In the past, quantized local descriptors have been shown to be a good base for the representation of images, that can be applied to a wide range of tasks. However, current approac...
Image matching is a fundamental task for many applications of computer vision. Today it is very popular to represent two matched images as two bags of local descriptors, and the c...
In this paper, we propose a novel contextual descriptor which combines the contextual information and local appearance. Based on Gibbs distribution, a local descriptor is designed...
Yi Ouyang, Ming Tang, Jian Cheng, Jinqiao Wang, Ha...
We present an approach to detect anatomical structures by configurations of interest points, from a single example image. The representation of the configuration is based on Markov...
Most recent class-level object recognition systems work with visual words, i.e., vector quantized local descriptors. In this paper we examine the feasibility of a dataindependent ...