Search Results

Symbolic Regression is sometimes treated as a multi-objective optimization problem where two objectives (Accuracy and Complexity) are optimized simultaneously. In this paper, we propose a novel approach, Hierarchical Multi-objective Symbolic Regression (...

Abstract: Traditional folk games are often rooted in time-honored local culture and customs. As intangible cultural heritages, many traditional folk games are of great significance to the study of national will and local customs and culture. With the ...

A pyramid residual convolutional neural network (PRCNN) is proposed to restore image with compression artifacts in this paper, and the method is enable to process multiple resolutions by fixing patch size extracted from whole image. Convolutional neural ...

In October 2015, the ScanPyramids (SP)¹ mission started looking for unknown structures inside Egyptian pyramids with non-invasive technologies. Possibly the most successful imaging technology was muography which is similar to X-ray radiography but with ...

We introduce a Bernstein--Bezier basis for the pyramid, whose restriction to the face reduces to the Bernstein--Bezier basis on the triangle or quadrilateral. The basis satisfies the standard positivity and partition of unity properties common to Bernstein ...

Discontinuous Galerkin (DG) methods discretized under the method of lines must handle the inverse of a block diagonal mass matrix at each time step. Efficient implementations of the DG method hinge upon inexpensive and low-memory techniques for the ...

Large Scale 3D Terrain Generation is a hot and difficult problem in many applications, such as Geographic Information System (GIS), Virtual Reality (VR) and 3D games. The key issues of 3D terrain Generation are how to store massive terrain data and how ...

The signed volume function for polyhedra can be generalized to a mean volume function for volume elements by averaging over the triangulations of the underlying polyhedron. If we consider these up to translation and scaling, the resulting quotient space is ...

Real-time 3D pose estimation from monocular image sequences is a challenging research topic. Although current methods are able to recover 3D pose, they are severely challenged by the computational cost. To address this problem, we propose a tracking and ...

For the problem of low detection accuracy and slow speed to fast motion object, when solving the basic optical flow constraint equation with the traditional algorithm, an improved optical flow algorithm based on LK optical flow algorithm has been put ...

Fernandes and Kanevsky proposed an important structure in interconnection network, WKR Pyramid Networks (WKP_{(d, t, L)}, for short), in 1993. They are constructed by taking difference size WK-recursive network as difference layers. That paper discussed ...

A particular group of neural network (NN) learning algorithms known as constructive algorithms (CoNN) congregates algorithms that dynamically combine two processes: (1) the definition of the NN architecture and (2) learning. Generally both processes ...

To efficiently extract local and global features in face description and recognition, a pyramid-based multi-scale LBP approach is proposed. Firstly, the face image pyramid is constructed through multi-scale analysis. Then the LBP operator is applied to ...

We study the problem of an electron confined in a semiconductor quantum dot shaped as a square-base pyramid, assuming specular reflection of a particle from quantum dot boundaries. The application of boundary condition equals the wave function in an ...

In this paper, we propose an example-based facial sketch hallucination approach. Given a face image, its sketch image will be automatically hallucinated by learning from a training set, which includes a lot of face images and their corresponding sketch ...

We propose a pyramid based representation together with a partial weighted similarity measure to address the partial occlusion problem in visual tracking. In current histogram based tracking methods, due to the lost of spatial information, occlusion ...

In this paper, we present a fast algorithm for medical image registration. Through utilizing steerable filters, we can extract multi-directional feature information of image steadily and then combine it to obtain synthesized feature graph for more ...

Improving the computational efficiency of image processing tasks has become a dominant issue with the ultimate goal of real-time processing. One solution to improve efficiency is the use of a hexagonal image representation and we present an approach to ...

Polynomial extensions play a vital role in the analysis of the $p$ and $h$-$p$ finite element method (FEM) and the spectral element method. We construct explicitly polynomial extensions on standard elements: cubes and triangular prisms, which together ...

A distinction is usually made between wavelet bases and wavelet frames. The former are associated with a one-to-one representation of signals, which is somewhat constrained but most efficient computationally. The latter are over-complete, but they offer ...