Results 11  20
of
354
Geometric Algorithms for Transposition Invariant ContentBased Music Retrieval£
"... We represent music as sets of points or sets of horizontal line segments in the Euclidean plane. Via this geometric representation we cast transposition invariant contentbased music retrieval problems as ones of matching sets of points or sets of horizontal line segments in plane under translations ..."
Abstract
 Add to MetaCart
We represent music as sets of points or sets of horizontal line segments in the Euclidean plane. Via this geometric representation we cast transposition invariant contentbased music retrieval problems as ones of matching sets of points or sets of horizontal line segments in plane under
Constructing models for contentbased image retrieval
 In Proc. CVPR
, 2001
"... This paper presents a new method for constructing models from a set of positive and negative sample images; the method requires no manual extraction of significant objects or features. Our model representation is based on two layers. The first one consists of “generic ” descriptors which represent s ..."
Abstract

Cited by 133 (12 self)
 Add to MetaCart
is multimodal and is represented by a set of “spatialfrequency ” clusters. It adds a statistical spatial constraint which is rotationally invariant. Our twolayer representation is novel; it allows to efficiently capture “texturelike ” visual structure. The selection of distinctive structure determines
Discrete Representation of Signals
 Proc. IEEE
, 1972
"... Abstructh proceaaing continuou&ime signals by digitalmeans, it is necessary to represent the signal by a digital sequence. There are many ways other than periodic sampling for obtaining such a sequence. The requirements for such representations and some examples are discussed within the framew ..."
Abstract

Cited by 57 (0 self)
 Add to MetaCart
the framework of simulating linear timeinvariant systems. The representation of digital sequences by other digital sequences is also discussed, with particular emphasis on the use of such representations to implement a nonlinear warping of the digital frequency axis. Some applications and hardware imple
MDLBased TranslationInvariant Denoising And Robust TimeFrequency Representations
 Proc. of the 4th IEEESP Int. Symposium on TimeFrequency and TimeScale Analysis
, 1998
"... A lranslaiioninvariani den&sing reelhod, based on lhe Minimum Description Length (MDL) criierion and lhe ShiftInvariant Wavelet Packet Decomposition (SIWPD) is presenied. A colleciion of signal models is generaled using an exiended library of orihonormal vaveleipackei bases, and an addiiive c ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
robusi limefrequency representations, characierized by high resoluiion and suppressed inierferenceierms. The proposed reelhod is compared viih aliernaiive approaches, and ils superioriiy is demonsiraied. 1.
MdlBased TranslationInvariant Denoising And Robust TimeFrequency Representations
 Proc. of the 4th IEEESP Int. Symposium on TimeFrequency and TimeScale Analysis
, 1998
"... A translationinvariant denoising method, based on the Minimum Description Length (MDL) criterion and the ShiftInvariant Wavelet Packet Decomposition (SIWPD) is presented. A collection of signal models is generated using an extended library of orthonormal waveletpacket bases, and an additive cost ..."
Abstract
 Add to MetaCart
timefrequency representations, characterized by high resolution and suppressed interferenceterms. The proposed method is compared with alternative approaches, and its superiority is demonstrated. 1. INTRODUCTION The use of wavelet bases for estimating noisy signals has been the object
1 Invariant Scattering Convolution Networks
, 1203
"... Abstract—A wavelet scattering network computes a translation invariant image representation, which is stable to deformations and preserves high frequency information for classification. It cascades wavelet transform convolutions with nonlinear modulus and averaging operators. The first network laye ..."
Abstract

Cited by 44 (7 self)
 Add to MetaCart
Abstract—A wavelet scattering network computes a translation invariant image representation, which is stable to deformations and preserves high frequency information for classification. It cascades wavelet transform convolutions with nonlinear modulus and averaging operators. The first network
DERIVATIVE VARIATION PATTERN FOR ILLUMINATIONINVARIANT IMAGE REPRESENTATION
"... This paper presents a novel image descriptor called Derivative Variation Pattern (DVP) and its application to face and palmprint recognition. DVP captures image variations in both the frequency and the spatial domains. The effects of uncontrolled illumination are compensated in the frequency domain ..."
Abstract
 Add to MetaCart
This paper presents a novel image descriptor called Derivative Variation Pattern (DVP) and its application to face and palmprint recognition. DVP captures image variations in both the frequency and the spatial domains. The effects of uncontrolled illumination are compensated in the frequency
Quantum Gravity Momentum Representation and Maximum Invariant Energy
, 2004
"... We use the idea of the symmetry between the spacetime coordinates x µ and the energymomentum p µ in quantum theory to construct a momentum space quantum gravity geometry with a metric sµν and a curvature tensor P λ µνρ. For a closed maximally symmetric momentum space with a constant 3curvature, th ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
, the volume of the pspace admits a cutoff with an invariant maximum momentum a. A WheelerDeWitttype wave equation is obtained in the momentum space representation. The vacuum energy density and the selfenergy of a charged particle are shown to be finite, and modifications of the electromagnetic radiation
A Volumetric/Iconic Frequency Domain Representation for Objects with application for Pose Invariant Face Recognition
, 1998
"... A novel method for representing 3D objects that unifies viewer and model centered object representations is presented. A unified 3D frequencydomain representation (called Volumetric Frequency Representation  VFR) encapsulates both the spatial structure of the object and a continuum of its views ..."
Abstract

Cited by 13 (1 self)
 Add to MetaCart
in the same data structure. The frequencydomain image of an object viewed from any direction can be directly extracted employing an extension of the Projection Slice Theorem, where each Fouriertransformed view is a planar slice of the volumetric frequency representation. The VFR is employed for poseinvariant
SHARING THE COMPONENTS OF TRANSPOSITIONINVARIANT DISTANCE, DIT, ON DITORGANIZED BURKHARDKELLER STRUCTURE IN SEARCHES FOR BEST MATCHING STRINGS
"... In this work various construction character/frequency information sharing structure approaches are proposed in order to optimize transposition_invariant distance evaluation, [SD87], that distance is used to construct a Burkhardkeller tree, [BK73] and [NK82], where is organized a dictionary of strin ..."
Abstract
 Add to MetaCart
In this work various construction character/frequency information sharing structure approaches are proposed in order to optimize transposition_invariant distance evaluation, [SD87], that distance is used to construct a Burkhardkeller tree, [BK73] and [NK82], where is organized a dictionary
Results 11  20
of
354