Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer
Authors:
Top Cited Papers
- 24 October 2022
- book chapter
- Published by Springer Nature
- p. 102-118
Abstract
No abstract availableKeywords
All Related Versions
This publication has 24 references indexed in Scilit:
- High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs2018
- Learning to Generate Time-Lapse Videos Using Multi-stage Dynamic Generative Adversarial Networks2018
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018
- MoCoGAN: Decomposing Motion and Content for Video Generation2018
- Hierarchical Neural Story Generation2018
- Temporal Generative Adversarial Nets with Singular Value Clipping2017
- Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset2017
- Audio Set: An ontology and human-labeled dataset for audio events2017
- Perceptual Losses for Real-Time Style Transfer and Super-Resolution2016
- Learning Spatiotemporal Features with 3D Convolutional Networks2015