X
Xingwen Guo
Researcher at University of Hong Kong
Publications - 3
Citations - 527
Xingwen Guo is an academic researcher from University of Hong Kong. The author has contributed to research in topics: Laplacian matrix & Convolutional neural network. The author has an hindex of 2, co-authored 2 publications receiving 441 citations.
Papers
More filters
Proceedings ArticleDOI
SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation
TL;DR: SyncSpecCNN as mentioned in this paper proposes a spectral convolutional neural network for 3D shape part segmentation and keypoint prediction, which enables weight sharing by parametrizing kernels in the spectral domain spanned by graph Laplacian eigenbases.
Posted Content
SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation
TL;DR: SyncSpecCNN as discussed by the authors proposes a spectral convolutional neural network for 3D shape part segmentation and keypoint prediction, which enables weight sharing by parameterizing kernels in the spectral domain spanned by graph laplacian eigenbases.
Proceedings ArticleDOI
Automatically Reconfigurable Optical Network for HPC System Based on Deep Reinforcement Learning
TL;DR: In this article , a reconfigurable optical network for HPC systems that can automatically switch between different topologies controlled by a Deep Reinforcement Learning (DRL) agent is proposed.