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:
-
-
(Preview, Accepted manuscript, pdf, 571.2KB, Terms of use)
-
- Publisher copy:
- 10.1007/978-3-540-85853-9_6
Authors
- 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
- Copyright holder:
- Springer
- Copyright date:
- 2008
- Rights statement:
- © Springer-Verlag Berlin Heidelberg 2008
- Notes:
- This paper was presented at the 5th International Workshop, Machine Learning for Multimodal Interaction (MLMI 2008), Utrecht, The Netherlands, September 2008. This is the accepted manuscript version of the paper. The final version is available online from Springer Nature at https://dx.doi.org/10.1007/978-3-540-85853-9_6
If you are the owner of this record, you can report an update to it here: Report update to this record