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
Deep Learning Shape Priors for Object Segmentation
TL;DR: A new shape-driven approach for object segmentation is introduced which uses deep Boltzmann machine to learn the hierarchical architecture of shape priors, and is applied to data-driven variational methods to perform object extraction of corrupted data based on shape probabilistic representation.
Posted Content
Structured Probabilistic Pruning for Convolutional Neural Network Acceleration
TL;DR: A novel progressive parameter pruning method, named Structured Probabilistic Pruning (SPP), which effectively prunes weights of convolutional layers in a probabilistic manner and can be directly applied to accelerate multi-branch CNN networks, such as ResNet, without specific adaptations.
Journal ArticleDOI
Attributes-aided part detection and refinement for person re-identification
Shuzhao Li,Huimin Yu,Roland Hu +2 more
TL;DR: Zhang et al. as mentioned in this paper utilized the process of attribute detection to generate corresponding attribute-part detectors, whose invariance to many influences like poses and camera views can be guaranteed.
Journal ArticleDOI
Shape Sparse Representation for Joint Object Classification and Segmentation
Fei Chen,Huimin Yu,Roland Hu +2 more
TL;DR: A novel variational model based on prior shapes for simultaneous object classification and segmentation is proposed, and a sparse linear combination of training shapes in a low-dimensional representation is used to regularize the target shape in variational image segmentation.
Proceedings ArticleDOI
Constrained optimisation of 3D polygonal mesh watermarking by quadratic programming
TL;DR: A blind and robust watermarking method for 3D polygonal meshes is proposed by minimising the mean square error between the original mesh and the watermarked mesh under several constraints.