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 address the problem of estimating human body pose from a single image with cluttered background. We train multiple local linear regressors for estimating the 3D pose f...
This paper overviews a new gesture recognition framework
based on learning local motion signatures (LMSs) introduced
by [1]. After the generation of these LMSs computed
on one i...
Growing on-chip wire delays are motivating architectural features that expose on-chip communication to the compiler. EDGE architectures are one example of communication-exposed mi...
Katherine E. Coons, Xia Chen, Doug Burger, Kathryn...
This paper addresses the problem of recognizing freeform 3D objects in point clouds. Compared to traditional approaches based on point descriptors, which depend on local informati...
Bertram Drost, Markus Ulrich, Nassir Navab, Slobod...