhD Qualification Exam.

As a PhD student, I mainly focus on volumetric video compression, evaluation, and streaming.

We present QV4, a Quality-of-Experience (QoE) based streaming system for viewpoint-aware V-PCC-encoded volumetric video. It is the first volumetric video streaming system that exploits user viewing adaptations on V-PCC-encoded content.

We represent 3D dynamic content as a sequence of NeRFs, converting the explicit representation to neural representation. We then compress the neural representation based on the insight of significant similarity between successive NeRFs.

We propose a QoE model to predict the subjective quality with respect to the compression level of geometry and texture, quantifying the impact of geometry and texture compression on perceptual quality.

We investigated the influence of rendering face quality of the avatars on users' viewing experience in MPEG V-PCC-encoded volumetric videos, and revealed the significant role of facial quality in influencing users' overall perceptual quality in volumetric videos.

We show that it is possible to improve the quality of V-PCC encoded point clouds at low bit-rate by exploiting redundant information among the points in the 3D domain.

We present an open dynamic 3D point cloud dataset with motion ground truth, which can be used by researchers who need temporal information across frames, e.g., motion estimation.

When I was a Master student, my dissertation is about human activity recognition in-the-wild.

ShapeCNF is a simple, fast, and accurate change-point detection method which uses shape-based features to model the patterns and a conditional neural field to model the temporal correlations among the time regions.

During my undergraduate, I spent most of my time on medical image analysis.

We propose a consistency training framework for semi-supervised NPC segmentation, which includes an Uncertainty-weighted Prediction Consistency Training (UPCT) strategy and a Relation-driven Consistency Training (RCT) strategy.

ASMFS is a novel multi-modal feature selection method for classification of Alzheimer's Disease, which performs adaptive similarity learning and feature selection simultaneously.

• [2024/01-2024/05] - Graduate Tutor & Teaching Assistant, CS3244 Machine Learning.
• [2023/01-2023/05] - Graduate Tutor & Teaching Assistant, CS3244 Machine Learning.
• [2022/08-2022/12] - Graduate Tutor & Teaching Assistant, CS3244 Machine Learning.

• ACM Multimedia (MM) 2024.
• Medical Image Analysis (MIA).
• IEEE Transactions on Cognitive and Developmental Systems (TCDS).
• ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM).

• [2022/11] - Student Volunteer, The 21st IEEE International Symposium on Mixed and Augmented Reality, 2022.