Disentangling Video with Independent Prediction
arXiv:1901.05590
Abstract
We propose an unsupervised variational model for disentangling video into independent factors, i.e. each factor's future can be predicted from its past without considering the others. We show that our approach often learns factors which are interpretable as objects in a scene.
arXiv commentPresented at the Learning Disentangled Representations: from Perception to Control workshop at NIPS 2017
References in corpus (13)
- Adam: A Method for Stochastic Optimization
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Estimating Mutual Information
- Unsupervised Learning of Video Representations using LSTMs
- Deep Convolutional Inverse Graphics Network
- Self-Normalizing Neural Networks
- Unsupervised Learning of Disentangled Representations from Video
- Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA
- Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data
- Learning Disentangled Representations with Semi-Supervised Deep Generative Models
- Independently Controllable Factors
- Understanding Visual Concepts with Continuation Learning
- Disentangling Space and Time in Video with Hierarchical Variational Auto-encoders