Book Chapter10.1007/978-3-540-36668-3_64
Variable duration motion texture for human motion modeling
Tianyu Huang,Fengxia Li,Shouyi Zhan,Jianyuan Min +3 more
- 07 Aug 2006
- pp 603-612
2
TL;DR: In this article, a variable duration motion texture is proposed to represent complex human motion that is statistically similar to the original captured motion data, which is defined as a threelevel structure with moton abstracts, motons and their distribution.
read more
Abstract: Statistical model is an effective method for character motion modeling. In this paper, a variable duration motion texture is proposed to represent complex human motion that is statistically similar to the original captured motion data. The motion texture is defined as a threelevel structure with moton abstracts, motons and their distribution. The motion texture is modeled by a Semi-SLDS (Semi- Switching Linear Dynamic System), which provides an intuitive framework for describing the continuous but nonlinear dynamics of human motion. To explicitly incorporate duration modeling capability, the Semi-SLDS is adopted to improve SLDS by replacing the Markov switching layer with semi-Markov model. In addition, the proposed approach is proved flexible and effective by several motion applications, namely motion synthesis, motion recognition and motion compression.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Hierarchical Analysis Model of Human Motion
Xiangchen Li,Tianyu Huang,Jihai Sun +2 more
- 08 Oct 2016
TL;DR: A four-level hierarchical model with posture- activity- motion- style was proposed in this paper, which is specified formally by PDM (Point Distribution Models), and the model validations were given by the experiments and applications.
Explicit-Duration Markov Switching Models
TL;DR: In this article, the authors provide a description of explicit-duration Markov switching models by categorizing the different approaches into three groups, which differ in encoding in the explicitduration variables different information about regime change/reset boundaries.
References
Style machines
Matthew E. Brand,Aaron Hertzmann +1 more
- 01 Jul 2000
TL;DR: This work approaches the problem of stylistic motion synthesis by learning motion patterns from a highly varied set of motion capture sequences, and identifies common choreographic elements across sequences, the different styles in which each element is performed, and a small number of styling degrees of freedom which span the many variations in the dataset.
802
•Proceedings Article
Learning Switching Linear Models of Human Motion
Vladimir Pavlovic,James M. Rehg,John MacCormick +2 more
- 01 Jan 2000
TL;DR: A new variational inference algorithm is obtained by casting the SLDS model as a Dynamic Bayesian Network, and classification experiments show the superiority of SLDS over conventional HMM's for the problem domain.
A dynamic Bayesian network approach to figure tracking using learned dynamic models
Vladimir Pavlovic,James M. Rehg,Tat-Jen Cham,Kevin Murphy +3 more
- 01 Jan 1999
TL;DR: A novel DBN-based switching linear dynamic system (SLDS) model that is an approximate Viterbi inference technique for overcoming the intractability of exact inference in mixed-state DBNs is described and its application to figure motion analysis is presented.
What are Textons
TL;DR: A three-level generative image model for learning textons from texture images and a sequence of experiments for learning the geometric, dynamic, and photometric structures from images and videos are presented and how general textons can be learned from generic natural images is discussed.