Perception Updating Networks: On Architectural Constraints for Interpretable Video Generative Models
Abstract
We investigate a neural network architecture and statistical framework that models frames in videos using principles inspired by computer graphics pipelines. The proposed model explicitly represents "sprites" or its percepts inferred from maximum likelihood of the scene and infers its movement independently of its content. We impose architectural constraints that forces resulting architecture to behave as a recurrent what-where prediction network.
Cite
Text
Santana and Príncipe. "Perception Updating Networks: On Architectural Constraints for Interpretable Video Generative Models." International Conference on Learning Representations, 2017.Markdown
[Santana and Príncipe. "Perception Updating Networks: On Architectural Constraints for Interpretable Video Generative Models." International Conference on Learning Representations, 2017.](https://mlanthology.org/iclr/2017/santana2017iclr-perception/)BibTeX
@inproceedings{santana2017iclr-perception,
title = {{Perception Updating Networks: On Architectural Constraints for Interpretable Video Generative Models}},
author = {Santana, Eder and Príncipe, José C.},
booktitle = {International Conference on Learning Representations},
year = {2017},
url = {https://mlanthology.org/iclr/2017/santana2017iclr-perception/}
}