How we design and evaluate for emotions depends crucially on what we take emotions to be. In affective computing, affect is often taken to be another kind of information - discret...
— Many application tasks require the cooperation of two or more robots. Humans are good at cooperation in shared workspaces, because they anticipate and adapt to the intentions a...
—Recovering the 3D shape of a nonrigid surface from a single viewpoint is known to be both ambiguous and challenging. Resolving the ambiguities typically requires prior knowledge...
Most approaches to classifying media content assume a fixed, closed vocabulary of labels. In contrast, we advocate machine learning approaches which take advantage of the millions...
Humans have an amazing ability to instantly grasp the overall 3D structure of a scene – ground orientation, relative positions of major landmarks, etc – even from a single ima...