• Publications
  • Influence
Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
TLDR
We present a formulation of CNNs in the context of spectral graph theory, which provides the necessary mathematical background and efficient numerical schemes to design fast localized convolutional filters on graphs. Expand
  • 2,818
  • 420
  • PDF
The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains
TLDR
In applications such as social, energy, transportation, sensor, and neuronal networks, high-dimensional data naturally reside on the vertices of weighted graphs. Expand
  • 2,253
  • 335
  • PDF
FREAK: Fast Retina Keypoint
TLDR
We propose a novel keypoint descriptor inspired by the human visual system and more precisely the retina, coined Fast Retina Keypoint (FREAK). Expand
  • 1,676
  • 267
  • PDF
Wavelets on Graphs via Spectral Graph Theory
TLDR
We propose a novel method for constructing wavelet transforms of functions defined on the vertices of an arbitrary finite weighted graph using spectral decomposition of the discrete graph Laplacian L. Expand
  • 1,231
  • 151
  • PDF
Fast Global Minimization of the Active Contour/Snake Model
TLDR
In this paper, we propose to solve this problem by determining a global minimum of the active contour model. Expand
  • 877
  • 100
  • PDF
Geometric Deep Learning: Going beyond Euclidean data
TLDR
We would like to use deep neural networks to model geometric data with an underlying structure that is non-Euclidean. Expand
  • 1,357
  • 77
  • PDF
Graph Signal Processing: Overview, Challenges, and Applications
TLDR
Research in graph signal processing (GSP) aims to develop tools for processing data defined on irregular graph domains. Expand
  • 509
  • 66
  • PDF
Geodesic Convolutional Neural Networks on Riemannian Manifolds
TLDR
We introduce Geodesic Convolutional Neural Networks (GCNN), a generalization of the convolutional neural networks (CNN) paradigm to non-Euclidean manifolds. Expand
  • 475
  • 49
  • PDF
Learning Laplacian Matrix in Smooth Graph Signal Representations
TLDR
The construction of a meaningful graph plays a crucial role in the success of many graph-based representations and algorithms for handling structured data, especially in the emerging field of graph signal processing. Expand
  • 296
  • 44
  • PDF
Compressed Sensing for Real-Time Energy-Efficient ECG Compression on Wireless Body Sensor Nodes
TLDR
We quantify the potential of the emerging compressed sensing (CS) signal acquisition/compression paradigm for low-complexity energy-efficient ECG compression on the state-of-the-art Shimmer WBSN mote. Expand
  • 609
  • 42
  • PDF
...
1
2
3
4
5
...