Search Results for author: Antonio Ortega

Found 67 papers, 16 papers with code

Full reference point cloud quality assessment using support vector regression

1 code implementation15 Jun 2024 Ryosuke Watanabe, Shashank N. Sridhara, Haoran Hong, Eduardo Pavez, Keisuke Nonaka, Tatsuya Kobayashi, Antonio Ortega

Thus, establishing reliable point cloud quality assessment (PCQA) methods is essential as a benchmark to develop efficient compression methods.

Point Cloud Quality Assessment regression

Adaptive Online Learning of Separable Path Graph Transforms for Intra-prediction

no code implementations26 Feb 2024 Wen-Yang Lu, Eduardo Pavez, Antonio Ortega, Xin Zhao, Shan Liu

Current video coding standards, including H. 264/AVC, HEVC, and VVC, employ discrete cosine transform (DCT), discrete sine transform (DST), and secondary to Karhunen-Loeve transforms (KLTs) decorrelate the intra-prediction residuals.

Lossy Compression of Adjacency Matrices by Graph Filter Banks

no code implementations5 Feb 2024 Kenta Yanagiya, Junya Hara, Hiroshi Higashi, Yuichi Tanaka, Antonio Ortega

In this paper, we propose a lossy compression of weighted adjacency matrices, where the binary adjacency information is encoded losslessly (so the topological information of the graph is preserved) while the edge weights are compressed lossily.

Fast graph-based denoising for point cloud color information

no code implementations18 Jan 2024 Ryosuke Watanabe, Keisuke Nonaka, Eduardo Pavez, Tatsuya Kobayashi, Antonio Ortega

Second, we propose a fast noise level estimation method using eigenvalues of the covariance matrix on a graph.

Denoising graph construction

Optimizing $k$ in $k$NN Graphs with Graph Learning Perspective

no code implementations16 Jan 2024 Asuka Tamaru, Junya Hara, Hiroshi Higashi, Yuichi Tanaka, Antonio Ortega

$k$NN is one of the most popular approaches and is widely used in machine learning and signal processing.

Denoising graph construction +1

Frequency analysis and filter design for directed graphs with polar decomposition

1 code implementation18 Dec 2023 Semin Kwak, Laura Shimabukuro, Antonio Ortega

This approach provides a novel interpretation in the node domain and reveals aspects of graph signals that may be overlooked with a singular measure of variation.

Irregularity-Aware Bandlimited Approximation for Graph Signal Interpolation

no code implementations14 Dec 2023 Darukeesan Pakiyarajah, Eduardo Pavez, Antonio Ortega

In most work to date, graph signal sampling and reconstruction algorithms are intrinsically tied to graph properties, assuming bandlimitedness and optimal sampling set choices.

Towards a geometric understanding of Spatio Temporal Graph Convolution Networks

1 code implementation12 Dec 2023 Pratyusha Das, Sarath Shekkizhar, Antonio Ortega

In this paper, we first propose to use a local Dataset Graph (DS-Graph) obtained from the feature representation of input data at each layer to develop an understanding of the layer-wise embedding geometry of the STGCN.

Action Recognition Dynamic Time Warping +2

The faces of Convolution: from the Fourier theory to algebraic signal processing

no code implementations16 Jul 2023 Feng Ji, Wee Peng Tay, Antonio Ortega

In this expository article, we provide a self-contained overview of the notion of convolution embedded in different theories: from the classical Fourier theory to the theory of algebraic signal processing.

Signal Variation Metrics and Graph Fourier Transforms for Directed Graphs

no code implementations10 Apr 2023 Laura Shimabukuro, Antonio Ortega

In this paper we consider the problem of constructing graph Fourier transforms (GFTs) for directed graphs (digraphs), with a focus on developing multiple GFT designs that can capture different types of variation over the digraph node-domain.

Graph Signal Processing: History, Development, Impact, and Outlook

no code implementations21 Mar 2023 Geert Leus, Antonio G. Marques, José M. F. Moura, Antonio Ortega, David I Shuman

Graph signal processing (GSP) generalizes signal processing (SP) tasks to signals living on non-Euclidean domains whose structure can be captured by a weighted graph.

