Learning Dynamic Generator Model by Alternating Back-Propagation through Time

national conference on artificial intelligence, pp. 5498-5507, 2019.

Cited by: 13|Views44
EI

Abstract:

This paper studies the dynamic generator model for spatial-temporal processes such as dynamic textures and action sequences in video data. In this model, each time frame of the video sequence is generated by a generator model, which is a non-linear transformation of a latent state vector, where the non-linear transformation is parametrize...More

Code:

Data:

Your rating :
0

 

Tags
Comments