This paper presents an approach to unsupervised segmentation of moving and static objects occurring in a video. Objects are, in general, spatially cohesive and characterized by lo...
Scene labeling research has mostly focused on outdoor scenes, leaving the harder case of indoor scenes poorly understood. Microsoft Kinect dramatically changed the landscape, show...
Many of the recently popular shape based category recognition methods require stable, connected and labeled edges as input. This paper introduces a novel method to find the most st...
Michael Donoser, Hayko Riemenschneider and Horst B...
Sequence matching techniques are effective for comparing two videos. However, existing approaches suffer from demanding computational costs and thus are not scalable for large-sca...
Abstract— We describe a framework for detecting and tracking continuous ”trails” in images and image sequences for autonomous robot navigation. Continuous trails are extended...