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. |
Year | Venue | DocType |
---|---|---|
2017 | ICML | Conference |
Volume | Citations | PageRank |
abs/1610.00527 | 0 | 0.34 |
References | Authors | |
0 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nal Kalchbrenner | 1 | 3662 | 149.32 |
Aäron Van Den Oord | 2 | 1585 | 64.43 |
Karen Simonyan | 3 | 12058 | 446.84 |
ivo danihelka | 4 | 855 | 43.46 |
Oriol Vinyals | 5 | 9419 | 418.45 |
Graves, Alex | 6 | 8572 | 405.10 |
Koray Kavukcuoglu | 7 | 10189 | 504.11 |