Search Results for author: Thierry Bouwmans

Found 17 papers, 7 papers with code

Time-varying Signals Recovery via Graph Neural Networks

no code implementations22 Feb 2023 Jhon A. Castro-Correa, Jhony H. Giraldo, Anindya Mondal, Mohsen Badiey, Thierry Bouwmans, Fragkiskos D. Malliaros

The recovery of time-varying graph signals is a fundamental problem with numerous applications in sensor networks and forecasting in time series.

Graph Learning Time Series +1

Higher-order Sparse Convolutions in Graph Neural Networks

no code implementations21 Feb 2023 Jhony H. Giraldo, Sajid Javed, Arif Mahmood, Fragkiskos D. Malliaros, Thierry Bouwmans

Graph Neural Networks (GNNs) have been applied to many problems in computer sciences.

On the Trade-off between Over-smoothing and Over-squashing in Deep Graph Neural Networks

1 code implementation5 Dec 2022 Jhony H. Giraldo, Konstantinos Skianis, Thierry Bouwmans, Fragkiskos D. Malliaros

Graph Neural Networks (GNNs) have succeeded in various computer science applications, yet deep GNNs underperform their shallow counterparts despite deep learning's success in other domains.

Representation Learning

Reconstruction of Time-varying Graph Signals via Sobolev Smoothness

1 code implementation13 Jul 2022 Jhony H. Giraldo, Arif Mahmood, Belmar Garcia-Garcia, Dorina Thanou, Thierry Bouwmans

In the current work, we assume that the temporal differences of graph signals are smooth, and we introduce a novel algorithm based on the extension of a Sobolev smoothness function for the reconstruction of time-varying graph signals from discrete samples.

Automated Mathematical Equation Structure Discovery for Visual Analysis

3 code implementations17 Apr 2021 Caroline Pacheco do Espírito Silva, José A. M. Felippe De Souza, Antoine Vacavant, Thierry Bouwmans, Andrews Cordolino Sobral

In this paper, we focus on recent AI advances to present a novel framework for automatically discovering equations from scratch with little human intervention to deal with the different challenges encountered in real-world scenarios.

On the Minimization of Sobolev Norms of Time-Varying Graph Signals: Estimation of New Coronavirus Disease 2019 Cases

1 code implementation1 Jul 2020 Jhony H. Giraldo, Thierry Bouwmans

To this end, we proposed a new method based on the minimization of the Sobolev norm in graph signal processing.

GraphBGS: Background Subtraction via Recovery of Graph Signals

no code implementations17 Jan 2020 Jhony H. Giraldo, Thierry Bouwmans

Several deep learning methods for background subtraction have been proposed in the literature with competitive performances.

Change Detection graph construction +3

Moving Objects Detection with a Moving Camera: A Comprehensive Review

2 code implementations15 Jan 2020 Marie-Neige Chapel, Thierry Bouwmans

During about 30 years, a lot of research teams have worked on the big challenge of detection of moving objects in various challenging environments.

Motion Compensation Motion Segmentation +1

Deep Neural Network Concepts for Background Subtraction: A Systematic Review and Comparative Evaluation

no code implementations13 Nov 2018 Thierry Bouwmans, Sajid Javed, Maryam Sultana, Soon Ki Jung

Currently, the top current background subtraction methods in CDnet 2014 are based on deep neural networks with a large gap of performance in comparison on the conventional unsupervised approaches based on multi-features or multi-cues strategies.

Video Background Subtraction

Robust Subspace Learning: Robust PCA, Robust Subspace Tracking, and Robust Subspace Recovery

no code implementations26 Nov 2017 Namrata Vaswani, Thierry Bouwmans, Sajid Javed, Praneeth Narayanamurthy

The problem of subspace learning or PCA in the presence of outliers is called robust subspace learning or robust PCA (RPCA).

Dimensionality Reduction

On the Role and the Importance of Features for Background Modeling and Foreground Detection

no code implementations28 Nov 2016 Thierry Bouwmans, Caroline Silva, Cristina Marghes, Mohammed Sami Zitouni, Harish Bhaskar, Carl Frelicot

Background modeling has emerged as a popular foreground detection technique for various applications in video surveillance.

Decomposition into Low-rank plus Additive Matrices for Background/Foreground Separation: A Review for a Comparative Evaluation with a Large-Scale Dataset

1 code implementation4 Nov 2015 Thierry Bouwmans, Andrews Sobral, Sajid Javed, Soon Ki Jung, El-Hadi Zahzah

In this context, this work aims to initiate a rigorous and comprehensive review of the similar problem formulations in robust subspace learning and tracking based on decomposition into low-rank plus additive matrices for testing and ranking existing algorithms for background/foreground separation.

Matrix Completion

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