Learning switching linear models of human motion

Vladimir Pavlovic, James M. Rehg, John MacCormick

Research output: Chapter in Book/Report/Conference proceedingConference contribution

76 Scopus citations

Abstract

The human figure exhibits complex and rich dynamic behavior that is both nonlinear and time-varying. Effective models of human dynamics can be learned from motion capture data using switching linear dynamic system (SLDS) models. We present results for human motion synthesis, classification, and visual tracking using learned SLDS models. Since exact inference in SLDS is intractable, we present three approximate inference algorithms and compare their performance. In particular, a new variational inference algorithm is obtained by casting the SLDS model as a Dynamic Bayesian Network. Classification experiments show the superiority of SLDS over conventional HMM's for our problem domain.

Original languageEnglish (US)
Title of host publicationAdvances in Neural Information Processing Systems 13 - Proceedings of the 2000 Conference, NIPS 2000
PublisherNeural information processing systems foundation
ISBN (Print)0262122413, 9780262122412
StatePublished - 2001
Externally publishedYes
Event14th Annual Neural Information Processing Systems Conference, NIPS 2000 - Denver, CO, United States
Duration: Nov 27 2000Dec 2 2000

Publication series

NameAdvances in Neural Information Processing Systems
ISSN (Print)1049-5258

Other

Other14th Annual Neural Information Processing Systems Conference, NIPS 2000
Country/TerritoryUnited States
CityDenver, CO
Period11/27/0012/2/00

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Fingerprint

Dive into the research topics of 'Learning switching linear models of human motion'. Together they form a unique fingerprint.

Cite this