We propose a new technique for fusing multiple cues to robustly segment an object from its background in video sequences that suffer from abrupt changes of both illumination and p...
Francesc Moreno-Noguer, Alberto Sanfeliu, Dimitris...
In this paper, we present a patch-based variational Bayesian framework of image processing using the language of factor graphs (FGs). The variable and factor nodes of FGs represen...
This paper proposes a data driven image segmentation algorithm, based on decomposing the target output (ground truth). Classical pixel labeling methods utilize machine learning al...
This paper presents a system for video object generation and selective encoding with applications in surveillance, mobile videophones, and automotive industry. Object tracking and...
Alessio Del Bue, Dorin Comaniciu, Visvanathan Rame...
The analysis of video data targeting the identification of relevant objects and the extraction of associated descriptive characteristics will be the enabling factor for a number o...