This study develops a procedure for automatic extraction and segmentation of a class-specific object (or region) by learning class-specific boundaries. We present and evaluate t...
Abstract. This paper presents a unified approach to crowd segmentation. A global solution is generated using an Expectation Maximization framework. Initially, a head and shoulder d...
Gianfranco Doretto, Jens Rittscher, Nils Krahnstoe...
Abstract. We describe a visual communication application for a dark, theaterlike interactive virtual simulation training environment. Our system visually estimates and tracks the b...
This paper presents a bottom-up approach that combines audio and video to simultaneously locate individual speakers in the video (2-D source localization) and segment their speech ...
Automatically understanding events happening at a site is the ultimate goal of visual surveillance system. This paper investigates the challenges faced by automated surveillance s...