Conference item icon

Conference item

Ambiguity modeling in latent spaces

Abstract:
We are interested in the situation where we have two or more representations of an underlying phenomenon. In particular we are interested in the scenario where the representation are complementary. This implies that a single individual representation is not sufficient to fully discriminate a specific instance of the underlying phenomenon, it also means that each representation is an ambiguous representation of the other complementary spaces. In this paper we present a latent variable model capable of consolidating multiple complementary representations. Our method extends canonical correlation analysis by introducing additional latent spaces that are specific to the different representations, thereby explaining the full variance of the observations. These additional spaces, explaining representation specific variance, separately model the variance in a representation ambiguous to the other. We develop a spectral algorithm for fast computation of the embeddings and a probabilistic model (based on Gaussian processes) for validation and inference. The proposed model has several potential application areas, we demonstrate its use for multi-modal regression on a benchmark human pose estimation data set.
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1007/978-3-540-85853-9_6

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Role:
Author
ORCID:
0009-0006-0259-5732


Publisher:
Springer Nature
Host title:
Machine Learning for Multimodal Interaction: 5th International Workshop, MLMI 2008
Pages:
62-73
Series:
Lecture Notes in Computer Science
Series number:
5237
Publication date:
2008-01-01
Event title:
5th International Workshop, Machine Learning for Multimodal Interaction (MLMI 2008)
Event location:
Utrecht, The Netherlands
Event start date:
2008-09-08
Event end date:
2008-09-10
DOI:
EISSN:
1611-3349
ISSN:
0302-9743
ISBN:
9783540858522


Language:
English
Keywords:
Pubs id:
971548
Local pid:
pubs:971548
Deposit date:
2024-05-21

Terms of use



Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP