Existing Digital Rights Management systems, initiatives like Creative Commons or research works as some digital rights ontologies provide limited support for content value chains m...
We propose a novel directed graphical model for label propagation in lengthy and complex video sequences. Given hand-labelled start and end frames of a video sequence, a variation...
Ignas Budvytis, Vijay Badrinarayanan, Roberto Cipo...
Abstract--The paper proposes a biologically-inspired cognitive agent model, known as FALCON-X, based on an integration of the Adaptive Control of Thought (ACT-R) architecture and a...
Many well-known existing image matching methods are based on local texture analysis, and consequently have difficulty handling low-textured 3D objects, such as those man-made buil...
Optical flow estimation is one of the main subjects in computer vision. Many methods developed to compute the motion fields are built using standard heuristic formulation. In this...