Sciweavers

111 search results - page 20 / 23
» Discriminant Additive Tangent Spaces for Object Recognition
Sort
View
ICCV
2011
IEEE
12 years 8 months ago
Kinecting the dots: Particle Based Scene Flow from depth sensors
The motion field of a scene can be used for object segmentation and to provide features for classification tasks like action recognition. Scene flow is the full 3D motion fiel...
Simon Hadfield, Richard Bowden
KES
2005
Springer
14 years 1 months ago
3-D Building Reconstruction Using IKONOS Multispectral Stereo Images
This paper presents an effective strategy to extract the buildings and to reconstruct 3-D buildings using high-resolution multispectral stereo satellite images. Proposed scheme con...
Hong-Gyoo Sohn, Choung-Hwan Park, Joon Heo
AAAI
2010
13 years 5 months ago
Multilinear Maximum Distance Embedding Via L1-Norm Optimization
Dimensionality reduction plays an important role in many machine learning and pattern recognition tasks. In this paper, we present a novel dimensionality reduction algorithm calle...
Yang Liu, Yan Liu, Keith C. C. Chan
JMLR
2012
11 years 11 months ago
On Nonparametric Guidance for Learning Autoencoder Representations
Unsupervised discovery of latent representations, in addition to being useful for density modeling, visualisation and exploratory data analysis, is also increasingly important for...
Jasper Snoek, Ryan Prescott Adams, Hugo Larochelle
CRV
2011
IEEE
254views Robotics» more  CRV 2011»
12 years 8 months ago
Wavelet Model-based Stereo for Fast, Robust Face Reconstruction
—When reconstructing a specific type or class of object using stereo, we can leverage prior knowledge of the shape of that type of object. A popular class of object to reconstru...
Alan Brunton, Jochen Lang, Eric Dubois, Chang Shu