—This paper presents a procedure for automatic extraction and segmentation of a class-specific object (or region) by learning class-specific boundaries. We describe and evaluat...
Active learning methods aim to select the most informative unlabeled instances to label first, and can help to focus image or video annotations on the examples that will most impr...
This paper proposes a system to relate objects in an image using occlusion cues and arrange them according to depth. The system does not rely on any a priori knowledge of the scen...
Many methods for motion computation and object tracking are based on the Lucas-Kanade (LK) framework [1]. We present a method which substantially speeds up the LK approach while p...
In a previous experiment, we have studied the preference judgement of pictorial images with image experts and naive observers. We asked image experts to improve pictorial images t...
Clotilde Boust, Ferruccio Cittadini, Mohamed Ben C...