We identify here various kinds of failure conditions and robustness issues that arise in context-aware pervasive computing applications. Such conditions are related to failures in...
This paper presents a new approach to computing dense depth and motion estimates from multiple images. Rather than computing a single depth or motion map from such a collection, w...
We propose a film directing semantics taxonomy grounded upon cinematographic elements to unlock the immense potential for motion indexing in the subtler and much neglected film do...
This paper presents a learning based approach to tracking articulated human body motion from a single camera. In order to address the problem of pose ambiguity, a one-to-many mappi...
This paper extends the classical warping-based optical flow method to achieve accurate flow in the presence of spatially-varying motion blur. Our idea is to parameterize the app...