Wasserstein dictionary learning: Optimal transport-based unsupervised nonlinear dictionary learning

MA Schmitz, M Heitz, N Bonneel, F Ngole… - SIAM Journal on Imaging …, 2018‏ - SIAM
This paper introduces a new nonlinear dictionary learning method for histograms in the
probability simplex. The method leverages optimal transport theory, in the sense that our aim …

Dynamic texture recognition using volume local binary count patterns with an application to 2D face spoofing detection

X Zhao, Y Lin, J Heikkilä - IEEE Transactions on Multimedia, 2017‏ - ieeexplore.ieee.org
In this paper, a local spatiotemporal descriptor, namely, the volume local binary count
(VLBC), is proposed for the representation and recognition of dynamic texture. This …

Deep convolutional network with locality and sparsity constraints for texture classification

X Bu, Y Wu, Z Gao, Y Jia - Pattern Recognition, 2019‏ - Elsevier
Recent studies have demonstrated advantages of the representations learned by
Convolutional Neural Networks (CNNs) in providing an appealing paradigm for visual …

Dynamic texture classification based on 3D ICA-learned filters and fisher vector encoding in big data environment

Z **ong, F Mo, X Zhao, F Xu, X Zhang, Y Wu - Journal of Signal …, 2022‏ - Springer
Many researchers focus on the local feature-based description of the dynamic texture,
because of its stability and low dimensionality. Among the existing dynamic texture …

A comprehensive taxonomy of dynamic texture representation

TT Nguyen, TP Nguyen - ACM Computing Surveys (CSUR), 2021‏ - dl.acm.org
Representing dynamic textures (DTs) plays an important role in many real implementations
in the computer vision community. Due to the turbulent and non-directional motions of DTs …

A new large scale dynamic texture dataset with application to convnet understanding

I Hadji, RP Wildes - Proceedings of the European …, 2018‏ - openaccess.thecvf.com
This paper introduces a new large scale dynamic texture dataset. The dataset is provided
with two complementary organizations, one based on dynamics independent of spatial …

Dynamic texture classification using unsupervised 3D filter learning and local binary encoding

X Zhao, Y Lin, L Liu, J Heikkilä… - IEEE Transactions on …, 2019‏ - ieeexplore.ieee.org
Local binary descriptors, such as local binary pattern (LBP) and its various variants, have
been studied extensively in texture and dynamic texture analysis due to their outstanding …

SMTCNN-A global spatio-temporal texture convolutional neural network for 3D dynamic texture recognition

L Wang, L Zhou, P Liang, K Wang, L Ge - Image and Vision Computing, 2024‏ - Elsevier
Dynamic textures (DT) are typically 3D videos of physical processes showing statistical
regularity but have indeterminate spatial and temporal extent. Existing DT recognition …

Robust non-linear matrix factorization for dictionary learning, denoising, and clustering

J Fan, C Yang, M Udell - IEEE Transactions on Signal …, 2021‏ - ieeexplore.ieee.org
Low dimensional nonlinear structure abounds in datasets across computer vision and
machine learning. Kernelized matrix factorization techniques have recently been proposed …

Momental directional patterns for dynamic texture recognition

TT Nguyen, TP Nguyen, F Bouchara… - Computer Vision and …, 2020‏ - Elsevier
Understanding the chaotic motions of dynamic textures (DTs) is a challenging problem of
video representation for different tasks in computer vision. This paper presents a new …