In this paper, we represent human actions as short sequences of atomic body poses. The knowledge of body pose is stored only implicitly as a set of silhouettes seen from multiple ...
Abhijit S. Ogale, Alap Karapurkar, Yiannis Aloimon...
In this paper, we propose a novel Spatiotemporal Interest Point (MC-STIP) detector based on the coherent motion pattern around each voxel in videos. Our detector defines the local...
Abstract. Mobile and ubiquitous systems require task models for addressing the challenges of adaptivity and situation-aware assistance. Today, both challenges are seen as separate ...
Martin Giersich, Peter Forbrig, Georg Fuchs, Thoma...