Y
Yiqun Hu
Researcher at Nanyang Technological University
Publications - 39
Citations - 1759
Yiqun Hu is an academic researcher from Nanyang Technological University. The author has contributed to research in topics: Salient & Feature (computer vision). The author has an hindex of 17, co-authored 39 publications receiving 1699 citations. Previous affiliations of Yiqun Hu include University of Western Australia & PayPal.
Papers
More filters
Proceedings ArticleDOI
Sparse approximated nearest points for image set classification
Yiqun Hu,Ajmal Mian,Robyn Owens +2 more
TL;DR: This paper introduces a novel between-set distance called Sparse Approximated Nearest Point (SANP) distance, which enforces sparsity on the sample coefficients rather than the model coefficients and jointly optimizes the nearest points as well as their sparse approximations.
Journal ArticleDOI
Face Recognition Using Sparse Approximated Nearest Points between Image Sets
Yiqun Hu,Ajmal Mian,Robyn Owens +2 more
TL;DR: An efficient and robust solution for image set classification which includes the image samples of the set and their affine hull model and jointly optimizes the nearest points as well as their sparse approximations is proposed.
Journal ArticleDOI
Random Walks on Graphs for Salient Object Detection in Images
TL;DR: A semisupervised learning technique is used to determine the labels of the unlabeled nodes by optimizing a smoothness objective label function on the newly created “pop-out graph” model along with some weighted soft constraints on the labeled nodes.
Book ChapterDOI
Motion Context: A New Representation for Human Action Recognition
TL;DR: This paper proposes a novel motion-based representation called Motion Context (MC), which is insensitive to the scale and direction of an action, by employing image representation techniques, and tests the approach on two human action video datasets.
Journal ArticleDOI
Salient Region Detection by Modeling Distributions of Color and Orientation
TL;DR: A robust salient region detection framework based on the color and orientation distribution in images is presented and is carried out on a large image database annotated with ldquoground-truthrdquo salient regions, provided by Microsoft Research Asia, which enables us to conduct robust objective level comparisons with other salient regions detection algorithms.