3D Convolutional Networks for Action Recognition: Application to Sport Gesture Recognition - Archive ouverte HAL Accéder directement au contenu
Chapitre D'ouvrage Année : 2021

3D Convolutional Networks for Action Recognition: Application to Sport Gesture Recognition

Résumé

3D convolutional networks is a good means to perform tasks such as video segmentation into coherent spatio-temporal chunks and classification of them with regard to a target taxonomy. In the chapter we are interested in the classification of continuous video takes with repeatable actions, such as strokes of table tennis. Filmed in a free marker less ecological environment, these videos represent a challenge from both segmentation and classification point of view. The 3D convnets are an efficient tool for solving these problems with window-based approaches.
Fichier principal
Vignette du fichier
Multi_faceted_Deep_Learning__Models_and_Data.pdf (2.28 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03639273 , version 1 (12-04-2022)

Identifiants

Citer

Pierre-Etienne Martin, J Benois-Pineau, R Péteri, A Zemmari, J Morlier. 3D Convolutional Networks for Action Recognition: Application to Sport Gesture Recognition. Multi-faceted Deep Learning, 2021. ⟨hal-03639273⟩

Collections

CNRS
14 Consultations
104 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More