Journal
INTERNATIONAL JOURNAL OF COMPUTER VISION
Volume 130, Issue 11, Pages 2695-2706Publisher
SPRINGER
DOI: 10.1007/s11263-022-01668-8
Keywords
3D skeletal motion; Bayesian inference; Biologically valid interpretation; Generative models; Latent state modeling; Variational inference
Categories
Ask authors/readers for more resources
In this paper, we propose a Bayesian switching dynamical model for segmentation of 3D pose data over time that uncovers interpretable patterns in the data and is generative. The experiments demonstrate that our model outperforms state-of-the-art methods on biological motion datasets.
In this paper, we propose a Bayesian switching dynamical model for segmentation of 3D pose data over time that uncovers interpretable patterns in the data and is generative. Our model decomposes highly correlated skeleton data into a set of few spatial basis of switching temporal processes in a low-dimensional latent framework. We parameterize these temporal processes with regard to a switching deep vector autoregressive prior in order to accommodate both multimodal and higher-order nonlinear inter-dependencies. This results in a dynamical deep generative latent model that parses the meaningful intrinsic states in the dynamics of 3D pose data using approximate variational inference, and enables a realistic low-level dynamical generation and segmentation of complex skeleton movements. Our experiments on four biological motion data containing bat flight, salsa dance, walking, and golf datasets substantiate superior performance of our model in comparison with the state-of-the-art methods.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available