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.

Adaptive streaming addresses the increasing and heterogenous demand of multimedia content over the Internet by offering several streams for each video. Each stream has a different resolution and bit rate, aimed at a specific set of users, e.g., TV, mobile ...

Multi-pod systolic arrays are emerging as the architecture of choice in DNN inference accelerators. Despite their potential, designing multi-pod systolic arrays to maximize effective throughput/Watt-i.e., throughput/Watt adjusted when accounting for array ...

We address the problem of keyword spotting in continuous speech streams when training and testing conditions can be different. We propose a keyword spotting algorithm based on sparse representation of speech signals in a time-frequency feature space. The t ...

In many applications, a dataset can be considered as a set of observed signals that live on an unknown underlying graph structure. Some of these signals may be seen as white noise that has been filtered on the graph topology by a graph filter. Hence, the k ...

Along with the successful deployment of deep neural networks in several application domains, the need to unravel the black-box nature of these networks has seen a significant increase recently. Several methods have been introduced to provide insight into t ...

We address the problem of prioritized video streaming over lossy overlay networks. We propose to exploit network path diversity via a novel Randomized Network Coding (RNC) approach that provides unequal error protection (UEP) to the packets conveying the v ...

We present a novel plenoptic sampling scheme that permits an efficient representation of the full light ray field in a space limited by a convex closed surface. We show that a convenient way to sample the light ray field around an observer consists in usin ...

This paper presents a new scalable and highly flexible color image coder based on a Matching Pursuit expansion. The Matching Pursuit algorithm provides an intrinsically progressive stream and the proposed coder allows us to reconstruct color information from the first bit received. In order to efficiently capture edges in natural images, the dictionary of atoms is built by translation, rotation and anisotropic refinement of a wavelet-like mother function. This dictionary is moreover invariant under shifts a

This paper addresses the problem of optimal rate allocation for multiple description coding with redundant signal expansions. In case of redundant descriptions, the quantization of the transform coefficients has clearly to be adapted to the importance of t ...

This paper presents an extension of block-based motion estimation for omnidirectional videos, based on a camera and translational object motion model that accounts for the spherical geometry of the imaging system. We use this model to design a new algorith ...

In this work, we study graph-based multi-arms bandit (MAB) problems aimed at optimizing actions on irregular and high-dimensional graphs. More formally, we consider a decision-maker that takes sequential actions over time and observes the experienced rewar ...

We propose a cross-layer strategy for resource allocation between spatially correlated sources in the uplink of multi-cell FDMA networks. Our objective is to find the optimum power and channel allocation to the different sources, in order to minimize the m ...

Multiparty videoconferences, or more generally multiparty video calls, are gaining a lot of popularity as they offer a rich communication experience. These applications have however, large requirements in terms of both network and computational resources a ...

Predicting the saliency map of a 360-degree video is the key for various downstream tasks, such as saliency-based compression and tile-based adaptive streaming. Besides static salient objects, the moving target will also contribute to the saliency map. The ...

This paper addresses the problem of super- resolution from low resolution spherical images that are not perfectly registered. Such a problem is typically en- countered in omnidirectional vision scenarios with re- duced resolution sensors in imperfect setti ...

The extension of convolutional neural networks to irregular domains has pavedthe way to promising graph data analysis methods. It has however come at theexpense of a reduced representation power, as most of these new network archi-tectures can only learn i ...

We consider the problem of distributed average consensus where sensors exchange quantized data with their neighbors. We deploy a polynomial filtering approach in the network nodes in order to accelerate the convergence of the consensus problem. The quantiz ...

Traditionally, most multimedia content has been developed to stimulate two of the human senses, i.e., sight and hearing. Due to recent technological advancements, however, innovative services have been developed that provide more realistic, immersive, and ...

The Multiview Video Coding (MVC) standard efficiently compresses multiview video by considering spatial, temporal and interview correlations. This letter studies the impact of the MVC interview prediction structure on both the transmission and the overall ...

Pascal Frossard

Chat with Graph Search

Optimal Set of Video Representations in Adaptive Streaming

Scale-out Systolic Arrays

Fast keyword detection with sparse time-frequency models

Figlearn: Filter And Graph Learning Using Optimal Transport

DARE: Towards Robust Text Explanations in Biomedical and Healthcare Applications

Prioritized Distributed Video Delivery with Randomized Network Coding

Plenoptic Spherical Sampling

Color image scalable coding with Matching Pursuit

Multiple description image coding with redundant expansions and optimal quantization

Color Image Scalable Coding with Matching Pursuit

Deformable block based motion estimation in omnidirectional image sequences

Spectral MAB for Unknown Graph Processes

Correlation-aware Resource Allocation in Multi-Cell Networks

Distributed rate allocation in switch-based multiparty videoconference

360Spred: Saliency Prediction for 360-Degree Videos Based on 3D Separable Graph Convolutional Networks

Super-resolution from unregistered omnidirectional images

Learning anisotropic filters on product graphs

Polynomial Filter Design for Quantized Consensus

Subjective Evaluation of 360-degree Sensory Experiences

Optimized MVC Prediction Structures for Interactive Multiview Video Streaming