Graph Learning

Joint Graph and Vertex Importance Learning

no code implementations15 Mar 2023 Benjamin Girault, Eduardo Pavez, Antonio Ortega

In this paper, we explore the topic of graph learning from the perspective of the Irregularity-Aware Graph Fourier Transform, with the goal of learning the graph signal space inner product to better model data.

Graph Learning

Towards bandwidth estimation for graph signal reconstruction

no code implementations12 Mar 2023 Ajinkya Jayawant, Antonio Ortega

In numerous graph signal processing applications, data is often missing for a variety of reasons, and predicting the missing data is essential.

Rate-Distortion Optimization With Alternative References For UGC Video Compression

no code implementations11 Mar 2023 Xin Xiong, Eduardo Pavez, Antonio Ortega, Balu Adsumilli

We proposed a geometric criterion for saturation detection that works with rate-distortion optimization, and only requires a few frames from the UGC video.

Video Compression

Image Coding via Perceptually Inspired Graph Learning

no code implementations3 Mar 2023 Samuel Fernández-Menduiña, Eduardo Pavez, Antonio Ortega

Most codec designs rely on the mean squared error (MSE) as a fidelity metric in rate-distortion optimization, which allows to choose the optimal parameters in the transform domain but may fail to reflect perceptual quality.

Graph Learning MS-SSIM +1

Study of Manifold Geometry using Multiscale Non-Negative Kernel Graphs

no code implementations31 Oct 2022 Carlos Hurtado, Sarath Shekkizhar, Javier Ruiz-Hidalgo, Antonio Ortega

Modern machine learning systems are increasingly trained on large amounts of data embedded in high-dimensional spaces.

graph construction regression

Motion estimation and filtered prediction for dynamic point cloud attribute compression

no code implementations15 Oct 2022 Haoran Hong, Eduardo Pavez, Antonio Ortega, Ryosuke Watanabe, Keisuke Nonaka

The scheme includes integer-precision motion estimation and an adaptive graph based in-loop filtering scheme for improved attribute prediction.

Attribute Motion Estimation

The Geometry of Self-supervised Learning Models and its Impact on Transfer Learning

no code implementations18 Sep 2022 Romain Cosentino, Sarath Shekkizhar, Mahdi Soltanolkotabi, Salman Avestimehr, Antonio Ortega

Self-supervised learning (SSL) has emerged as a desirable paradigm in computer vision due to the inability of supervised models to learn representations that can generalize in domains with limited labels.

Data Augmentation Self-Supervised Learning +1

Toward a Geometrical Understanding of Self-supervised Contrastive Learning

no code implementations13 May 2022 Romain Cosentino, Anirvan Sengupta, Salman Avestimehr, Mahdi Soltanolkotabi, Antonio Ortega, Ted Willke, Mariano Tepper

When used for transfer learning, the projector is discarded since empirical results show that its representation generalizes more poorly than the encoder's.

Contrastive Learning Data Augmentation +2

Compression of user generated content using denoised references

no code implementations7 Mar 2022 Eduardo Pavez, Enrique Perez, Xin Xiong, Antonio Ortega, Balu Adsumilli

UGC video is uploaded by users, and then it is re-encoded to be made available at various levels of quality.

Denoising

Two Channel Filter Banks on Arbitrary Graphs with Positive Semi Definite Variation Operators

no code implementations6 Mar 2022 Eduardo Pavez, Benjamin Girault, Antonio Ortega, Philip A. Chou

Our approach is based on novel graph Fourier transforms (GFTs) given by the generalized eigenvectors of the variation operator.

Hybrid Model-based / Data-driven Graph Transform for Image Coding

no code implementations2 Mar 2022 Saghar Bagheri, Tam Thuc Do, Gene Cheung, Antonio Ortega

Transform coding to sparsify signal representations remains crucial in an image compression pipeline.

