We describe a method for obtaining the principal objects, characters and scenes in a video by measuring the reoccurrence of spatial configurations of viewpoint invariant features....
In this paper, we present iBroker, an Intelligent Broker for ontology based publish/subscribe systems which syntactically and semantically match incoming OWL data to multiple user ...
We present a novel approach to tracking 2D human motion in uncalibrated monocular videos. Human motion usually exhibits timevarying patterns, and we propose to use locally learnt ...
We propose a new sequential, adaptive, quadratic-time algorithm for variable-rate lossy compression of memoryless sources at a fixed distortion. The algorithm uses approximate pat...
This paper investigates a new automated personal authentication technique using finger-knuckle-print (FKP) imaging. First, a specific data acquisition device is developed to captur...