Space-Time Pose Representation for 3D Human Action Recognition


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… (More)
DOI: 10.1007/978-3-642-41190-8_49
View Slides


4 Figures and Tables


Citations per Year

53 Citations

Semantic Scholar estimates that this publication has 53 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Devanne2013SpaceTimePR, title={Space-Time Pose Representation for 3D Human Action Recognition}, author={Maxime Devanne and Hazem Wannous and Stefano Berretti and Pietro Pala and Mohamed Daoudi and Alberto Del Bimbo}, booktitle={ICIAP Workshops}, year={2013} }