This paper reports a new method for 3D shape classification. Given a 3D shape M, we first define a spectral function at every point on M that is a weighted summation of the geodesics from the point to a set of curvature-sensitive feature points on M. Based on this spectral field, a real-valued square matrix is defined that correlates the topology (the spectral field) with the geometry (the maxi...

Thanks to the success of 3D reconstruction algorithms and the development of online tools for computer-aided design (CAD) the number of publicly available 3D models has grown significantly in recent years, and will continue to do so. This thesis investigates representations of 3D models for 3D shape matching, instance-level 2D-3D alignment, and category-level 2D-3D recognition. The geometry of ...

The space target recognition algorithm, which is based on the time series of radar cross section (RCS), is proposed in this paper to solve the problems of space target recognition in the active radar system. In the algorithm, EMD method is applied for the first time to extract the eigen of RCS time series. The normalized instantaneous frequencies of high-frequency intrinsic mode functions obtai...

We show that the supersymmetric rational Calogero-Moser-Sutherland (CMS) model of AN+1-type is equivalent to a set of free super-oscillators, through a similarity transformation. We prescribe methods to construct the complete eigen-spectrum and the associated eigen-functions, both in supersymmetry preserving as well as supersymmetry breaking phases, from the free super-oscillator basis. Further...

We introduce Eigen Evolution Pooling, an efficient method to aggregate a sequence of feature vectors. Eigen evolution pooling is designed to produce compact feature representations for a sequence of feature vectors, while maximally preserving as much information about the sequence as possible, especially the temporal evolution of the features over time. Eigen evolution pooling is a general pool...