Sciweavers

100 search results - page 3 / 20
» Sparse Flexible Models of Local Features
Sort
View
CVPR
2007
IEEE
16 years 3 months ago
Flexible Object Models for Category-Level 3D Object Recognition
Today's category-level object recognition systems largely focus on fronto-parallel views of objects with characteristic texture patterns. To overcome these limitations, we pr...
Akash Kushal, Cordelia Schmid, Jean Ponce
COMSIS
2010
14 years 10 months ago
3D point pattern matching based on spatial geometric flexibility
We propose a new method for matching two 3D point sets of identical cardinality with global similarity but local non-rigid deformations and distribution errors. This problem arises...
Xiaopeng Wei, Xiaoyong Fang, Qiang Zhang, Dongshen...
ICASSP
2008
IEEE
15 years 7 months ago
Sparse and shift-invariant feature extraction from non-negative data
In this paper we describe a technique that allows the extraction of multiple local shift-invariant features from analysis of non-negative data of arbitrary dimensionality. Our app...
Paris Smaragdis, Bhiksha Raj, Madhusudana V. S. Sh...
ICMLA
2009
14 years 11 months ago
Regularizing the Local Similarity Discriminant Analysis Classifier
Abstract--We investigate parameter-based and distributionbased approaches to regularizing the generative, similarity-based classifier called local similarity discriminant analysis ...
Luca Cazzanti, Maya R. Gupta
CLOR
2006
15 years 5 months ago
A Sparse Object Category Model for Efficient Learning and Complete Recognition
We present a "parts and structure" model for object category recognition that can be learnt efficiently and in a weakly-supervised manner: the model is learnt from examp...
Robert Fergus, Pietro Perona, Andrew Zisserman