We propose a flexible summarization framework for teamsport videos, which is able to integrate both the knowledge about displayed content (e.g. level of interest, type of view, et...
We propose a novel algorithm for segmenting multiple motions of different types from point correspondences in multiple affine or perspective views. Since point trajectories associ...
Scientific data-sets often come with an inherent hierarchical structure such as functional substructures within organs. In this work we propose a new visualization approach for vo...
Jean-Paul Balabanian, Ivan Viola, Martin Ystad, Ar...
In this paper, we address the issue of joint space-time segmentation of image sequences. Typical approaches to such segmentation consider two image frames at a time, and perform t...
Abstract. Compressive sensing (CS) is an emerging field that provides a framework for image recovery using sub-Nyquist sampling rates. The CS theory shows that a signal can be reco...
Volkan Cevher, Aswin C. Sankaranarayanan, Marco F....