Results 51 to 60 of about 2,604 (146)

Tensor Decomposition Through Neural Architectures

Applied Sciences
Machine learning (ML) technologies are currently widely used in many domains of science and technology, to discover models that transform input data into output data.
Chady Ghnatios, Francisco Chinesta
doaj   +1 more source

Enhancing generalized spectral clustering with embedding Laplacian graph regularization

CAAI Transactions on Intelligence Technology, EarlyView.
Abstract An enhanced generalised spectral clustering framework that addresses the limitations of existing methods by incorporating the Laplacian graph and group effect into a regularisation term is presented. By doing so, the framework significantly enhances discrimination power and proves highly effective in handling noisy data.
Hengmin Zhang, Jian Yang, Bob Zhang, Yang Tang, Wenli Du, Bihan Wen   +5 more
wiley   +1 more source

The effect of the total small vessel disease burden on the structural brain network

Scientific Reports, 2018
Different cerebral small vessel disease (SVD) lesion types have been shown to disrupt structural brain network individually. Considering that they often coexist, we investigated the relation between their collective effect using the recently proposed ...
Xiaopei Xu, Kui Kai Lau, Yuen Kwun Wong, Henry K. F. Mak, Edward S. Hui   +4 more
doaj   +1 more source

Robust Tensor Factorization for Color Image and Grayscale Video Recovery

IEEE Access, 2020
Low-rank tensor completion (LRTC) plays an important role in many fields, such as machine learning, computer vision, image processing, and mathematical theory.
Shiqiang Du, Yuqing Shi, Wenjin Hu, Weilan Wang, Jing Lian   +4 more
doaj   +1 more source

TT4D: Tensor‐Train‐based 4D Time‐Dependent Volume Rendering

Computer Graphics Forum, EarlyView.
Abstract Visualizing large‐scale, time‐varying volumetric data using direct volume rendering remains a significant challenge in scientific visualization, particularly as data sizes and resolutions continue to increase. One promising direction for addressing this challenge is the use of tensor decompositions, which have proven to be a useful tool for ...
Clara Hartmann, Rafael Ballester‐Ripoll, Renato Pajarola   +2 more
wiley   +1 more source

Efficient Techniques for Low-Rank Tensor Approximation and Applications in Robust Object Detection

Technologies
This paper introduces efficient randomized fixed-precision and single-pass algorithms for low-tubal-rank approximation of third-order tensors. The proposed fixed-precision algorithms are faster and more efficient than the existing algorithms for ...
Salman Ahmadi-Asl, Naeim Rezaeian, Cesar F. Caiafa, André L. F. de Almeida   +3 more
doaj   +1 more source

Application of Diffusion Tensor Imaging Parameters to Detect Change in Longitudinal Studies in Cerebral Small Vessel Disease. [PDF]

PLoS ONE, 2016
Cerebral small vessel disease (SVD) is the major cause of vascular cognitive impairment, resulting in significant disability and reduced quality of life.
Eva Anna Zeestraten, Philip Benjamin, Christian Lambert, Andrew John Lawrence, Owen Alan Williams, Robin Guy Morris, Thomas Richard Barrick, Hugh Stephen Markus   +7 more
doaj   +1 more source

As‐Rigid‐As‐Possible Regularization for Implicit Surfaces

Computer Graphics Forum, EarlyView.
Abstract Implicit surface representations have regained popularity because of their use in machine learning. A common component in optimization is regularization, penalizing the deviation of the surface from its original shape. The popular as‐rigid‐as‐possible (Arap) energy strikes a good compromise between realistic deformation behavior and efficient ...
T. Djuren, M. Worchel, U. Finnendahl, M. Alexa   +3 more
wiley   +1 more source

Topological approaches to quantum tensor train compression via ZX-calculus and SVD

Scientific Reports
The rapid advancement of quantum-inspired classical algorithms, particularly Quantics Tensor Trains (QTT), has demonstrated that exponentially large vectors can be manipulated efficiently via Matrix Product States (MPS).
Luis Gerardo Ayala Bertel, Srinjoy Ganguly   +1 more
doaj   +1 more source

On Bending in the As‐Rigid‐As‐Possible Deformation Energy

Computer Graphics Forum, EarlyView.
Abstract The well‐established As‐Rigid‐As‐Possible (ARAP) energy has various forms. For surface deformation, commonly used energies contain an implicit bending penalty. We present a natural, continuous generalization that incorporates multiple ARAP versions with an implicit, user‐controllable bending penalty.
Ugo Finnendahl, Marc Alexa
wiley   +1 more source