A tutorial on hidden Markov models and selected applications in speech recognition
Readings in speech recognition
An Introduction to Variational Methods for Graphical Models
Machine Learning
Proceedings of the 27th annual conference on Computer graphics and interactive techniques
Motion texture: a two-level statistical model for character motion synthesis
Proceedings of the 29th annual conference on Computer graphics and interactive techniques
Proceedings of the 29th annual conference on Computer graphics and interactive techniques
Verbs and Adverbs: Multidimensional Motion Interpolation
IEEE Computer Graphics and Applications
Style-based inverse kinematics
ACM SIGGRAPH 2004 Papers
Learning physics-based motion style with nonlinear inverse optimization
ACM SIGGRAPH 2005 Papers
Multifactor Gaussian process models for style-content separation
Proceedings of the 24th international conference on Machine learning
Topologically-constrained latent variable models
Proceedings of the 25th international conference on Machine learning
Representing cyclic human motion using functional analysis
Image and Vision Computing
Hybrid motion graph for character motion synthesis
Journal of Visual Languages and Computing
| Hi-index | 0.00 |
This paper describes an unsupervised learning technique for modeling human locomotion styles, such as distinct related activities (e.g. running and striding) or variations of the same motion performed by different subjects. Modeling motion styles requires identifying the common structure in the motions and detecting style-specific characteristics. We propose an algorithm that learns a hierarchical model of styles from unlabeled motion capture data by exploiting the cyclic property of human locomotion. We assume that sequences with the same style contain locomotion cycles generated by noisy, temporally warped versions of a single latent cycle. We model these style-specific latent cycles as random variables drawn from a common "parent" cycle distribution, representing the structure shared by all motions. Given these hierarchical priors, the algorithm learns, in a completely unsupervised fashion, temporally aligned latent cycle distributions, each modeling a specific locomotion style, and computes for each example the style label posterior distribution, the segmentation into cycles, and the temporal warping with respect to the latent cycles. We demonstrate the flexibility of the model on several application problems such as style clustering, animation, style blending, and filling in of missing data.