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...
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...
This paper brings together two recent developments in image analysis. We consider a new mathematical framework that provides illumination invariant descriptors for face detection....
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, ...
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...