Sciweavers

229 search results - page 10 / 46
» Learning spatial relations in object recognition
Sort
View
CVPR
2001
IEEE
14 years 9 months ago
Learning Spatially Localized, Parts-Based Representation
In this paper, we propose a novel method, called local nonnegative matrix factorization (LNMF), for learning spatially localized, parts-based subspace representation of visual pat...
Stan Z. Li, XinWen Hou, HongJiang Zhang, QianSheng...
PCM
2010
Springer
200views Multimedia» more  PCM 2010»
13 years 6 months ago
A New Shape Descriptor for Object Recognition and Retrieval
Abstract. We present a new shape descriptor for measuring the similarity between shapes and exploit it in graphical object recognition and retrieval. By statistically integrating t...
Feng Su, Tong Lu, Ruoyu Yang
ICCV
2011
IEEE
12 years 7 months ago
Scene Recognition and Weakly Supervised Object Localization with Deformable Part-Based Models
Weakly supervised discovery of common visual structure in highly variable, cluttered images is a key problem in recognition. We address this problem using deformable part-based mo...
Megha Pandey, Svetlana Lazebnik
CVPR
2010
IEEE
14 years 9 days ago
Object Recognition as Ranking Holistic Figure-Ground Hypotheses
We present an approach to visual object-class recognition and segmentation based on a pipeline that combines multiple, holistic figure-ground hypotheses generated in a bottom-up,...
Fuxin Li, JoãCarreira, Cristian Sminchisescu
JMLR
2008
95views more  JMLR 2008»
13 years 7 months ago
Learning Similarity with Operator-valued Large-margin Classifiers
A method is introduced to learn and represent similarity with linear operators in kernel induced Hilbert spaces. Transferring error bounds for vector valued large-margin classifie...
Andreas Maurer