Publication

Deep learning on graph for semantic segmentation of point cloud

Publications associées (96)

Graph Chatbot

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

Connectez-vous pour utiliser Chat avec Graph Search

A Windowed Graph Fourier Transform

Pierre Vandergheynst, Benjamin Ricaud, David Shuman

The prevalence of signals on weighted graphs is increasing; however, because of the irregular structure of weighted graphs, classical signal processing techniques cannot be directly applied to signals on graphs. In this paper, we define generalized transla ...

Ieee2012

A Windowed Graph Fourier Transform

Pierre Vandergheynst, Benjamin Ricaud, David Shuman

IEEE2012

On localisation and uncertainty measures on graphs

Nathanaël Perraudin

Due to the appearance of data on networks such as internet or Facebook, the number of applications of signal on weighted graph is increasing. Unfortunately, because of the irregular structure of this data, classical signal processing techniques are not app ...

2012

Information Processing and Structure of Dynamical Networks

Ali Ajdari Rad

Networks are everywhere and we are confronted with many networks in our daily life. Networks such as Internet, World Wide Web, social, biological and economical networks have been subject to extensive studies in the last decade. The volume of publications ...

EPFL2011

Chebyshev polynomial approximation for transductive learning on graphs

Nathanaël Perraudin

The goal of transductive learning is to find a way to recover the labels of lots of data with only a few known samples. In this work, we will work on graphs for two reasons. First, it’s possible to construct a graph from a given dataset with features. The ...

2011

Space crossing numbers

We define the crossing number for an embedding of a graph G into R^3, and prove a lower bound on it which almost implies the classical crossing lemma. We also give sharp bounds on the space crossing numbers of pseudo-random graphs. ...

2011

Disjoint homometric sets in graphs

János Pach

Two subsets of vertices in a graph are called homometric if the multisets of distances determined by them are the same. Let h(n) denote the largest number h such that any connected graph of n vertices contains two disjoint homometric subsets of size h. It ...

2011

Semi-Supervised Learning with Spectral Graph Wavelets

Pierre Vandergheynst, David Shuman, Mohammadjavad Faraji

We consider the transductive learning problem when the labels belong to a continuous space. Through the use of spectral graph wavelets, we explore the benefits of multiresolution analysis on a graph constructed from the labeled and unlabeled data. The spec ...

2011

Exploring Spatial Characteristics of Urban Transportation Networks

Nikolaos Geroliminis, Yuxuan Ji

It has been shown recently that a Macroscopic Fundamental Diagram (MFD) exists in urban transportation networks under certain conditions. However, MFD is not universally expected. Previous research demonstrates the existence of MFDs in homogeneous networks ...

Ieee Service Center, 445 Hoes Lane, Po Box 1331, Piscataway, Nj 08855-1331 Usa2011

Microsimulation Framework for Urban Price-Taker Markets

Bilal Farooq

In the context of integrated transportation and other urban engineering infrastructure systems, there are many examples of markets, where consumers exhibit price-taking behaviour. While this behaviour is ubiquitous, the underlying mechanism can be captured ...

2011