Graph Learning Image Compression

Fractional Motion Estimation for Point Cloud Compression

no code implementations1 Feb 2022 Haoran Hong, Eduardo Pavez, Antonio Ortega, Ryosuke Watanabe, Keisuke Nonaka

Motivated by the success of fractional pixel motion in video coding, we explore the design of motion estimation with fractional-voxel resolution for compression of color attributes of dynamic 3D point clouds.

Motion Compensation Motion Estimation

Channel redundancy and overlap in convolutional neural networks with channel-wise NNK graphs

no code implementations18 Oct 2021 David Bonet, Antonio Ortega, Javier Ruiz-Hidalgo, Sarath Shekkizhar

Feature spaces in the deep layers of convolutional neural networks (CNNs) are often very high-dimensional and difficult to interpret.

NNK-Means: Data summarization using dictionary learning with non-negative kernel regression

no code implementations15 Oct 2021 Sarath Shekkizhar, Antonio Ortega

An increasing number of systems are being designed by gathering significant amounts of data and then optimizing the system parameters directly using the obtained data.

Data Summarization Dictionary Learning +1

Orthogonal Transforms for Signals on Directed Graphs

no code implementations15 Oct 2021 Julia Barrufet, Antonio Ortega

In this paper we consider the problem of defining transforms for signals on directed graphs, with a specific focus on defective graphs where the corresponding graph operator cannot be diagonalized.

Channel-Wise Early Stopping without a Validation Set via NNK Polytope Interpolation

1 code implementation27 Jul 2021 David Bonet, Antonio Ortega, Javier Ruiz-Hidalgo, Sarath Shekkizhar

Motivated by our observations, we use CW-DeepNNK to propose a novel early stopping criterion that (i) does not require a validation set, (ii) is based on a task performance metric, and (iii) allows stopping to be reached at different points for each channel.

Cylindrical coordinates for LiDAR point cloud compression

no code implementations21 Jun 2021 Shashank N. Sridhara, Eduardo Pavez, Antonio Ortega

We present an efficient voxelization method to encode the geometry and attributes of 3D point clouds obtained from autonomous vehicles.

Attribute Autonomous Vehicles

Multi-resolution intra-predictive coding of 3D point cloud attributes

no code implementations16 Jun 2021 Eduardo Pavez, Andre L. Souto, Ricardo L. De Queiroz, Antonio Ortega

We propose an intra frame predictive strategy for compression of 3D point cloud attributes.

DCT and DST Filtering with Sparse Graph Operators

no code implementations22 Mar 2021 Keng-Shih Lu, Antonio Ortega, Debargha Mukherjee, Yue Chen

These sparse operators can be viewed as graph filters operating in the DCT domain, which allows us to approximate any DCT graph filter by a MPGF, leading to a design with more degrees of freedom than the conventional PGF approach.

Practical graph signal sampling with log-linear size scaling

1 code implementation21 Feb 2021 Ajinkya Jayawant, Antonio Ortega

Graph signal sampling is the problem of selecting a subset of representative graph vertices whose values can be used to interpolate missing values on the remaining graph vertices.

Pre-demosaic Graph-based Light Field Image Compression

no code implementations15 Feb 2021 Yung-Hsuan Chao, Haoran Hong, Gene Cheung, Antonio Ortega

Using a conventional Bayer pattern, data captured at each pixel is a single color component (R, G or B). The sensed data then undergoes demosaicking (interpolation of RGB components per pixel) and conversion to an array of sub-aperture images (SAIs).

Demosaicking Graph Learning +1

Spatio-Temporal Graph Scattering Transform

no code implementations ICLR 2021 Chao Pan, Siheng Chen, Antonio Ortega

Although spatio-temporal graph neural networks have achieved great empirical success in handling multiple correlated time series, they may be impractical in some real-world scenarios due to a lack of sufficient high-quality training data.

Time Series Time Series Analysis

Representing Deep Neural Networks Latent Space Geometries with Graphs

no code implementations14 Nov 2020 Carlos Lassance, Vincent Gripon, Antonio Ortega

However, when processing a batch of inputs concurrently, the corresponding set of intermediate representations exhibit relations (what we call a geometry) on which desired properties can be sought.

