Search: onr:"swepub:oai:DiVA.org:kth-50656" >
Ambiguity modeling ...
Ambiguity modeling in latent spaces
-
Ek, Carl Henrik (author)
-
Rihan, J. (author)
-
Torr, P. (author)
-
show more...
-
Rogez, G. (author)
-
Lawrence, Neil D. (author)
-
show less...
- BERLIN : SPRINGER-VERLAG BERLIN, 2008
- 2008
- English.
-
In: MACHINE LEARNING FOR MULTIMODAL INTERACTION, PROCEEDINGS. - BERLIN : SPRINGER-VERLAG BERLIN. ; , s. 62-73
- Related links:
-
https://urn.kb.se/re...
Abstract
Subject headings
Close
- 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 Lire 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 Lire 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.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)
Keyword
- VARIABLE MODELS
- HUMAN POSE
Publication and Content Type
- ref (subject category)
- kon (subject category)
To the university's database