In this paper we propose a framework for learning a regression function form a set of local features in an image. The regression is learned from an embedded representation that re...
We couple occlusion modeling and multi-frame motion estimation to compute dense, temporally extended point trajectories in video with significant occlusions. Our approach combine...
Searching for optimal ways in a network is an important task in multiple application areas such as social networks, co-citation graphs or road networks. In the majority of applicat...
The constraint language for lambda structures (CLLS) can model lambda terms that are known only partially. In this paper, we introduce beta reduction constraints to describe beta r...
Manuel Bodirsky, Katrin Erk, Alexander Koller, Joa...
The feedback loop for temporal prediction of traditional implementations of an MPEG-compliant video coder requires conversion of images from the spatial domain to the transform do...