Disentangled Dynamic Representations from Unordered Data
arXiv preprint arXiv:1812.03962, 2018•arxiv.org
We present a deep generative model that learns disentangled static and dynamic
representations of data from unordered input. Our approach exploits regularities in
sequential data that exist regardless of the order in which the data is viewed. The result of
our factorized graphical model is a well-organized and coherent latent space for data
dynamics. We demonstrate our method on several synthetic dynamic datasets and real
video data featuring various facial expressions and head poses.
representations of data from unordered input. Our approach exploits regularities in
sequential data that exist regardless of the order in which the data is viewed. The result of
our factorized graphical model is a well-organized and coherent latent space for data
dynamics. We demonstrate our method on several synthetic dynamic datasets and real
video data featuring various facial expressions and head poses.
We present a deep generative model that learns disentangled static and dynamic representations of data from unordered input. Our approach exploits regularities in sequential data that exist regardless of the order in which the data is viewed. The result of our factorized graphical model is a well-organized and coherent latent space for data dynamics. We demonstrate our method on several synthetic dynamic datasets and real video data featuring various facial expressions and head poses.
arxiv.org
Showing the best result for this search. See all results