Discriminative Sequence Back-constrained GP-LVM for MOCAP based Action Recognition - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2013

Discriminative Sequence Back-constrained GP-LVM for MOCAP based Action Recognition

Valsamis Ntouskos
  • Function : Author
Panagiotis Papadakis
Fiora Pirri
  • Function : Author

Abstract

In this paper we address the problem of human action recognition within Motion Capture sequences. We introduce a method based on Gaussian Process Latent Variable Models and Alignment Kernels. We build a new discriminative latent variable model with back-constraints induced by the similarity of the original sequences. We compare the proposed method with a standard sequence classification method based on Dynamic Time Warping and with the recently introduced V-GPDS model which is able to model highly dimensional dynamical systems. The proposed methodology exhibits high performance even for datasets that have not been manually pre-processed while it further allows fast inference by exploiting the back constraints.
Fichier principal
Vignette du fichier
CR_ICPRAM_2013_122.pdf (750.39 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00832895 , version 1 (11-06-2013)

Identifiers

Cite

Valsamis Ntouskos, Panagiotis Papadakis, Fiora Pirri. Discriminative Sequence Back-constrained GP-LVM for MOCAP based Action Recognition. International Conference on Pattern Recognition Applications and Methods, Feb 2013, Barcelona, Spain. ⟨10.5220/0004268600870096⟩. ⟨hal-00832895⟩
165 View
265 Download

Altmetric

Share

Gmail Facebook X LinkedIn More