Skip to Main content Skip to Navigation
Conference papers

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

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.
Complete list of metadata

Cited literature [32 references]  Display  Hide  Download

https://hal.inria.fr/hal-00832895
Contributor : Panagiotis Papadakis <>
Submitted on : Tuesday, June 11, 2013 - 3:22:14 PM
Last modification on : Wednesday, September 26, 2018 - 4:32:03 PM
Long-term archiving on: : Thursday, September 12, 2013 - 4:08:48 AM

File

CR_ICPRAM_2013_122.pdf
Files produced by the author(s)

Identifiers

Citation

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⟩

Share

Metrics

Record views

385

Files downloads

456