J
Junhui Hou
Researcher at City University of Hong Kong
Publications - 236
Citations - 6392
Junhui Hou is an academic researcher from City University of Hong Kong. The author has contributed to research in topics: Computer science & Point cloud. The author has an hindex of 27, co-authored 192 publications receiving 2712 citations. Previous affiliations of Junhui Hou include Northwestern Polytechnical University & Southeast University.
Papers
More filters
Journal ArticleDOI
Video summarization via block sparse dictionary selection
TL;DR: Experimental results on two benchmark datasets demonstrate that the proposed SBOMP based VS method clearly outperforms several state-of-the-art sparse representation based methods in terms of F-score, redundancy among keyframes and robustness to outlier frames.
Proceedings ArticleDOI
Light Field Spatial Super-Resolution via Deep Combinatorial Geometry Embedding and Structural Consistency Regularization
TL;DR: A novel learning-based LF spatial SR framework, in which each view of an LF image is first individually super-resolved by exploring the complementary information among views with combinatorial geometry embedding, which preserves more accurate parallax details, at a lower computation cost.
Journal ArticleDOI
3D Point Cloud Attribute Compression Using Geometry-Guided Sparse Representation
TL;DR: Experimental results show that the proposed compression scheme for the attributes of voxelized 3D point clouds is able to achieve better rate-distortion performance and visual quality, compared with state-of-the-art methods.
Journal ArticleDOI
Semi-Supervised Non-Negative Matrix Factorization With Dissimilarity and Similarity Regularization
TL;DR: The proposed semi-supervised non-negative matrix factorization model is capable of generating discriminable low-dimensional representations to improve clustering performance and theoretically proves that the proposed algorithm can converge to a limiting point that meets the Karush–Kuhn–Tucker conditions.
Proceedings ArticleDOI
Integrating spectral and spatial information into deep convolutional Neural Networks for hyperspectral classification
TL;DR: This paper proposes a novel five-layer CNN for hyperspectral classification by encountering recent achievement in deep learning area, such as batch normalization, dropout, Parametric Rectified Linear Unit (PReLu) activation function.