DeepAI AI Chat
Log In Sign Up

Temporal Generative Adversarial Nets with Singular Value Clipping

by   Masaki Saito, et al.
Preferred Infrastructure

In this paper, we propose a generative model, Temporal Generative Adversarial Nets (TGAN), which can learn a semantic representation of unlabeled videos, and is capable of generating videos. Unlike existing Generative Adversarial Nets (GAN)-based methods that generate videos with a single generator consisting of 3D deconvolutional layers, our model exploits two different types of generators: a temporal generator and an image generator. The temporal generator takes a single latent variable as input and outputs a set of latent variables, each of which corresponds to an image frame in a video. The image generator transforms a set of such latent variables into a video. To deal with instability in training of GAN with such advanced networks, we adopt a recently proposed model, Wasserstein GAN, and propose a novel method to train it stably in an end-to-end manner. The experimental results demonstrate the effectiveness of our methods.


page 6

page 7


Conditional Generative Adversarial Nets

Generative Adversarial Nets [8] were recently introduced as a novel way ...

Recurrent Deconvolutional Generative Adversarial Networks with Application to Text Guided Video Generation

This paper proposes a novel model for video generation and especially ma...

Diverse Video Captioning Through Latent Variable Expansion with Conditional GAN

Automatically describing video content with text description is challeng...

TGANv2: Efficient Training of Large Models for Video Generation with Multiple Subsampling Layers

In this paper, we propose a novel method to efficiently train a Generati...

Generative Adversarial Image Synthesis with Decision Tree Latent Controller

This paper proposes the decision tree latent controller generative adver...

Progressive Generative Adversarial Binary Networks for Music Generation

Recent improvements in generative adversarial network (GAN) training tec...

Learning Probabilistic Models from Generator Latent Spaces with Hat EBM

This work proposes a method for using any generator network as the found...