The Zuzen framework is an intelligent tool set for assisting in the generation of machinima. With Zuzen, users that are novice cinematographers do not need to use complex movie-ma...
In this paper, we present a shadow removal technique which effectively eliminates a human shadow cast from an unknown direction of light source. A multi-cue shadow descriptor is p...
Many common objects have highly reflective metallic or painted finishes. Their appearance is primarily defined by the distortion the curved shape of the surface introduces in the ...
E. Tosun, Yotam I. Gingold, Jason Reisman, Denis Z...
In this paper, we propose a novel graph embedding method for the problem of lipreading. To characterize the temporal connections among video frames of the same utterance, a new di...
This video presents the working of a new algorithm/software called DelPSC that meshes piecewise smooth complexes in three dimensions with Delaunay simplices. Piecewise smooth comp...