Accession Number:

ADA556113

Title:

Spike Train Driven Dynamical Models for Human Actions

Descriptive Note:

Conference paper

Corporate Author:

CALIFORNIA UNIV LOS ANGELES DEPT OF COMPUTER SCIENCE

Report Date:

2010-06-01

Pagination or Media Count:

9.0

Abstract:

We investigate dynamical models of human motion that can support both synthesis and analysis tasks. Unlike coarser discriminative models that work well when action classes are nicely separated, we seek models that have finescale representational power and can therefore model subtle differences in the way an action is performed. To this end, we model an observed action as an unknown linear time-invariant dynamical model of relatively small order driven by a sparse bounded input signal. Our motivating intuition is that the time-invariant dynamics will capture the unchanging physical characteristics of an actor, while the inputs used to excite the system will correspond to a causal signature of the action being performed. We show that our model has sufficient representational power to closely approximate large classes of non-stationary actions with significantly reduced complexity. We also show that temporal statistics of the inferred input sequences can be compared in order to recognize actions and detect transitions between them.

Subject Categories:

  • Cybernetics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE