Today's category-level object recognition systems largely focus on fronto-parallel views of objects with characteristic texture patterns. To overcome these limitations, we pr...
In this paper, we present a system that integrates fully automatic scene geometry estimation, 2D object detection, 3D localization, trajectory estimation, and tracking for dynamic...
Bastian Leibe, Nico Cornelis, Kurt Cornelis, Luc J...
We present a novel method for the discovery and detection of visual object categories based on decompositions using topic models. The approach is capable of learning a compact and...
Recognition systems have generally treated specular highlights as noise. We show how to use these highlights as a positive source of information that improves recognition of shiny...
Margarita Osadchy, David W. Jacobs, Ravi Ramamoort...
Abstract. This paper presents a prototype system for pedestrian detection on-board a moving vehicle. The system uses a generic two-step approach for efficient object detection. In ...