Conventional non-blind image deblurring algorithms involve natural image priors and maximum a-posteriori (MAP) estimation. As a consequence of MAP estimation, separate pre-process...
Human activity recognition and speech recognition appear to be two loosely related research areas. However, on a careful thought, there are several analogies between activity and ...
While most existing enhancement tools for photographs have universal auto-enhancement functionality, recent research [8] shows that users can have personalized preferences. In thi...
As having multiple images of an object is practically convenient nowadays, to jointly align them is important for subsequent studies and a wide range of applications. In this pape...
This paper addresses the problem of simultaneous tracking of multiple targets in a video. We first apply object detectors to every video frame. Pairs of detection responses from ...