We propose a framework for general multiple target tracking, where the input is a set of candidate regions in each frame, as obtained from a state of the art background learning, ...
Abstract. One of the most difficult aspects of visual object tracking is the handling of occlusions and target appearance changes due to variations in illumination and viewing dir...
Bogdan Georgescu, Dorin Comaniciu, Tony X. Han, Xi...
Abstract. In this paper we introduce a new salient object segmentation method, which is based on combining a saliency measure with a conditional random field (CRF) model. The propo...
Esa Rahtu, Juho Kannala, Mikko Salo, Janne Heikkil...
We present a method for synthesizing animations of autonomous space, water, and land-based vehicles in games or other interactive simulations. Controlling the motion of such vehic...
Abstract. We propose a novel Multiple Instance Learning (MIL) framework to perform target localization from image sequences. The proposed approach consists of a softmax logistic re...