Spike Train Driven Dynamical Models for Human Actions

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.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 2010
Accession Number
ADA556113

Entities

People

  • Kamil Wnuk
  • Michalis Raptis
  • Stefano Soatto

Organizations

  • University of California, Los Angeles

Tags

Communities of Interest

  • Energy and Power Technologies
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence Software
  • Computational Science
  • Computer Science
  • Computer Vision
  • Data Science
  • Hidden Markov Models
  • Identification
  • Information Science
  • Machine Learning
  • Motion Capture
  • Pattern Recognition
  • Sequences
  • Stationary
  • Statistics
  • Supervised Machine Learning
  • Transitions

Fields of Study

  • Computer science

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Atmospheric Science / Meteorology, specifically Wind Wave Turbulence.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference