Skip to Main content Skip to Navigation
Conference papers

Space-time Pose Representation for 3D Human Action Recognition

Maxime Devanne 1, 2, 3, * Hazem Wannous 1 Stefano Berretti 3 Pietro Pala 3 Mohamed Daoudi 1, 2 Alberto del Bimbo 3
* Corresponding author
LIFL - Laboratoire d'Informatique Fondamentale de Lille
Abstract : 3D human action recognition is an important current challenge at the heart of many research areas lying to the modeling of the spatio-temporal information. In this paper, we propose representing human actions using spatio-temporal motion trajectories. In the proposed approach, each trajectory consists of one motion channel corresponding to the evolution of the 3D position of all joint coordinates within frames of action sequence. Action recognition is achieved through a shape trajectory representation that is learnt by a K-NN classifier, which takes benefit from Riemannian geometry in an open curve shape space. Experiments on the MSR Action 3D and UTKinect human action datasets show that, in comparison to state-of-the-art methods, the proposed approach obtains promising results that show the potential of our approach.
Document type :
Conference papers
Complete list of metadata

Cited literature [14 references]  Display  Hide  Download
Contributor : Maxime Devanne <>
Submitted on : Friday, June 28, 2013 - 11:29:38 AM
Last modification on : Monday, September 20, 2021 - 11:38:27 AM
Long-term archiving on: : Sunday, September 29, 2013 - 4:36:39 AM


Files produced by the author(s)


  • HAL Id : hal-00839494, version 1


Maxime Devanne, Hazem Wannous, Stefano Berretti, Pietro Pala, Mohamed Daoudi, et al.. Space-time Pose Representation for 3D Human Action Recognition. ICIAP Workshop on Social Behaviour Analysis, Sep 2013, Naples, France. pp.1. ⟨hal-00839494⟩



Record views


Files downloads