We present techniques for rendering and animation of realistic scenes by analyzing and training on short video sequences. This work extends the new paradigm for computer animation...
We propose a joint representation and classification framework that achieves the dual goal of finding the most discriminative sparse overcomplete encoding and optimal classifier p...
We have incorporated interactive skills into an active gaze tracking system. Our active gaze tracking system can identify an object in a cluttered scene that a person is looking a...
Background: Life Science Identifiers (LSIDs) are persistent, globally unique identifiers for biological objects. The decentralised nature of LSIDs makes them attractive for identi...
We propose a novel solution to object detection, localization and pose estimation with applications in robot vision. The proposed method is especially applicable when the objects ...