R
Roland Hu
Researcher at Zhejiang University
Publications - 44
Citations - 590
Roland Hu is an academic researcher from Zhejiang University. The author has contributed to research in topics: Segmentation & Image segmentation. The author has an hindex of 12, co-authored 42 publications receiving 494 citations. Previous affiliations of Roland Hu include University of Southampton & Université catholique de Louvain.
Papers
More filters
Proceedings ArticleDOI
Applying Spread Transform Dither Modulation for 3D-mesh watermarking by using perceptual models
TL;DR: The results show that the proposed 3D-mesh watermarking method has high tolerance to noise and is robust against mesh smoothing.
Journal ArticleDOI
Topic discovery and evolution in scientific literature based on content and citations
Houkui Zhou,Huimin Yu,Roland Hu +2 more
TL;DR: This paper proposes a citation- content-latent Dirichlet allocation (LDA) topic discovery method that accounts for both document citation relations and the con-tent of the document itself via a probabilistic generative model and tests the algorithm on two online datasets to demonstrate that it effectively discovers important topics and reflects the topic evolution of important research themes.
Journal ArticleDOI
Applying 3D Polygonal Mesh Watermarking for Transmission Security Protection through Sensor Networks
TL;DR: The proposed blind watermarking algorithm is proposed to protect the transmission security of 3D polygonal meshes through sensor networks and can achieve robustness against the cropping attack both theoretically and experimentally.
Journal ArticleDOI
Unsupervised regions based segmentation using object discovery
Bai Yang,Huimin Yu,Roland Hu +2 more
TL;DR: A fully unsupervised foreground object discovery scheme, a tree-constrained iterative algorithm, and a color-based FG model that works well on objects with complicated fine structures are proposed.
Posted Content
Structured Deep Neural Network Pruning by Varying Regularization Parameters.
TL;DR: A theoretically sound regularization-based pruning method to incrementally assign different regularization parameters to different weights based on their importance to the network, which can achieve 4x theoretical speedup with similar accuracies compared with the baselines.