• Publications
  • Influence
Intrinsic colorization
TLDR
In this paper, we present an example-based colorization technique robust to illumination differences between grayscale target and color reference images, and obtain the final result with excellent color consistency. Expand
  • 93
  • 8
  • PDF
The Rhombic Dodecahedron Map: An Efficient Scheme for Encoding Panoramic Video
TLDR
Omnidirectional videos are usually mapped to planar domain for encoding with off-the-shelf video compression standards. Expand
  • 65
  • 7
  • PDF
Convergence Analyses on On-Line Weight Noise Injection-Based Training Algorithms for MLPs
TLDR
Injecting weight noise during training is a simple technique that has been proposed for almost two decades. Expand
  • 22
  • 4
  • PDF
Waveform Design With Unit Modulus and Spectral Shape Constraints via Lagrange Programming Neural Network
TLDR
We solve the waveform design problem as a nonlinear constrained optimization problem by introducing auxiliary variable neurons and Lagrange neurons and solve it using the Lagrange programming neural network. Expand
  • 48
  • 3
PSO-based K-Means clustering with enhanced cluster matching for gene expression data
TLDR
An integration of particle swarm optimization (PSO) and K-Means clustering algorithm is becoming one of the popular strategies for solving clustering problem. Expand
  • 30
  • 3
On-Line Node Fault Injection Training Algorithm for MLP Networks: Objective Function and Convergence Analysis
TLDR
This paper presents the objective function and the convergence proof of the on-line node fault injection-based algorithm, in which hidden nodes randomly output zeros during training. Expand
  • 12
  • 3
All-Frequency Lighting with Multiscale Spherical Radial Basis Functions
TLDR
We propose a multiscale and hierarchical structure of spherical radial basis functions (SRBFs) with basis functions uniformly distributed over the sphere. Expand
  • 11
  • 3
Discrete Wavelet Transform on Consumer-Level Graphics Hardware
TLDR
This paper presents a SIMD algorithm that performs the convolution-based DWT completely on a GPU, which brings us significant performance gain on a normal PC. Expand
  • 104
  • 2
  • PDF
A pruning method for the recursive least squared algorithm
TLDR
This paper elucidates how generalization ability can be improved by selecting an appropriate initial value of the error covariance matrix in the recursive least squared algorithm in the RLS algorithm. Expand
  • 57
  • 2
Convergence and Objective Functions of Some Fault/Noise-Injection-Based Online Learning Algorithms for RBF Networks
TLDR
This paper studies six common fault/noise-injection-based online learning algorithms for radial basis function (RBF) networks, namely 1) injecting additive input noise, injecting additive/multiplicative weight noise, 3) injecting multiplicative node noise, 4) injecting multiweight fault (random disconnection of weights), 5) injecting multinode fault, and 6) weight decay. Expand
  • 47
  • 2
  • PDF