C
Chi-Sing Leung
Researcher at City University of Hong Kong
Publications - 159
Citations - 2574
Chi-Sing Leung is an academic researcher from City University of Hong Kong. The author has contributed to research in topics: Artificial neural network & Rendering (computer graphics). The author has an hindex of 28, co-authored 152 publications receiving 2371 citations. Previous affiliations of Chi-Sing Leung include The Chinese University of Hong Kong & Nanyang Technological University.
Papers
More filters
Journal ArticleDOI
Intrinsic colorization
TL;DR: This paper presents an example-based colorization technique robust to illumination differences between grayscale target and color reference images, and demonstrates via several examples that this method generates results with excellent color consistency.
Journal ArticleDOI
Hopf bifurcation and chaos in a single delayed neuron equation with non-monotonic activation function
TL;DR: In this article, a simple neural network model with discrete time delay is investigated, and the linear stability of this model is discussed by analyzing the associated characteristic transcendental equation, and it is found that Hopf bifurcation occurs when this influence varies and passes through a sequence of critical values.
Journal ArticleDOI
Discrete Wavelet Transform on Consumer-Level Graphics Hardware
TL;DR: A SIMD algorithm is presented that performs the convolution-based DWT completely on a GPU, which brings us significant performance gain on a normal PC without extra cost.
Journal ArticleDOI
The Rhombic Dodecahedron Map: An Efficient Scheme for Encoding Panoramic Video
TL;DR: This paper proposes a novel mapping scheme, known as the rhombic dodecahedron map (RD map) to represent data over the spherical domain, and shows that with its ultra-fast data indexing capability, it can playback omnidirectional videos with very high frame rates on conventional PCs with GPU support.
Journal ArticleDOI
On the Kalman filtering method in neural network training and pruning
TL;DR: In this paper, some cues on the setting of the initial condition will be presented with a simple example illustrated and an elegant equation linking the error sensitivity measure (the saliency) and the result obtained via extended Kalman filter is devised.