
Multifeature 360 Video Quality Estimation
We propose a new method for the visual quality assessment of 360degree ...
read it

A neural anisotropic view of underspecification in deep learning
The underspecification of most machine learning pipelines means that we ...
read it

Predicting traffic signals on transportation networks using spatiotemporal correlations on graphs
Forecasting multivariate time series is challenging as the variables are...
read it

Multilayer Graph Clustering with Optimized Node Embedding
We are interested in multilayer graph clustering, which aims at dividing...
read it

On the benefits of robust models in modulation recognition
Given the rapid changes in telecommunication systems and their higher de...
read it

Bioinspired Robustness: A Review
Deep convolutional neural networks (DCNNs) have revolutionized computer ...
read it

SelfSupervision by Prediction for Object Discovery in Videos
Despite their irresistible success, deep learning algorithms still heavi...
read it

Improving filling level classification with adversarial training
We investigate the problem of classifying  from a single image  the le...
read it

QUACKIE: A NLP Classification Task With Ground Truth Explanations
NLP Interpretability aims to increase trust in model predictions. This m...
read it

SentenceBased Model Agnostic NLP Interpretability
Today, interpretability of BlackBox Natural Language Processing (NLP) m...
read it

FiGLearn: Filter and Graph Learning using Optimal Transport
In many applications, a dataset can be considered as a set of observed s...
read it

Multilayer Clustered Graph Learning
Multilayer graphs are appealing mathematical tools for modeling multiple...
read it

Optimism in the Face of Adversity: Understanding and Improving Deep Learning through Adversarial Robustness
Driven by massive amounts of data and important advances in computationa...
read it

FAR: A General Framework for Attributional Robustness
Attribution maps have gained popularity as tools for explaining neural n...
read it

Modurec: Recommender Systems with Feature and Time Modulation
Current state of the art algorithms for recommender systems are mainly b...
read it

Graph signal processing for machine learning: A review and new perspectives
The effective representation, processing, analysis, and visualization of...
read it

node2coords: Graph Representation Learning with Wasserstein Barycenters
In order to perform network analysis tasks, representations that capture...
read it

Towards robust sensing for Autonomous Vehicles: An adversarial perspective
Autonomous Vehicles rely on accurate and robust sensor observations for ...
read it

Building powerful and equivariant graph neural networks with messagepassing
Messagepassing has proved to be an effective way to design graph neural...
read it

Graph Pooling with Node Proximity for Hierarchical Representation Learning
Graph neural networks have attracted wide attentions to enable represent...
read it

Neural Anisotropy Directions
In this work, we analyze the role of the network architecture in shaping...
read it

GeoDA: a geometric framework for blackbox adversarial attacks
Adversarial examples are known as carefully perturbed images fooling ima...
read it

Wassersteinbased Graph Alignment
We propose a novel method for comparing nonaligned graphs of different ...
read it

Hold me tight! Influence of discriminative features on deep network boundaries
Important insights towards the explainability of neural networks and the...
read it

Joint Graphbased Depth Refinement and Normal Estimation
Depth estimation is an essential component in understanding the 3D geome...
read it

Multiview shape estimation of transparent containers
The 3D localisation of an object and the estimation of its properties, s...
read it

On the choice of graph neural network architectures
Seminal works on graph neural networks have primarily targeted semisupe...
read it

Imperceptible Adversarial Attacks on Tabular Data
Security of machine learning models is a concern as they may face advers...
read it

Mask Combination of Multilayer Graphs for Global Structure Inference
Structure inference is an important task for network data processing and...
read it

CDOT: Continuous Domain Adaptation using Optimal Transport
In this work, we address the scenario in which the target domain is cont...
read it

iPool  Informationbased Pooling in Hierarchical Graph Neural Networks
With the advent of data science, the analysis of network or graph data h...
read it

GOT: An Optimal Transport framework for Graph comparison
We present a novel framework based on optimal transport for the challeng...
read it

A geometryinspired decisionbased attack
Deep neural networks have recently achieved tremendous success in image ...
read it

Graph heat mixture model learning
Graph inference methods have recently attracted a great interest from th...
read it

Visual Distortions in 360degree Videos
Omnidirectional (or 360degree) images and videos are emergent signals i...
read it

Stochastic Gradient Descent for Spectral Embedding with Implicit Orthogonality Constraint
In this paper, we propose a scalable algorithm for spectral embedding. T...
read it

Robustness via curvature regularization, and vice versa
Stateoftheart classifiers have been shown to be largely vulnerable to...
read it

Spherical clustering of users navigating 360^∘ content
In Virtual Reality (VR) applications, understanding how users explore th...
read it

Kernel Regression for Graph Signal Prediction in Presence of Sparse Noise
In presence of sparse noise we propose kernel regression for predicting ...
read it

SparseFool: a few pixels make a big difference
Deep Neural Networks have achieved extraordinary results on image classi...
read it

Supervised Linear Regression for Graph Learning from Graph Signals
We propose a supervised learning approach for predicting an underlying g...
read it

Multilayer Graph Signal Clustering
Multilayer graphs are commonly used to model relationships of different ...
read it

Graph Laplacian mixture model
Graph learning methods have recently been receiving increasing interest ...
read it

Isometric Transformation Invariant Graphbased Deep Neural Network
Learning transformation invariant representations of visual data is an i...
read it

Learning Graphs from Data: A Signal Representation Perspective
The construction of a meaningful graph topology plays a crucial role in ...
read it

The SumRateDistortion Region of Correlated GaussMarkov Sources
We derive the sumratedistortion region for a generic number of success...
read it

Adaptive Streaming in Interactive Multiview Video Systems
Multiview applications endow final users with the possibility to freely ...
read it

IRSA Transmission Optimization via Online Learning
In this work, we propose a new learning framework for optimising transmi...
read it

Graphbased Transform Coding with Application to Image Compression
In this paper, we propose a new graphbased coding framework and illustr...
read it

Adaptive Quantization for Deep Neural Network
In recent years Deep Neural Networks (DNNs) have been rapidly developed ...
read it
Pascal Frossard
verfied profile
Professor of Electrical Engineering, EPFL