We propose a new learning method which exploits temporal consistency to successfully learn a complex appearance model from a sparsely labeled training video. Our approach consists...
Matching based on local brightness is quite limited, because
small changes on local appearance invalidate the
constancy in brightness. The root of this limitation is its
treatme...
Ying Wu (Northwestern University), Jialue Fan (Nor...
In this paper we propose a new method for human action categorization by using an effective combination of a new 3D gradient descriptor with an optic flow descriptor, to represent...
Traditional techniques for tracking non-rigid objects such as optical flow, correlation, active contours or color, can not deal with situations where image changes are not due to ...
Communications devices intended for use in securitycritical applications must be rigorously evaluated to ensure they preserve data confidentiality. This process includes tracing t...