Citation

BibTex format

@inproceedings{Eleftheriadis:2017:10.1007/978-3-319-54184-6_10,
author = {Eleftheriadis, S and Rudovic, O and Deisenroth, MP and Pantic, M},
doi = {10.1007/978-3-319-54184-6_10},
pages = {154--170},
title = {Variational gaussian process auto-Encoder for ordinal prediction of facial action units},
url = {http://dx.doi.org/10.1007/978-3-319-54184-6_10},
year = {2017}
}

RIS format (EndNote, RefMan)

TY  - CPAPER
AB - © Springer International Publishing AG 2017. We address the task of simultaneous feature fusion and modeling of discrete ordinal outputs. We propose a novel Gaussian process (GP) autoencoder modeling approach. In particular, we introduce GP encoders to project multiple observed features onto a latent space, while GP decoders are responsible for reconstructing the original features. Inference is performed in a novel variational framework, where the recovered latent representations are further constrained by the ordinal output labels. In this way, we seamlessly integrate the ordinal structure in the learned manifold, while attaining robust fusion of the input features. We demonstrate the representation abilities of our model on benchmark datasets from machine learning and affect analysis. We further evaluate the model on the tasks of feature fusion and joint ordinal prediction of facial action units. Our experiments demonstrate the benefits of the proposed approach compared to the state of the art.
AU - Eleftheriadis,S
AU - Rudovic,O
AU - Deisenroth,MP
AU - Pantic,M
DO - 10.1007/978-3-319-54184-6_10
EP - 170
PY - 2017///
SN - 0302-9743
SP - 154
TI - Variational gaussian process auto-Encoder for ordinal prediction of facial action units
UR - http://dx.doi.org/10.1007/978-3-319-54184-6_10
UR - http://hdl.handle.net/10044/1/40069
ER -