While great strides have been made in detecting and localizing specific objects in natural images, the bottom-up segmentation of unknown, generic objects remains a difficult chall...
We combine detection and tracking techniques to achieve robust 3?D motion recovery of people seen from arbitrary viewpoints by a single and potentially moving camera. We rely on d...
Andrea Fossati, Miodrag Dimitrijevic, Vincent Lepe...
We propose multiple description (MD) video coders which use motion compensated predictions. Our MD video coders utilize MD transform coding and three separate prediction paths at ...
Amy R. Reibman, Hamid Jafarkhani, Yao Wang, Michae...
—Motion information is an important cue for a robot to separate foreground moving objects from the static background world. Based on the observation that the motion of the backgr...
In this paper, we present a temporal candidate generation scheme that can be applied to motion estimators in Scalable Video Codecs (SVCs). For bidirectional motion estimation, usu...
Marijn J. H. Loomans, Cornelis J. Koeleman, Peter ...