Results 1 - 10 of 2,484

Spatio-Temporal Modeling of Grasping Actions

by Javier Romero, Thomas Feix, Hedvig Kjellström, Danica Kragic
"... Abstract — Understanding the spatial dimensionality and temporal context of human hand actions can provide representations for programming grasping actions in robots and inspire design of new robotic and prosthetic hands. The natural representation of human hand motion has high dimensionality. For s ..."
Abstract - Cited by 9 (3 self) - Add to MetaCart
. For specific activities such as handling and grasping of objects, the commonly observed hand motions lie on a lower-dimensional non-linear manifold in hand posture space. Although full body human motion is well studied within Computer Vision and Biomechanics, there is very little work on the analysis of hand

Contracting auto-encoders: Explicit invariance during feature extraction

by Salah Rifai, Pascal Vincent, Xavier Muller, Xavier Glorot, Yoshua Bengio - In Proceedings of the Twenty-eight International Conference on Machine Learning (ICML’11 , 2011
"... We present in this paper a novel approach for training deterministic auto-encoders. We show that by adding a well chosen penalty term to the classical reconstruction cost function, we can achieve results that equal or surpass those attained by other regularized autoencoders as well as denoising auto ..."
Abstract - Cited by 77 (12 self) - Add to MetaCart
directions of variation dictated by the data, corresponding to a lower-dimensional non-linear manifold, while being more invariant to the vast majority of directions orthogonal to the manifold. Finally, we show that by using the learned features to initialize a MLP, we achieve state of the art classification

Learning invariant features through local space contraction

by Salah Rifai, Xavier Muller, Xavier Glorot, Yoshua Bengio, Pascal Vincent , 2011
"... We present in this paper a novel approach for training deterministic auto-encoders. We show that by adding a well chosen penalty term to the classical reconstruction cost function, we can achieve results that equal or surpass those attained by other regularized auto-encoders as well as denoising aut ..."
Abstract - Cited by 2 (1 self) - Add to MetaCart
directions of variation dictated by the data, corresponding to a lower-dimensional non-linear manifold, while being more invariant to the vast majority of directions orthogonal to the manifold. Finally, we show that by using the learned features to initialize a MLP, we achieve state of the art classification

Explicit Invariance During Feature Extraction

by Contractive Auto-encoders
"... We present in this paper a novel approach for training deterministic auto-encoders. We show that by adding a well chosen penalty term to the classical reconstruction cost func-tion, we can achieve results that equal or sur-pass those attained by other regularized auto-encoders as well as denoising a ..."
Abstract - Add to MetaCart
directions of varia-tion dictated by the data, corresponding to a lower-dimensional non-linear manifold, while being more invariant to the vast majority of directions orthogonal to the manifold. Fi-nally, we show that by using the learned fea-tures to initialize a MLP, we achieve state of the art

The geometry of algorithms with orthogonality constraints

by Alan Edelman, Tomás A. Arias, Steven T. Smith - SIAM J. MATRIX ANAL. APPL , 1998
"... In this paper we develop new Newton and conjugate gradient algorithms on the Grassmann and Stiefel manifolds. These manifolds represent the constraints that arise in such areas as the symmetric eigenvalue problem, nonlinear eigenvalue problems, electronic structures computations, and signal proces ..."
Abstract - Cited by 640 (1 self) - Add to MetaCart
In this paper we develop new Newton and conjugate gradient algorithms on the Grassmann and Stiefel manifolds. These manifolds represent the constraints that arise in such areas as the symmetric eigenvalue problem, nonlinear eigenvalue problems, electronic structures computations, and signal

Identifying Objects from Hand Configurations during In-hand Exploration

by Diego R. Faria, Jorge Lobo, Jorge Dias
"... Abstract — In this work we use hand configuration and contact points during in-hand object exploration to identify the manipulated objects. Different contact points associated to an object shape can be represented in a latent space and lie on a lower dimensional non-linear manifold in the contact po ..."
Abstract - Add to MetaCart
Abstract — In this work we use hand configuration and contact points during in-hand object exploration to identify the manipulated objects. Different contact points associated to an object shape can be represented in a latent space and lie on a lower dimensional non-linear manifold in the contact

Locality Preserving Projection,"

by Xiaofei He , Partha Niyogi - Neural Information Processing System, , 2004
"... Abstract Many problems in information processing involve some form of dimensionality reduction. In this paper, we introduce Locality Preserving Projections (LPP). These are linear projective maps that arise by solving a variational problem that optimally preserves the neighborhood structure of the ..."
Abstract - Cited by 414 (16 self) - Add to MetaCart
of the data set. LPP should be seen as an alternative to Principal Component Analysis (PCA) -a classical linear technique that projects the data along the directions of maximal variance. When the high dimensional data lies on a low dimensional manifold embedded in the ambient space, the Locality Preserving

A Data-Driven Reflectance Model

by Wojciech Matusik , Hanspeter Pfister, Matt Brand, Leonard McMillan - ACM TRANSACTIONS ON GRAPHICS , 2003
"... We present a generative model for isotropic bidirectional reflectance distribution functions (BRDFs) based on acquired reflectance data. Instead of using analytical reflectance models, we represent each BRDF as a dense set of measurements. This allows us to interpolate and extrapolate in the space o ..."
Abstract - Cited by 210 (7 self) - Add to MetaCart
of acquired BRDFs to create new BRDFs. We treat each acquired BRDF as a single high-dimensional vector taken from a space of all possible BRDFs. We apply both linear (subspace) and non-linear (manifold) dimensionality reduction tools in an effort to discover a lowerdimensional representation

Learning non-linear image manifolds by global alignment of local linear models

by Jakob Verbeek , 2005
"... Appearance based methods, based on statistical models of the pixels values in an image (region) rather than geometrical object models, are increasingly popular in computer vision. In many applications the number of degrees of freedom (DOF) in the image generating process is much lower than the numb ..."
Abstract - Cited by 15 (0 self) - Add to MetaCart
from such manifolds and (ii) recover global parameterizations of the manifold. A globally non-linear probabilistic two-way mapping between coordinates on the manifold and images is obtained by combining several, locally valid, linear mappings. We propose a parameter estimation scheme that improves upon

On Beamforming with Finite Rate Feedback in Multiple Antenna Systems

by Krishna Kiran Mukkavilli, Ashutosh Sabharwal, Elza Erkip, Behnaam Aazhang , 2003
"... In this paper, we study a multiple antenna system where the transmitter is equipped with quantized information about instantaneous channel realizations. Assuming that the transmitter uses the quantized information for beamforming, we derive a universal lower bound on the outage probability for any f ..."
Abstract - Cited by 272 (14 self) - Add to MetaCart
between any two beamforming vectors in the beamformer codebook, and is equivalent to the problem of designing unitary space time codes under certain conditions. Finally, we show that good beamformers are good packings of 2-dimensional subspaces in a 2t-dimensional real Grassmannian manifold with chordal
Results 1 - 10 of 2,484