Learning Alignments from Latent Space Structures

Ieva Kazlauskaite; Carl Henrik Ek; Neill Campbell

Learning Alignments from Latent Space Structures

Ieva Kazlauskaite, Carl Henrik Ek, Neill Campbell

Research output: Contribution to conference › Paper › peer-review

95 Downloads (Pure)

Abstract

In this paper we present a model that is capable of learning alignments between high-dimensional data by exploiting low-dimensional structures. Specifically, our method uses a Gaussian process latent variable model (GP-LVM) to learn alignments and latent representations simultaneously. The results show that our model performs alignment implicitly and improves the smoothness of the low dimensional representations.

Original language	English
Publication status	Published - 9 Dec 2016
Event	NIPS Workshop on Learning in High Dimensions with Structure - Duration: 9 Dec 2016 → … https://sites.google.com/site/structuredlearning16/

Workshop

Workshop	NIPS Workshop on Learning in High Dimensions with Structure
Period	9/12/16 → …
Internet address	https://sites.google.com/site/structuredlearning16/

Access to Document

lhds16_alignments

Centre for the Analysis of Motion, Entertainment Research and Applications (CAMERA)
Cosker, D., Bilzon, J., Campbell, N., Cazzola, D., Colyer, S., Fincham Haines, T., Hall, P., Kim, K. I., Lutteroth, C., McGuigan, P., O'Neill, E., Richardt, C., Salo, A., Seminati, E., Tabor, A. & Yang, Y.
Engineering and Physical Sciences Research Council
1/09/15 → 28/02/21
Project: Research council

Cite this

@conference{20a5625e20b04873b23606af2fe7387f,

title = "Learning Alignments from Latent Space Structures",

abstract = "In this paper we present a model that is capable of learning alignments between high-dimensional data by exploiting low-dimensional structures. Specifically, our method uses a Gaussian process latent variable model (GP-LVM) to learn alignments and latent representations simultaneously. The results show that our model performs alignment implicitly and improves the smoothness of the low dimensional representations.",

author = "Ieva Kazlauskaite and Ek, {Carl Henrik} and Neill Campbell",

year = "2016",

month = dec,

day = "9",

language = "English",

note = "NIPS Workshop on Learning in High Dimensions with Structure ; Conference date: 09-12-2016",

url = "https://sites.google.com/site/structuredlearning16/",

}

TY - CONF

T1 - Learning Alignments from Latent Space Structures

AU - Kazlauskaite, Ieva

AU - Ek, Carl Henrik

AU - Campbell, Neill

PY - 2016/12/9

Y1 - 2016/12/9

N2 - In this paper we present a model that is capable of learning alignments between high-dimensional data by exploiting low-dimensional structures. Specifically, our method uses a Gaussian process latent variable model (GP-LVM) to learn alignments and latent representations simultaneously. The results show that our model performs alignment implicitly and improves the smoothness of the low dimensional representations.

AB - In this paper we present a model that is capable of learning alignments between high-dimensional data by exploiting low-dimensional structures. Specifically, our method uses a Gaussian process latent variable model (GP-LVM) to learn alignments and latent representations simultaneously. The results show that our model performs alignment implicitly and improves the smoothness of the low dimensional representations.

M3 - Paper

T2 - NIPS Workshop on Learning in High Dimensions with Structure

Y2 - 9 December 2016

ER -

Learning Alignments from Latent Space Structures

Abstract

Workshop

Access to Document

Projects

Centre for the Analysis of Motion, Entertainment Research and Applications (CAMERA)

Cite this