Learning Sparse Graph Laplacian with K Eigenvector Prior via Iterative GLASSO and Projection

no code implementations25 Oct 2020 Saghar Bagheri, Gene Cheung, Antonio Ortega, Fen Wang

Learning a suitable graph is an important precursor to many graph signal processing (GSP) pipelines, such as graph spectral signal compression and denoising.

Denoising Graph Learning

DeepNNK: Explaining deep models and their generalization using polytope interpolation

1 code implementation20 Jul 2020 Sarath Shekkizhar, Antonio Ortega

Modern machine learning systems based on neural networks have shown great success in learning complex data patterns while being able to make good predictions on unseen data points.

BIG-bench Machine Learning Interpretability Techniques for Deep Learning +2

Sampling Signals on Graphs: From Theory to Applications

no code implementations9 Mar 2020 Yuichi Tanaka, Yonina C. Eldar, Antonio Ortega, Gene Cheung

In this article, we review current progress on sampling over graphs focusing on theory and potential applications.

Region adaptive graph fourier transform for 3d point clouds

1 code implementation4 Mar 2020 Eduardo Pavez, Benjamin Girault, Antonio Ortega, Philip A. Chou

Since clusters may have a different numbers of points, each block transform must incorporate the relative importance of each coefficient.

Efficient graph construction for image representation

1 code implementation16 Feb 2020 Sarath Shekkizhar, Antonio Ortega

Graphs are useful to interpret widely used image processing methods, e. g., bilateral filtering, or to develop new ones, e. g., kernel based techniques.

Denoising graph construction

Time-Varying Graph Learning with Constraints on Graph Temporal Variation

no code implementations10 Jan 2020 Koki Yamada, Yuichi Tanaka, Antonio Ortega

We propose a novel framework for learning time-varying graphs from spatiotemporal measurements.

Graph Learning

Deep geometric knowledge distillation with graphs

1 code implementation8 Nov 2019 Carlos Lassance, Myriam Bontonou, Ghouthi Boukli Hacene, Vincent Gripon, Jian Tang, Antonio Ortega

Specifically we introduce a graph-based RKD method, in which graphs are used to capture the geometry of latent spaces.

Knowledge Distillation

Neighborhood and Graph Constructions using Non-Negative Kernel Regression

3 code implementations21 Oct 2019 Sarath Shekkizhar, Antonio Ortega

Data-driven neighborhood definitions and graph constructions are often used in machine learning and signal processing applications.

graph construction Graph Learning +1

Structural Robustness for Deep Learning Architectures

no code implementations11 Sep 2019 Carlos Lassance, Vincent Gripon, Jian Tang, Antonio Ortega

Deep Networks have been shown to provide state-of-the-art performance in many machine learning challenges.

BIG-bench Machine Learning

Graph-based Transforms for Video Coding

no code implementations3 Sep 2019 Hilmi E. Egilmez, Yung-Hsuan Chao, Antonio Ortega

In many state-of-the-art compression systems, signal transformation is an integral part of the encoding and decoding process, where transforms provide compact representations for the signals of interest.

Video Compression

Laplacian Networks: Bounding Indicator Function Smoothness for Neural Network Robustness

no code implementations24 May 2018 Carlos Eduardo Rosar Kos Lassance, Vincent Gripon, Antonio Ortega

For the past few years, Deep Neural Network (DNN) robustness has become a question of paramount importance.

Active covariance estimation by random sub-sampling of variables

no code implementations4 Apr 2018 Eduardo Pavez, Antonio Ortega

We apply our analysis in an active learning framework, where the expected number of observed variables is small compared to the dimension of the vector of interest, and propose a design of optimal sub-sampling probabilities and an active covariance matrix estimation algorithm.

Active Learning

Graph Learning from Filtered Signals: Graph System and Diffusion Kernel Identification

1 code implementation7 Mar 2018 Hilmi E. Egilmez, Eduardo Pavez, Antonio Ortega

This paper introduces a novel graph signal processing framework for building graph-based models from classes of filtered signals.

