—We propose an approach for improving object recognition and localization using spatial kernels together with instance embedding. Our approach treats each image as a bag of insta...
The traditional subspace-based approaches to segmentation (often referred to as multi-body factorization approaches) provide spatial clustering/segmentation by grouping together po...
We present the application of a novel nonparametric approach to restoration and interpolation of medical images. The proposed approach is based on the notion of spatially adaptive...
Dynamical low-rank approximation is a differential-equation based approach to efficiently computing low-rank approximations to time-dependent large data matrices or to solutions o...
ended abstract looks forward at which shared concepts and approaches are shaping future research in the field of location privacy, as well as reflecting on the broader achievement...