Generating Videos with Scene Dynamics

Abstract

We capitalize on large amounts of unlabeled video in order to learn a model of scene dynamics for both video recognition tasks (e.g. action classification) and video generation tasks (e.g. future prediction). We propose a generative adversarial network for video with a spatio-temporal convolutional architecture that untangles the scene’s foreground from the background. Experiments suggest this model can generate tiny videos up to a second at full frame rate better than simple baselines, and we show its utility at predicting plausible futures of static images. Moreover, experiments and visualizations show the model internally learns useful features for recognizing actions with minimal supervision, suggesting scene dynamics are a promising signal for representation learning. We believe generative video models can impact many applications in video understanding and simulation.

Extracted Key Phrases

7 Figures and Tables

05010020162017
Citations per Year

90 Citations

Semantic Scholar estimates that this publication has 90 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Vondrick2016GeneratingVW, title={Generating Videos with Scene Dynamics}, author={Carl Vondrick and Hamed Pirsiavash and Antonio Torralba}, booktitle={NIPS}, year={2016} }