2011
NeurIPS
NeurIPS 2011
Facial Expression Transfer with Input-Output Temporal Restricted Boltzmann Machines
Abstract
We present a type of Temporal Restricted Boltzmann Machine that defines a probability distribution over an output sequence conditional on an input sequence. It shares the desirable properties of RBMs: efficient exact inference, an exponentially more expressive latent state than HMMs, and the ability to model nonlinear structure and dynamics. We apply our model to a challenging real-world graphics problem: facial expression transfer. Our results demonstrate improved performance over several baselines modeling high-dimensional 2D and 3D data.
🌱
Topic Pioneer
- Image Translation
🌉
Interdisciplinary Bridge
- Artificial Intelligence and Computer Vision
📈
Trend Setter
- Variational Inference
🐣
Hot Topic Early Bird
- hidden markov model
Topics
Artificial Intelligence > Bayesian & Probabilistic > Probabilistic Modeling
Deep Learning > Architectures > Neural Networks
Deep Learning > Models > Generative Models
Computer Vision > Analysis > Face Recognition
Computer Vision > Generation > Image Translation
Computer Vision > Processing > Image Editing
Machine Learning > Bayesian & Probabilistic > Probabilistic Modeling
Artificial Intelligence > Core AI > Computer Vision
Computer Vision > Core AI > Computer Vision
Artificial Intelligence > Bayesian & Probabilistic > Variational Inference
Keywords
temporal modeling
probability distribution
exact inference
temporal restricted boltzmann machine
facial expression transfer
nonlinear structure
hidden markov model
latent variable model
restricted boltzmann machine
high-dimensional data
latent state
conditional probability distribution
temporal model
graphics application