Sciweavers

8 search results - page 1 / 2
» Gradient-based learning of higher-order image features
Sort
View
ICIP
2001
IEEE
14 years 6 months ago
Higher order autocorrelations for pattern classification
The use of higher-order local autocorrelations as features for pattern recognition has been acknowledged since many years, but their applicability was restricted to relatively low...
Vlad Popovici, Jean-Philippe Thiran
ICCV
2011
IEEE
12 years 4 months ago
Gradient-based learning of higher-order image features
Recent work on unsupervised feature learning has shown that learning on polynomial expansions of input patches, such as on pair-wise products of pixel intensities, can improve the...
Roland Memisevic
ICPR
2006
IEEE
14 years 5 months ago
Fast, Illumination Insensitive Face Detection Based on Multilinear Techniques and Curvature Features
This paper brings together two recent developments in image analysis. We consider a new mathematical framework that provides illumination invariant descriptors for face detection....
Christian Bauckhage, Thomas Käster
CVPR
2009
IEEE
14 years 11 months ago
Efficient Kernels for Identifying Unbounded-Order Spatial Features
Higher order spatial features, such as doublets or triplets have been used to incorporate spatial information into the bag-of-local-features model. Due to computational limits, ...
Yimeng Zhang (Carnegie Mellon University), Tsuhan ...
CVPR
2010
IEEE
13 years 10 months ago
Image Retrieval via Probabilistic Hypergraph Ranking
In this paper, we propose a new transductive learning framework for image retrieval, in which images are taken as vertices in a weighted hypergraph and the task of image search is...
Yuchi Huang, Qingshan Liu, Shaoting Zhang, Metaxas...