ICML 2017poster528 citations
Video Pixel Networks
Nal Kalchbrenner, Aäron Oord, Karen Simonyan, Ivo Danihelka, Oriol Vinyals, Alex Graves, Koray Kavukcuoglu
Abstract
We propose a probabilistic video model, the Video Pixel Network (VPN), that estimates the discrete joint distribution of the raw pixel values in a video. The model and the neural architecture reflect the time, space and color structure of video tensors and encode it as a four-dimensional dependency chain. The VPN approaches the best possible performance on the Moving MNIST benchmark, a leap over the previous state of the art, and the generated videos show only minor deviations from the ground truth. The VPN also produces detailed samples on the action-conditional Robotic Pushing benchmark and generalizes to the motion of novel objects.
BibTeX
@InProceedings{pmlr-v70-kalchbrenner17a,
title = {Video Pixel Networks},
author = {Nal Kalchbrenner and A{\"a}ron van den Oord and Karen Simonyan and Ivo Danihelka and Oriol Vinyals and Alex Graves and Koray Kavukcuoglu},
booktitle = {Proceedings of the 34th International Conference on Machine Learning},
pages = {1771--1779},
year = {2017},
editor = {Precup, Doina and Teh, Yee Whye},
volume = {70},
series = {Proceedings of Machine Learning Research},
month = {06--11 Aug},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v70/kalchbrenner17a/kalchbrenner17a.pdf},
url = {https://proceedings.mlr.press/v70/kalchbrenner17a.html},
abstract = {We propose a probabilistic video model, the Video Pixel Network (VPN), that estimates the discrete joint distribution of the raw pixel values in a video. The model and the neural architecture reflect the time, space and color structure of video tensors and encode it as a four-dimensional dependency chain. The VPN approaches the best possible performance on the Moving MNIST benchmark, a leap over the previous state of the art, and the generated videos show only minor deviations from the ground truth. The VPN also produces detailed samples on the action-conditional Robotic Pushing benchmark and generalizes to the motion of novel objects.}
}