Metric learning is a fundamental problem in computer vision. Different features and algorithms may tackle a problem from different angles, and thus often provide complementary inf...
Bo Wang, Jiayan Jiang, Wei Wang 0028, Zhi-Hua Zhou...
— We present a probabilistic framework for visual correspondence, inertial measurements and Egomotion. First, we describe a simple method based on Gabor filters to produce corre...
Document clustering techniques have been applied in several areas, with the web as one of the most recent and influent. Both general-purpose and text-oriented techniques exist and...
We propose a new voxel similarity measure which utilises local image structure as well intensity information. Gaussian scale space derivatives are used to provide the structural in...
Mark Holden, Lewis D. Griffin, Nadeem Saeed, Derek...
Spatio-temporal interest region detectors can be used in the analysis of video to determine sparse, informative regions as candidates for feature extraction. In this paper we comp...