Sciweavers

Share
CVPR
2012
IEEE

Multi-view latent variable discriminative models for action recognition

7 years 11 months ago
Multi-view latent variable discriminative models for action recognition
Many human action recognition tasks involve data that can be factorized into multiple views such as body postures and hand shapes. These views often interact with each other over time, providing important cues to understanding the action. We present multi-view latent variable discriminative models that jointly learn both view-shared and viewspecific sub-structures to capture the interaction between views. Knowledge about the underlying structure of the data is formulated as a multi-chain structured latent conditional model, explicitly learning the interaction between multiple views using disjoint sets of hidden variables in a discriminative manner. The chains are tied using a predetermined topology that repeats over time. We present three topologies – linked, coupled, and linked-coupled – that differ in the type of interaction between views that they model. We evaluate our approach on both segmented and unsegmented human action recognition tasks, using the ArmGesture, the NATOPS,...
Yale Song, Louis-Philippe Morency, Randall Davis
Added 28 Sep 2012
Updated 28 Sep 2012
Type Journal
Year 2012
Where CVPR
Authors Yale Song, Louis-Philippe Morency, Randall Davis
Comments (0)
books