MLGCN: Multi-Laplacian Graph Convolutional Networks for Human Action Recognition - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

MLGCN: Multi-Laplacian Graph Convolutional Networks for Human Action Recognition

Résumé

Convolutional neural networks are nowadays witnessing a major success in different pattern recognition problems. These learning models were basically designed to handle vectorial data such as images but their extension to non-vectorial and semi-structured data (namely graphs with variable sizes, topology, etc.) remains a major challenge, though a few interesting solutions are currently emerging.In this paper, we introduce MLGCN; a novel spectral Multi-Laplacian Graph Convolutional Network. The main contribution of this method resides in a new design principle that learns graph-laplacians as convex combinations of other elementary laplacians – each one dedicated to a particular topology of the input graphs. We also introduce a novel pooling operator, on graphs, that proceeds in two steps: context-dependent node expansion is achieved, followed by a global average pooling; the strength of this two-step process resides in its ability to preserve the discrimination power of nodes while achieving permutation invariance. Experiments conducted on SBU and UCF-101 datasets, show the validity of our method for the challenging task of action recognition.
Fichier principal
Vignette du fichier
1103-paper.pdf (380.36 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03089634 , version 1 (28-12-2020)

Identifiants

  • HAL Id : hal-03089634 , version 1

Citer

Ahmed Mazari, Hichem Sahbi. MLGCN: Multi-Laplacian Graph Convolutional Networks for Human Action Recognition. The British Machine Vision Conference (BMVC), Sep 2019, Cardiff, United Kingdom. ⟨hal-03089634⟩
224 Consultations
99 Téléchargements

Partager

Gmail Facebook X LinkedIn More