Graph Learning valid

Graph Signal Processing: Overview, Challenges and Applications

2 code implementations1 Dec 2017 Antonio Ortega, Pascal Frossard, Jelena Kovačević, José M. F. Moura, Pierre Vandergheynst

Research in Graph Signal Processing (GSP) aims to develop tools for processing data defined on irregular graph domains.

Signal Processing

Learning Graphs with Monotone Topology Properties and Multiple Connected Components

1 code implementation31 May 2017 Eduardo Pavez, Hilmi E. Egilmez, Antonio Ortega

Then, a graph weight estimation (GWE) step is performed by solving a generalized graph Laplacian estimation problem, where edges are constrained by the topology found in the GTI step.

A Sampling Theory Perspective of Graph-based Semi-supervised Learning

no code implementations26 May 2017 Aamir Anis, Aly El Gamal, Salman Avestimehr, Antonio Ortega

In this work, we reinforce this connection by viewing the problem from a graph sampling theoretic perspective, where class indicator functions are treated as bandlimited graph signals (in the eigenvector basis of the graph Laplacian) and label prediction as a bandlimited reconstruction problem.

Graph Sampling

Graph-Based Manifold Frequency Analysis for Denoising

no code implementations29 Nov 2016 Shay Deutsch, Antonio Ortega, Gerard Medioni

We propose a new framework for manifold denoising based on processing in the graph Fourier frequency domain, derived from the spectral decomposition of the discrete graph Laplacian.

Denoising

Graph Learning from Data under Structural and Laplacian Constraints

2 code implementations16 Nov 2016 Hilmi E. Egilmez, Eduardo Pavez, Antonio Ortega

For the proposed graph learning problems, specialized algorithms are developed by incorporating the graph Laplacian and structural constraints.

Computational Efficiency Graph Learning

Active Learning On Weighted Graphs Using Adaptive And Non-adaptive Approaches

no code implementations18 May 2016 Eyal En Gad, Akshay Gadde, A. Salman Avestimehr, Antonio Ortega

A new sampling algorithm is proposed, which sequentially selects the graph nodes to be sampled, based on an aggressive search for the boundary of the signal over the graph.

Active Learning

Active Learning for Community Detection in Stochastic Block Models

no code implementations8 May 2016 Akshay Gadde, Eyal En Gad, Salman Avestimehr, Antonio Ortega

Our main result is to show that, under certain conditions, sampling the labels of a vanishingly small fraction of nodes (a number sub-linear in $n$) is sufficient for exact community detection even when $D(a, b)<1$.

Active Learning Benchmarking +3

Asymptotic Justification of Bandlimited Interpolation of Graph signals for Semi-Supervised Learning

no code implementations14 Feb 2015 Aamir Anis, Aly El Gamal, A. Salman Avestimehr, Antonio Ortega

Graph-based methods play an important role in unsupervised and semi-supervised learning tasks by taking into account the underlying geometry of the data set.

Active Semi-Supervised Learning Using Sampling Theory for Graph Signals

1 code implementation16 May 2014 Akshay Gadde, Aamir Anis, Antonio Ortega

The sampling theory for graph signals aims to extend the traditional Nyquist-Shannon sampling theory by allowing us to identify the class of graph signals that can be reconstructed from their values on a subset of vertices.

Active Learning

Localized Iterative Methods for Interpolation in Graph Structured Data

no code implementations9 Oct 2013 Sunil K. Narang, Akshay Gadde, Eduard Sanou, Antonio Ortega

In this paper, we present two localized graph filtering based methods for interpolating graph signals defined on the vertices of arbitrary graphs from only a partial set of samples.

The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains

1 code implementation31 Oct 2012 David I Shuman, Sunil K. Narang, Pascal Frossard, Antonio Ortega, Pierre Vandergheynst

In applications such as social, energy, transportation, sensor, and neuronal networks, high-dimensional data naturally reside on the vertices of weighted graphs.

Translation

Cannot find the paper you are looking for? You can Submit a new open access paper.