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

60 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

Projects

1 Active

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

Cosker, D., Campbell, N., Fincham Haines, T., Hall, P., Kim, K. I., Lutteroth, C., O'Neill, E., Richardt, C. & Yang, Y.

Engineering and Physical Sciences Research Council

1/09/15 → 28/02/21

Project: Research council

Cite this

Kazlauskaite, I., Ek, C. H., & Campbell, N. (2016). Learning Alignments from Latent Space Structures. Paper presented at NIPS Workshop on Learning in High Dimensions with Structure, .

@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 -