S
Shiguang Shan
Researcher at Chinese Academy of Sciences
Publications - 512
Citations - 30066
Shiguang Shan is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Facial recognition system & Computer science. The author has an hindex of 76, co-authored 475 publications receiving 23566 citations. Previous affiliations of Shiguang Shan include University of Maryland, College Park & Media Research Center.
Papers
More filters
Journal ArticleDOI
Learning to Diffuse: A New Perspective to Design PDEs for Visual Analysis
TL;DR: A new PDE framework, named learning to diffuse (LTD), is proposed, to adaptively design the governing equation and the boundary condition of a diffusion PDE system for various vision tasks on different types of visual data.
Journal ArticleDOI
Cross-pose face recognition based on partial least squares
TL;DR: This paper proposes a novel cross-pose face recognition method based on partial least squares (PLS), which maximizes the squares of the intra-individual correlations and leads to improvements in recognizing faces across pose differences.
Proceedings ArticleDOI
Discriminative Covariance Oriented Representation Learning for Face Recognition with Image Sets
TL;DR: A Discriminative Covariance oriented Representation Learning (DCRL) framework to bridge the gap between face recognition with image sets and set model classification, and elaborately design two different loss functions which respectively lead to two different representation learning schemes.
Journal ArticleDOI
Learning Expressionlets via Universal Manifold Model for Dynamic Facial Expression Recognition
TL;DR: In this paper, an expression video clip is characterized as a spatial-temporal manifold (STM) formed by dense low-level features, and a universal manifold model (UMM) is learned over all lowlevel features and represented as a set of local modes.
Book ChapterDOI
Relative forest for attribute prediction
TL;DR: A Relative Tree algorithm which facilitates more accurate nonlinear ranking to capture the semantic relationships and a Relative Forest algorithm which resorts to randomized learning to reduce training time of Relative Tree are developed.