This paper presents a new kernel method for appearance-based object recognition, highly robust to noise and occlusion. It consists of a fully connected Markov Random Field that in...
We describe a linear-time algorithm that recovers absolute camera orientations and positions, along with uncertainty estimates, for networks of terrestrial image nodes spanning hun...
A novel approach is proposed to analyzing and tracking the motion of structured deformable shapes, which consist of multiple correlated deformable subparts. Since this problem is ...
Abstract. Recently, impressive results have been reported for the detection of objects in challenging real-world scenes. Interestingly however, the underlying models vary greatly e...
Automatic segmentation and classification of recorded meetings provides a basis towards understanding the content of a meeting. It enables effective browsing and querying in a me...