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
Screen Content Video Quality Assessment: Subjective and Objective Study
TL;DR: The first large-scale video quality assessment (VQA) database specifically for the screen content videos (SCVs) is constructed and the proposed spatiotemporal Gabor feature tensor-based model (SGFTM) consistently outperforms multiple classical and state-of-the-art image/video quality assessment models.
Proceedings ArticleDOI
Light Field Super-resolution via Attention-Guided Fusion of Hybrid Lenses
TL;DR: This paper proposes a novel end-to-end learning-based approach, which can comprehensively utilize the specific characteristics of the input from two complementary and parallel perspectives to reconstructing high-resolution light field images from hybrid lenses.
Journal ArticleDOI
Spectral Variation Alleviation by Low-Rank Matrix Approximation for Hyperspectral Image Analysis
TL;DR: 11-based low-rank matrix approximation is proposed to alleviate spectral variation for hyperspectral image analysis, and the performance of classification, and spectral unmixing can be clearly improved by the proposed approach.
Journal ArticleDOI
An Ensemble Rate Adaptation Framework for Dynamic Adaptive Streaming Over HTTP
TL;DR: In this paper, an ensemble rate adaptation framework for dynamic adaptive streaming over HTTP (DASH) is proposed, which aims to leverage the advantages of multiple rate adaptation methods involved in the framework to improve the quality of experience (QoE ) of users.
Proceedings ArticleDOI
Human motion capture data recovery via trajectory-based sparse representation
TL;DR: This paper proposes a new method to recover corrupted motion capture data through trajectory-based sparse representation, which achieves much better performance, especially when significant portions of data is missing, than the existing algorithms.