Sciweavers

772 search results - page 21 / 155
» Constructing Visual Models with a Latent Space Approach
Sort
View
EMNLP
2010
14 years 11 months ago
Nouns are Vectors, Adjectives are Matrices: Representing Adjective-Noun Constructions in Semantic Space
We propose an approach to adjective-noun composition (AN) for corpus-based distributional semantics that, building on insights from theoretical linguistics, represents nouns as ve...
Marco Baroni, Roberto Zamparelli
ECCV
2010
Springer
15 years 6 months ago
Inferring 3D Shapes and Deformations from Single Views
Abstract. In this paper we propose a probabilistic framework that models shape variations and infers dense and detailed 3D shapes from a single silhouette. We model two types of sh...
UIST
1996
ACM
15 years 5 months ago
The Cage: Efficient Construction in 3D Using a Cubic Adaptive Grid
The Cage is an easy to use 3D grid. Built into a 3D modeler, it provides a visualized reference coordinate system that helps the user to orient himself in 3D space, and that suppo...
Patrick Baudisch
GRC
2010
IEEE
15 years 2 months ago
Learning Multiple Latent Variables with Self-Organizing Maps
Inference of latent variables from complicated data is one important problem in data mining. The high dimensionality and high complexity of real world data often make accurate infe...
Lili Zhang, Erzsébet Merényi
ICIP
2007
IEEE
16 years 3 months ago
Monocular Tracking 3D People By Gaussian Process Spatio-Temporal Variable Model
Tracking 3D people from monocular video is often poorly constrained. To mitigate this problem, prior knowledge should be exploited. In this paper, the Gaussian process spatio-temp...
Junbiao Pang, Laiyun Qing, Qingming Huang, Shuqian...