Xumin Yu

I am a second year Ph.D student in the Department of Automation at Tsinghua University, advised by Prof. Jiwen Lu. In 2020, I obtained my B.Eng. in the Department of Electronic Engineering, Tsinghua University.

I am broadly interested in computer vision and deep learning. My current research focuses on 3D vision and Video analysis.

Email  /  Google Scholar  /  Github

Publications

* indicates equal contribution

PoinTr is a transformer-based model for point cloud completion. By representing the point cloud as a set of unordered groups of points with position embeddings, we convert the point cloud to a sequence of point proxies and employ a transformer encoder-decoder architecture for generation. We also propose two more challenging benchmarks ShapeNet-55/34 with more diverse incomplete point clouds that can better reflect the real-world scenarios to promote future research

We propose a new contrastive regression (CoRe) framework to learn the relative scores by pair-wise comparison, which highlights the differences between videos and guides the models to learn the key hints for assessment.

We propose a graph interaction networks (GINs) model for transferring relation knowledge across two graphs two different scenarios for video analysis, including a new proposed setting for unsupervised skeleton-based action recognition across different datasets, and supervised group activity recognition with multi-modal inputs.

Our method allows machine learning algorithms to perform fine-grained estimation of physiological states (e.g., sleep depth) even if the training labels are coarse-grained.

Website Template