Publications by Pascal Frossard

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

This work introduces DiGress, a discrete denoising diffusion model for generating graphs with categorical node and edge attributes. Our model utilizes a discrete diffusion process that progressively edits graphs with noise, through the process of adding or ...

Multiview video refers to videos of the same dynamic 3-D scene captured simultaneously by multiple closely spaced cameras from different viewpoints. We study interactive streaming of pre-encoded multiview videos, where, at any time, a client can request an ...

Sparse representations of images in well-designed dictionaries can be used for effective classification. Meanwhile, training data available in most realistic settings are likely to be exposed to geometric transformations, which poses a challenge for the de ...

Hierarchical Graph Neural Networks (GNNs) integrate pooling layers to generate graph representations by progressively coarsening graphs. These GNNs are provably more expressive than traditional GNNs that solely rely on message passing. While prior work shows that hierarchical architectures do not exhibit empirical performance gains, these findings are based on small datasets where structure-unaware baselines often perform well, limiting their generalizability. In this work, we comprehensively investigate th

In this work, we propose a distributed rate allocation algorithm that minimizes the average decoding delay for multimedia clients in inter-session network coding systems. We consider a scenario where the users are organized in a mesh network and each user ...

In free viewpoint video systems, where a user has the freedom to select a virtual view from which an observation image of the 3D scene is rendered, the scene is commonly represented by texture and depth images from multiple nearby viewpoints. In such repre ...

This paper addresses efficient packet loss recovery by retransmission in window-based congestion control protocols. It builds on explicit congestion control mechanisms to decouple the packet loss detection from the congestion feedback signals. Implicit algorithms alternatively infer congestion from losses (which yields to window size reduction), and therefore do not allow to evaluate the performance of window-based transmission algorithms in lossy environments. We first propose a simple modification of TCP

Bird's eye view (BEV) representation has emerged as a dominant solution for describing 3D space in autonomous driving scenarios. However, objects in the BEV representation typically exhibit small sizes, and the associated point cloud context is inherently ...

This paper addresses the problem of dense estimation of disparities between omnidirectional images, in a spherical framework. Omnidirectional imaging certainly represents important advantages for the representation and processing of the plenoptic function ...

We consider the problem of classification of a pattern from multiple compressed observations that are collected in a sensor network. In particular, we exploit the properties of random projections in generic sensor devices and we take some first steps in in ...

This paper addresses the problem of fair allocation of bandwidth resources on lossy channels in hybrid heterogeneous networks. It discusses more particularly the ability of window-based congestion control to support non-congestion related losses. We invest ...

This paper investigates context-driven flow allocation and media delivery in online social networks. We exploit information on contacts and content preferences found in social networking applications to provide efficient network services and operation at t ...

Neural Machine Translation (NMT) systems are used in various applications. However, it has been shown that they are vulnerable to very small perturbations of their inputs, known as adversarial attacks. In this paper, we propose a new targeted adversarial attack against NMT models. In particular, our goal is to insert a predefined target keyword into the translation of the adversarial sentence while maintaining similarity between the original sentence and the perturbed one in the source domain. To this aim,

Adapting the transmission rate of video telephony Internet applications in order to guarantee the maximal communication quality is still an open and extremely challenging problem. The congestion control algorithm, which is the algorithm responsible for adj ...

The invention relates to a method and an apparatus for encoding and/or decoding digital images, wherein said encoding apparatus (1100) comprises processing means (1110) configured for determining weights of a graph related to an image by minimizing a cost ...

Peer-to-peer (P2P) systems are becoming increasingly popular due to their ability to deliver large amounts of data at a reduced deployment cost. While P2P systems foster the development of novel media applications, they also represent an interesting altern ...

This paper presents a distributed and occlusion-robust coding scheme for multi-view omnidirectional images, which relies on the geometry of the 3D scene. The Wyner-Ziv coder uses a multi-view correlation model that relates 3D features in different images u ...

This paper presents a highly flexible video coding scheme (MP3D), based on the use of a redundant 3-D spatio-temporal dictionary of functions. Directionality and anisotropic scaling are key ingredients to the spatial components, that form a rich collection ...

This paper addresses the problem of representing multimedia information under a compressed form that permits efficient classification. The semantic coding problem starts from a subspace method where dimensionality reduction is formulated as a matrix factor ...

Modern data processing tasks frequently involve structured data, for example signals defined on the vertex set of a weighted graph. In this paper, we address the problem of inference of mobility patterns from data defined on geographical graphs based on sp ...

Pascal Frossard

Chat with Graph Search

DiGress: Discrete Denoising diffusion for graph generation

Coding Structure and Replication Optimization for Interactive Multiview Video Streaming

Transformation-Invariant Dictionary Learning for Classification with 1-Sparse Representations

On the Role of Structure in Hierarchical Graph Neural Networks

Distributed Rate Allocation in Inter-Session Network Coding

Encoder-Driven Inpainting Strategy in Multiview Video Compression

Explicit window-based transport control protocols in lossy environments

IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection

Dense Disparity Estimation from Omnidirectional Images

Compressed classification of observation sets with linear subspace embeddings

Loss-resilient window-based congestion control

Context-adaptive information flow allocation and media delivery in online social networks

Targeted Adversarial Attacks Against Neural Machine Translation

A Bayesian Bandit Approach to Adaptive Delay-based Congestion Control

Methods and apparatuses for encoding and decoding digital images or video streams

Enabling Adaptive Video Streaming in P2P Systems

Geometry-based distributed coding of multi-view omnidirectional images

Flexible Motion-Adaptive Video Coding with Redundant Expansions

Semantic coding by supervised dimensionality reduction

Inference of Mobility Patterns via Spectral Graph Wavelets